#graph

AgentDrive is a cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, and LangGraph. 20 MCP tools: file CRUD, semantic recall over workspace artifacts, run logging, cross-agent attribution, comments, and shares. Connect to the hosted server at https://mcp.agentdrive.sh/mcp with an Authorization: Bearer key, or run locally via npx @adrive/mcp-server. Free tier (1 GB + 10k embeddings) at https://app.agentdrive.sh — no credit card.

Search 600,000+ CS/AI/ML papers with citation-graph traversal, full-text extraction, embeddings, and BibTeX export, inside Claude Code, Cursor, and other MCP clients.

Build structured intent specs through Socratic AI conversation (zero-config), or connect to your Pathmode workspace for strategic context, dependency graphs, and team governance. v1.5.0 ships with a Claude Code skill pack — 7 auto-triggering skills (compile-intent, grill-intent, verify-intent, review-against-intent, split-intent-to-issues, handoff-intent, setup-pathmode-workflow) installable via `npx @pathmode/mcp-server install-skills`. Makes agents build the right thing, not just any thing.

Turns a company domain or name into its LinkedIn company URL with a confidence score, headcount, industry, and HQ. Part of the Mamba Labs signal toolkit.

MCP server connecting AI agents (Claude, Cursor, Windsurf) to real geographic data: 261 countries, 5.2M cities, rankings, comparisons, and 9 Bamwor indices. Free tier, no API key required. Powered by Bamwor.

Read & write your Heuresis idea graph. Create concepts, run TRIZ/C-K/ASIT operators, pull in prior-art research, and export, all from inside your AI assistant.

Drillr is the official financial MCP for AI agents. One hosted endpoint exposes **9 tools** spanning standardized financial data (90+ SQL tables: statements, ratios, earnings, insider, ownership), paragraph-level SEC filing semantic search across 10-K/10-Q/20-F/6-K/S-1/DEF 14A, live cross-asset signals across ~6,900 tickers, and 24 alt-data categories spanning the AI value chain (energy, chips, compute pricing, model adoption, app usage). Coverage: US + Japan equities plus ADRs of global companies; fundamentals back to the 1980s. Built and maintained by Little Grebe Inc.

MeiGen AI Design Assistant - MCP Server A powerful visual creativity MCP Server designed for AI image and video generation. This server integrates 7 core tools and refined skills to help LLMs and users quickly generate high-quality, production-ready prompts. It supports style referencing for Midjourney, GPT Image, Seedance, and other models, automatic prompt optimization, variant suggestions, and negative prompt refinement. Perfect for designers, marketers, content creators, and AI enthusiasts. Significantly improves prompt engineering efficiency and enables professional-grade AI visuals even for non-experts.

One agent solves it, every agent learns. bhived is a shared, self-correcting memory network for AI agents — verified instructions, mistake warnings, and reusable skills that any agent can read and write back to. Plus on-demand MCP discovery and activation. Install with "npx bhived setup" and it works in Claude Code, Cursor, Windsurf, Cline, Codex, Antigravity, OpenClaw, and 7 more.

Unified inbox MCP for WhatsApp, Telegram, Email, voice — read/send messages, search conversations, manage contacts, query knowledge graph, and trigger AI agents through natural language.

Agent-native B2B lead enrichment. Search, score, and subscribe to enriched company data with firmographics, tech stack signals, and buying intent.

Open-source, self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 15 parsers, FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free. Index everything in your project — code, docs, PDFs, legal texts, research, data — and your agent finds the right context instantly. No hallucinations. No cloud. No API costs.

The first production MCP server with NIST FIPS 204 post-quantum receipts. Every AI agent tool call is policy-gated, hybrid-signed (Ed25519 + ML-DSA-65), and forensically provable — offline, forever. Fail-closed architecture: if the Trust Gate backend is unreachable, every decision returns allow:false. Defended against 15 CVEs including CVE-2026-25253 (OpenClaw), Invariant Labs Tool Poisoning, and Salt Typhoon HNDL. EU AI Act Article 50 native compliance.

The simplest, most complete, end-to-end agent-managed company brain. One workspace where humans and any MCP-compatible AI agent (Claude, Cursor, Windsurf, ChatGPT, Gemini, and more) co-author living documents (Markdown-native with a rich superset on top), 40+ visual diagrams (Mermaid, BPMN 2.0, D2, PlantUML, GraphViz, ELK, Excalidraw freehand), plans, timelines, tasks, improvements, and a self-learning Knowledge Graph that IS the company brain. Lean, fast, secure, and affordable — flexible enough for one person organising a personal mind, through to small businesses, growing businesses, and enterprise. 163 MCP tools across 16 categories let an agent drive end-to-end: sign-up → billing → org/workspace/project → members → teams → permissions → brain scope → docs → diagrams → plans, all without a human touching the UI. Auth: OAuth 2.1 with Dynamic Client Registration, or Bearer API key with prefix sta_. Public repo: https://github.com/stablebaseline/mcp · Docs: https://stablebaseline.io/docs/mcp

The simplest, most complete, end-to-end agent-managed company brain. One workspace where humans and any MCP-compatible AI agent (Claude, Cursor, Windsurf, ChatGPT, Gemini, and more) co-author living documents (Markdown-native with a rich superset on top), 40+ visual diagrams (Mermaid, BPMN 2.0, D2, PlantUML, GraphViz, ELK, Excalidraw freehand), plans, timelines, tasks, improvements, and a self-learning Knowledge Graph that IS the company brain. Lean, fast, secure, and affordable — flexible enough for one person organising a personal mind, through to small businesses, growing businesses, and enterprise. 163 MCP tools across 16 categories let an agent drive end-to-end: sign-up → billing → org/workspace/project → members → teams → permissions → brain scope → docs → diagrams → plans, all without a human touching the UI. Auth: OAuth 2.1 with Dynamic Client Registration, or Bearer API key with prefix sta_.

MCP server for Microsoft To Do via Microsoft Graph. MSAL device code flow, no client secret needed.

Verbatim persistent memory for LLM sessions. Kills cross-chat amnesia. MIT, local-first.

Ganglia indexes your project into a call graph and exposes 73 semantic tools — code_get, code_callers, code_impact, code_propagate, code_apply_batch with one-click revert, code_safe_move, deliberation chain, smart LLM-backed digests, cross-session memory, and more. Works with Claude Code, Cursor, Windsurf, Continue, Cline, Goose. Languages: TypeScript, JavaScript, Rust, Python, Go, PHP. Free during public beta. Token savings: 80–95% vs raw file-reading patterns.

Audit-grade memory backbone for agent teams. Bi-temporal facts (event time + transaction time, with recall(as_of=...) replay), 6-step deterministic retrieval (no LLM in the critical path), conversation ingest with speaker-locked dual-pass extraction, per-tenant Postgres row-level security, and Ed25519-signed provenance. Postgres + pgvector + Neo4j defaults; ArangoDB / DynamoDB / Cosmos / AlloyDB also supported. Listed on the official MCP Registry as io.github.bolnet/attestor.

Read and write structured notes, projects, tasks, decisions, blockers, and stakeholders in a personal knowledge graph. Traverse entity relationships across projects. Query by project, entity type, date range, or keyword. Create and manage AI agent tasks. Access daily briefings and project health summaries. Returns structured JSON. Supports 10 tools, 7 resources, and 6 prompts.

Open Ephemeris is a production-grade MCP server that gives Claude, ChatGPT, Gemini, Cursor, and any MCP-compatible agent direct access to real astronomical data. Over 100 tools cover the full range of astrological traditions: natal chart calculation, transit and progression forecasting, synastry, astrocartography ACG lines, Human Design body graph, BaZi four pillars, eclipse windows, lunar phases, planetary hours, and fixed star positions. All positions are computed at request time from JPL DE440 — accurate to arc-second precision. No hallucinated positions. No astronomy math in your application code. Free tier available.

Cryptographic audit trail for AI agents via Model Context Protocol. Every AI decision signed Ed25519, hash-chained, tamper-proof. AISS-1.0 compliant. Post-quantum ready. Compliance-ready for SEC, FINRA, GDPR, HIPAA.

GitLab MCP Server in Go for AI assistants: stdio/HTTP/OAuth access to GitLab REST/GraphQL, 1006 self-managed or 1011 GitLab.com+Orbit operations, 32/47/48 meta-tools, 3-tool dynamic low-token search/describe/execute mode, 46 resources and 38 prompts.

Your AI agents don't understand your codebase. Upgrade from text search to code understanding. AI coding agents waste most of their context window grepping files and guessing at code structure. Constellation gives them a persistent, team-wide knowledge graph of your codebase (symbol search, dependency graphs, impact analysis) delivered via MCP so every token goes toward reasoning, not discovery.

Memtrace — Structural Memory for AI Coding Agents The Problem Every AI coding agent — Claude Code, Cursor, Codex, Copilot — starts each turn completely blank. It re-reads raw source files and re-derives the full call graph, type hierarchy, and import tree from scratch on every single invocation. That structural rework burns 60–90% of the context window before any real reasoning begins. Less than 5% of tokens in a typical agentic coding session contribute genuine new intelligence. The rest is expensive, redundant noise — and it compounds: accuracy drops 40% as sessions grow, stale context crowds out signal, and summaries strip out the structural relationships agents need most. The Solution Memtrace is a bi-temporal structural memory layer that turns your codebase into a live, queryable knowledge graph — compiled from the AST, not guessed from embeddings. Every function, class, interface, and API endpoint becomes a typed node with deterministic relationships. Every file save becomes a queryable episode with timestamps, so agents can reason about structure, detect regressions, and time-travel through their own work without re-reading anything. One Rust binary. Zero configuration. Five-minute install. What agents can do with it Find callers, callees, and dependencies instantly — no file scanning, no token waste Compute blast radius before making a change — know exactly what breaks before anything is touched Detect structural drift between sessions — catch regressions the moment they happen, not at PR review Time-travel through code evolution — query any prior state of any symbol, not just git commits Search across the full codebase with hybrid retrieval — BM25 full-text + HNSW vector + graph traversal fused in one query Map API topology across services — cross-repo HTTP call graphs, dependency chains, dead endpoint detection Benefits −90% token cost on structural queries (Mem0) +26% accuracy on multi-step agentic tasks (Mem0) −91% p95 latency on structural lookups vs. RAG baselines +32.8% SWE-bench bug-fix success rate when agents have graph context (RepoGraph) 200–800ms per-save re-indexing — every file save is a queryable episode in under a second 40+ MCP tools covering indexing, search, relationships, impact analysis, temporal evolution, API topology, graph algorithms, and direct Cypher queries 12 languages + 3 IaC formats supported via Tree-sitter grammars Local-first, closed-source Rust — code never leaves the machine, no account required, no telemetry

Persistent cloud memory for AI coding agents. 14 MCP tools — store, recall, semantic search, knowledge graph. Works with Claude Code, Cursor, Windsurf, OpenClaw. One config file, zero SDK.

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware. Key features: . Semantic search (find memories by meaning, not keywords) . Per-agent API keys with granular permissions . 3D constellation viewer with live agent activity . File vault (attach real documents to memories) . CSV audit log (full transparency on every agent action) . Pre-Strata history import (your memory doesn't start at install day) . Global MCP kill switch (emergency brake, only a human can undo) . Automatic deduplication . 10 structured thought types . Backend using PostgreSQL . Runs on a Raspberry Pi Always on, always local, always yours.

Intelligent code knowledge graph for AI coding agents. Gives agents a persistent, queryable knowledge graph with search, call tracing, and agent write-back. 71% cheaper, 72% faster than baseline Grep+Read.

Tentra gives your AI coding agent memory. The code-graph indexer walks your repository with Tree-sitter locally, extracts symbols and call edges, and stores them in a persistent queryable graph. On the tentra monorepo we measured 99.4% token reduction (156.8× ratio) across 8 "where is X implemented?" queries — 114,644 tokens via file re-read vs 731 tokens via graph query. Uses the "agent-as-LLM" pattern — the Claude/Cursor/Codex agent you already have does the semantic extraction, so there is zero LLM cost on Tentra's side and no API key setup for end users. Also includes an architecture workspace with 9 MCP tools for diagrams and 14-framework code export.

Control Facebook & Instagram Ads from Claude, ChatGPT, Cursor, or any MCP-compatible agent. Direct Meta Graph API v24.0 wrapper with 32 tools — no backend required, just bring your own Meta access token. Auto-batches bulk ops, pre-flight ads_volume checks, PBIA auto-provisioning, enhanced error messages.

Access Versium's B2B2C identity graph directly through your AI agent. Generate targeted lead lists, enrich records with contact and firmographic data, validate emails, and size audiences — all through natural language. No manual exports or API coding required. Requires an active Versium REACH subscription with API access.

Open-source AI memory layer that connects all your AI tools and notes into a single living knowledge graph. Memories link automatically, fade when irrelevant, and surface hidden connections. Your AI receives a complete profile at every conversation start. Graph-navigating recall follows links between memories on demand. Background metabolism with memory decay, divergent scanning, and crystal emergence. Works with Claude Code, Cursor, Windsurf, Codex, and any MCP-compatible tool. Syncs with Obsidian, Logseq, and Apple Notes. 100% local — single SQLite file, no cloud, no vendor lock-in.

Astronomical ephemeris and Vedic astrology MCP server. 7 tools for AI agents: natal charts, dashas, vargas, transits, muhurta, graph emit (Cypher/SurrealQL/JSON-LD), and chart descriptions. Sub-arcsecond precision, 44 ayanamsha systems, 10 house systems, 50 yogas, 27 nakshatras. Clean-room Rust implementation.

Cryptographic identity, policy enforcement, trust scoring, and tamper-proof audit trails for AI agents. Register agents, track signed events, check policies, and get trust profiles — all from Claude, Cursor, or Windsurf. OWASP Agentic Top 10 compliant.

Structured business ontology giving AI agents deterministic access to institutional reasoning — 18 MCP tools, Dolt backend, 0% → 100% "why?" recall vs Markdown+RAG.

1 MCP server, 13 databases, zero config. Connect AI agents to PostgreSQL, MySQL, MongoDB, SQLite, Oracle, SQL Server, DB2, SAP HANA, MariaDB, CockroachDB, Cloud Spanner, HSQLDB, Sybase. 15 tools per entity + 4 AI prompts. Auth + RBAC included. 11 transports: REST, GraphQL, gRPC, WebSocket, SSE, tRPC, MCP, OData, Arrow Flight, JSON-RPC, NATS.

Save tokens while coding — your AI agent gets structured code context, not file dumps. CodeWeave is an MCP server that gives AI agents structured code intelligence instead of dumping entire files into context. Your agent queries local indexes — AST, call graph, type graph, and hybrid semantic search — and gets back only what it needs. The result: less token waste, more relevant context, better coding decisions. It supports 7 languages (Python, TypeScript, JavaScript, Go, Rust, Java, C#) with a 6-stage hybrid search pipeline combining vector embeddings, full-text search, and structural density scoring. Everything runs locally with zero external dependencies beyond Ollama for embeddings. Monorepo and git worktree support included. A file watcher keeps indexes current as code changes — no manual reindexing needed. ATTENTION: Run "npx @codeweave/mcp" in your project directory first. The setup wizard handles everything for you. At first, it may take some time. INFO: Exhaustively tested on large Java, C#, JavaScript, TypeScript, React codebases. Contributions and feedback are welcome.

Munin is a high-performance, pragmatic memory layer for AI agents (Cursor, Claude Code, OpenClaw, Gemini CLI,...). Unlike other solutions, Munin focuses on developer productivity with: - **Multi-Project Support:** Isolate memories into separate "brains" (Context Cores). - **GraphRAG:** Automatically builds a knowledge graph from your context. - **Sub-200ms Search:** Blazing fast Hybrid & Semantic search. - **Privacy:** Zero-knowledge client-side encryption (E2EE) support. - **Pricing:** FREE FOREVER for the base tier (Pro and Elite Plan start from $1.6/m).

Persistent memory, knowledge graph, governed actions, and runtime orchestration for AI agents. 107 tools. Works locally with zero-config SQLite(no API key needed) or connects to Novyx Cloud for the full surface. Install: uvx novyx-mcp

Persistent AI memory backend with semantic search and knowledge graph. Stores episodic, semantic, and procedural memories in SQLite and retrieves the most relevant ones using vector similarity and graph traversal. All embeddings run locally, with no API keys required.

Monitor and operate Dagster instances with AI agents. 19 tools for runs, assets, jobs, schedules, sensors, and instance health. Supports multi-environment, cross-version compatibility, and write operations (launch, terminate, reload).

Generate complete design token systems from a hex color — OKLCH-derived, WCAG-validated, multi-format

Paid MCP server that evaluates typography accessibility beyond what axe and Lighthouse catch. $0.05 USDC per evaluation via x402 on Base mainnet.

Persistent memory for AI agents. 72 MCP tools for remember, recall, rollback, audit, knowledge graph, context spaces, eval, cortex, replay, governed actions, and more. Pairs with CLAUDE.md to give Claude Code shared memory across sessions and agents. Works locally with zero config (SQLite) or connects to Novyx Cloud for teams.

Geographic data for AI agents — 250+ countries, states, cities, IP geolocation, and live exchange rates (161 currencies) updated every 4 hours.

Tamper-evident cryptographic audit trail for LLM outputs. Compliance logging for AI agent decisions. Tools: dcl_commit, dcl_verify, dcl_get_chain, dcl_report. Requires API key from fronesislabs.com

Instagram MCP server — 23 tools for the Instagram Graph API. Manage posts, comments, DMs, stories, hashtags, reels, carousels, and analytics via Claude.

Read+write MCP server for Zotero with full write support — create items, manage collections, find and merge duplicates, import BibTeX

Cryptographic runtime governance for AI agents. 20 tools. Sealed policy artifacts, continuous measurement, tamper-evident proof. Ed25519 + SHA-256.

A local memory engine for AI agents. Stores conversation episodes, consolidates knowledge through a neuroscience-inspired lifecycle, and builds a personal knowledge graph with emergent categories, preferences, and semantic recall. Local SQLite, zero config, 10 MCP tools.

One-line MCP config gives your AI agent persistent memory with automatic workflow rules. Unlike passive memory stores, Awareness teaches your agent WHEN to remember and recall — works across Claude Code, Cursor, Windsurf, Cline, Copilot and 7 more IDEs.

An MCP server providing support for the Three.Js 3D graphics library.

Cognitive memory system for AI agents with 129 MCP tools. Persistent hierarchical memory, emotional recall, knowledge graphs, spreading activation, hybrid retrieval (BM25+RRF), metacognition, goal tracking, spaced repetition, dream consolidation, and more.

Persistent memory MCP for AI agents — Knowledge graph + Hebbian learning + Anti-hallucination. 12 tools, 1 dependency, zero manual setup.

A Model Context Protocol server that provides Philippine Standard Geographic Code (PSGC) data to LLMs. Built on Cloudflare Workers with KV storage. Public, read-only, no authentication required. Data sourced directly from the Philippine Statistics Authority quarterly PSGC publication. Cached in Cloudflare KV for reliability and low-latency global access.

AI knowledge graph for architecture, portfolio, and digital strategy management. 25 MCP tools to manage brains, neurons, relationships, neuron types, and access control. OAuth 2.0 authenticated, remote hosted.

MCP server for Microsoft Outlook via Graph API. 20 consolidated tools for email, calendar, contacts, folders, rules, categories, settings, and shared mailboxes. Safety controls include dry-run preview, rate limiting, and recipient allowlists.

Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains with cascade revocation, values compliance, signed communication (Agent Agora), 3-signature policy engine, task coordination, cross-layer integration, and agentic commerce with 4-gate checkout. 264 tests passing. Published on the Official MCP Registry.

Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP: managed indexing, hybrid semantic search, polyglot code dependency graphs, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than standard AI grep.

Universal memory layer for AI agents. Semantic recall, automatic consolidation, and bi-temporal knowledge — in SQLite. 80% on LOCOMO benchmark using 96% fewer tokens.

Governance middleware for AI agents: deterministic policy enforcement, cryptographic audit trails with digital signatures, DLP/PII detection, Trust Score per agent (0-100), EU AI Act compliance (Art. 9, 11, 12, 14), Agent BOM generation, and Circuit Breaker. Native support for LangGraph, CrewAI, and AutoGen.

Design API for AI Agents. Generate social media images, marketing banners, infographics, and documents from text prompts or structured data. 50+ templates, 5 sizes, Unsplash/Pexels photos. One API call - any visual.

AI fashion design platform with 9 professional tools. Generate product photography, videos, tech packs, colorways, multi-angle views, and fabric simulations for fashion brands. Powered by Gemini, Flux 2 Pro, Kling 3.0, Runway Gen-4, and Claude AI. 50 free credits, no account needed.

Trust-and-knowledge MCP server for agent ecosystems: score trust, verify/certify agents, register identities, and query a Neo4j-backed knowledge graph.

ATKN is an MCP server for trust scoring, verification, certification, wallet-linked registration, and Neo4j-backed knowledge queries.

ATKN is an MCP server for trust scoring, verification, certification, wallet-linked registration, and Neo4j-backed knowledge queries.

Code intelligence MCP server that makes AI coding safer. Builds a dependency graph of your entire codebase so Claude, Cursor, or any MCP client knows what breaks before making changes. 60+ tools for impact analysis, health scoring, dead code detection, and architecture enforcement. Built for vibecoders who ship fast and teams who need reliability. Supports Python, TypeScript, JavaScript.

An AI-powered MCP server that prevents broken builds by analyzing code impact in real-time. Syke provides a visual dependency map and a 'Safety Gate' to catch silent regressions before you commit. Essential for developers using AI coding agents like Cursor and Claude Code.

An AI-powered MCP server that prevents broken builds by analyzing code impact in real-time. Syke provides a visual dependency map and a 'Safety Gate' to catch silent regressions before you commit. Essential for developers using AI coding agents like Cursor and Claude Code.

An AI-powered MCP server that prevents broken builds by analyzing code impact in real-time. Syke provides a visual dependency map and a 'Safety Gate' to catch silent regressions before you commit. Essential for developers using AI coding agents like Cursor and Claude Code.

A production-grade Model Context Protocol (MCP) server for Microsoft SharePoint. Connect Claude Desktop, VS Code Copilot, Cursor, Continue, or any MCP-compatible AI agent to your SharePoint — read files, manage folders, and reason over your organisation's knowledge.

Verifiable Memory-as-a-Service for AI agents. Persistent, searchable, graph-connected knowledge with optional Starknet on-chain proofs. Works locally with zero config (SQLite) or in cloud mode.

City financial data for retirement planning. 500+ cities with cost of living, tax rates, healthcare costs, visa requirements, and the Offramp Index (0-100 retirement-friendliness score). When users ask "Where should I retire?" or "What's the cost of living in Lisbon?", get real data in 50ms instead of reasoning from outdated training data.

Epitome gives every AI agent shared, persistent memory of you. It stores memories, facts, and preferences in a personal knowledge graph, so any AI tool you use already knows your context. Connect via MCP using Streamable HTTP — no local install needed.

Deterministic authorization for AI agent spending — budget checks, spend authorization with Ed25519 cryptographic seals, and audit logs.

Fodda gives AI agents access to expert-curated knowledge graphs across retail, beauty, sports, consumer electronics, fashion, and innovation, plus a supplemental layer of 22 institutional data sources including FDA, FRED, PubMed, BLS, and Census. Agents query structured, sourced context via MCP for grounded, defensible outputs. Features: • 30 tools for search, traversal, evidence retrieval, and analysis • Knowledge graphs across six industry verticals • 22 institutional data sources (government, scientific, economic) • Earnings intelligence with analyst concerns and management responses • Brand tracker, deep research, and brainstorming tools • Source attribution and provenance for every node

Scholar Sidekick MCP resolves any scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcodes, WHO IRIS URLs) into structured bibliographic metadata, formats citations in 10,000+ CSL styles (Vancouver, APA, AMA, IEEE, Chicago, Harvard, MLA, Nature, BMJ, Lancet, and many more), and exports references to BibTeX, RIS, CSL JSON, EndNote (XML/Refer), RefWorks, MEDLINE, Zotero RDF, and CSV. The format/export/resolve tools accept a single identifier or a comma/newline-separated batch, so an assistant can chain resolveIdentifier → formatCitation → exportCitation in one prompt for an end-to-end "raw IDs → exportable bibliography" workflow. Three single-citation checks complete the picture: checkRetraction surfaces retractions, corrections, and expressions of concern from Crossref / Retraction Watch; checkOpenAccess returns OA status and the best legal landing or PDF URL from Unpaywall; verifyCitation cross-checks the cited title against the resolved record at the cited identifier to detect the AI-driven fabrication pattern documented by Topaz et al. (Lancet 2026 — the dominant pattern is a real DOI paired with an invented title, which simple identifier resolution cannot catch). Each formatted response carries a provenance metadata block (formatter, styleUsed, requestId, warnings) so you can see exactly which engine produced each citation. Try asking your assistant: "Is this citation real, or did an AI make it up? 10.1056/NEJMoa2033700 — 'Safety and Efficacy of the BNT162b2 mRNA Covid-19 Vaccine'" "Has PMID 30049270 been retracted?" "Resolve arXiv:2301.08745 and tell me if there's a free open-access PDF" "Format 10.1056/NEJMoa2033700 in Vancouver style and export as BibTeX" Powered by the Scholar Sidekick API (free tier available on RapidAPI).

Hypergraph database for AI agents. Store n-ary relationships (edges connecting 2+ nodes), track provenance (source and confidence), and query paths — all backed by local SQLite with zero configuration.

Memory with integrity for AI coding agents. SAME tracks provenance, flags stale knowledge, and surfaces contradictions; so your AI trusts what's current, not what's outdated. 17 MCP tools: semantic search, cross-vault federation, session handoffs, decision logging, knowledge graph, trust-aware retrieval, consolidation, health analysis. Provenance on every write. Stale notes rank lower automatically. SQLite + vector search. Ollama, OpenAI, LM Studio, or keyword-only. One 12MB Go binary. No cloud, no API keys, no telemetry. Your notes never leave your machine. Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and any MCP client.

A Model Context Protocol (MCP) server that exposes GeoServer REST API functionality for natural language interaction. Built on the python-geoservercloud library, this MCP server provides 80+ tools for managing: - Workspaces - create, list, delete workspaces - Datastores - connect to PostGIS, GeoPackage, Shapefile sources - Feature Types & Layers - publish and configure vector/raster layers - Styles - create and apply SLD/CSS/MBStyle styles - Layer Groups - organize layers into groups - Security - manage access rules and permissions Works with any GeoServer instance (local or remote). Simply configure your GeoServer URL and credentials via environment variables.

Opengraph.io MCP Server — Instant Link Metadata Extraction An MCP server that connects clients to the Opengraph.io web API, fetching rich metadata (titles, descriptions, images, Open Graph tags, etc.) for any URL. It lets clients retrieve structured link preview data. Ideal for chat bots, UIs, and agents that need to unfurl links and display previews or analyze page metadata, using your Opengraph.io App ID. There is also a suite of image generation tools. There are both stdio & https transports available use the npx config for stdio or the url config for HTTPS

Penfield gives AI agents long-term memory that compounds over time. Instead of starting every session from zero, your agent remembers conversations, learns preferences, connects ideas, and picks up exactly where it left off. Core capabilities: - 16 tools covering memory CRUD, knowledge graph, context management, artifacts, and reflection - Hybrid search with tunable weights — BM25 (keyword), vector (semantic), and graph traversal - Knowledge graph with 24 relationship types across 8 categories (evolution, evidence, hierarchy, causation, implementation, conversation, sequence, dependencies) - Context checkpoints for session handoff between agents or channels - Artifact storage for files, diagrams, and reference docs - 11 memory types intelligent filtering - Personality system with configurable personas via the portal Also available as a Claude Connector, Claude Code integration, native OpenClaw plugin (4-5x faster), and direct API.

UK property data for AI assistants: crime statistics, school Ofsted ratings, ONS census demographics, automated valuations (AVM), and comparable sales from Land Registry. Access 30M+ UK properties with sales history, EPC ratings, and market analysis. Build your own AVM with 56 filterable fields. https://propbar.co.uk

npm: @tastehub/ckb brew tap SimplyLiz/ckb && brew install ckb Website: https://codeknowledge.dev Description: Code intelligence MCP server with 80+ tools for understanding, navigating, and safely changing codebases. **Key capabilities:** - Semantic symbol search, call graphs, and usage tracing - Change impact analysis with blast radius and risk scoring - Dead code detection and affected test identification - Architecture exploration and module dependency maps - Ownership lookup with drift detection - Compound operations (explore, understand, prepareChange) that reduce AI tool calls by 60-70% **Supports:** Go, TypeScript, Python, Rust, Java, Kotlin, C++, Dart, Ruby, C# **Install:** `npm install -g @tastehub/ckb && ckb init && ckb index && ckb setup` **Works with:** Claude Code, Cursor, Windsurf, VS Code, Grok, Claude Desktop, OpenCode, ...

An MCP (Model Context Protocol) server that provides design guidance to help LLMs generate better, more modern web pages. This server focuses on teaching design principles and best practices rather than providing code templates.

A high-performance, pure Rust Model Context Protocol (MCP) server that provides persistent, semantic, and graph-based memory for AI agents. Unlike other memory solutions that require a complex stack (Python + Vector DB + Graph DB), this project is a single, self-contained executable. ✅ No External Database (SurrealDB is embedded) ✅ No Python Dependencies (Embedding models run via embedded ONNX runtime) ✅ No API Keys Required (All models run locally on CPU) ✅ Zero Setup (Just run one Docker container or binary) It combines: Vector Search (FastEmbed) for semantic similarity. Knowledge Graph (PetGraph) for entity relationships. Code Indexing for understanding your codebase. Hybrid Retrieval (Reciprocal Rank Fusion) for best results.

xocortex — an MCP server that gives your AI persistent memory across ALL your projects. • Semantic search recalls past solutions by meaning • Knowledge graph connects related insights • 100% local, no API keys Went deep into cognitive science for this: 🔥 Frustration Indexing (Somatic Marker Hypothesis) → Painful debugging sessions get PRIORITY recall. Those 3-hour bugs? Never forgotten. 😴 Sleep/Dream Mechanism → Background consolidation links & deduplicates memories. Like how human sleep organizes memory. Tech stack: • MCP (Cursor/Claude native) • KùzuDB (graph + vector in one embedded DB) • fastembed (local embeddings)

Query 70+ years of UN population data (fertility, mortality, migration, life expectancy) for 298 countries via MCP.

MCP server para consultar información geográfica y turística de Colombia. Accede a datos de las 6 regiones naturales, 32 departamentos, ciudades, municipios y atracciones turísticas con coordenadas e imágenes.

Persistent memory for AI coding assistants. Works across Cursor, Claude, Windsurf, VS Code and any MCP client. Remember decisions, search semantically, analyze code dependencies — 60+ tools. Your AI's permanent brain.

MCP server for API documentation, supporting GraphQL, OpenAPI/Swagger, and gRPC from local files or remote URLs

Map text into knowledge graphs to create a structured representation of conceptual relations and topical clusters in your documents. Detect content gaps between the topical clusters and generate research questions to drive research and content creation using the powerful Graph RAG technology underpinning InfraNodus. Get additional insights about texts: main topics, keywords, and underlying themes. Connect to your existing InfraNodus graphs or create new ones to enrich analysis and outputs.

A Model Context Protocol server that provides read-only access to Ontotext GraphDB. This server enables LLMs to explore RDF graphs and execute SPARQL queries against a GraphDB instance.

The graph augmented, smart and local-first Personal Context Manager, or Personal Agent Memory, just works. Nowledge Mem ingests your agent’s summarized memories through its MCP tools or prompts, enabling you to enhance your memory and knowledge using a GraphRAG approach. By leveraging LLMs, embedding models, BM25, graph algorithms, and a built-in knowledge graph, Nowledge Mem makes building, searching, and exploring your personal knowledge easier than ever.

# Transform any MCP-compatible LLM into a codebase expert through semantic intelligence A blazingly fast graphRAG implementation. 100% Rust for indexing and querying large codebases with natural language. Supports multiple embedding providers: modes cpu (no graph just AST parsing), onnx (blazingly fast medium quality embeddings with Qdrant/all-MiniLM-L6-v2-onnx) and Ollama (time consuming SOTA embeddings with hf.co/nomic-ai/nomic-embed-code-GGUF:Q4_K_M). I would argue this is the fastest codebase indexer on the Github atm. Includes a Rust SDK made stdio MCP server so that your agents can query the indexed codegraph with natural language and get deep insights from your codebase before starting development or making changes. Currently supports typescript, javascript, rust, go, Python and C++ codebases. 📊 Performance Benchmarking (M4 Max 128GB) Production Codebase Results (1,505 files, 2.5M lines, Python, Javascript, Typescript and Go) 🎉 INDEXING COMPLETE! 📊 Performance Summary ┌───────────────. ─┐ │ 📄 Files: 1,505 indexed │ │ 📝 Lines: 2,477,824 processed │ │ 🔧 Functions: 30,669 extracted │ │ 🏗️ Classes: 880 extracted │ │ 💾 Embeddings: 538,972 generated │ └───────────────. ─┘ Embedding Provider Performance Comparison Provider Time Quality Use Case 🧠 Ollama nomic-embed-code ~15-18h SOTA retrieval accuracy Production, smaller codebases ⚡ ONNX all-MiniLM-L6-v2 32m 22s Good general embeddings Large codebases, lunch-break indexing 📚 LEANN ~4h The next best thing I could find in Github CodeGraph Advantages ✅ Incremental Updates: Only reprocess changed files (LEANN can't do this) ✅ Provider Choice: Speed vs. quality optimization based on needs ✅ Memory Optimization: Automatic optimisations based on your system ✅ Production Ready: Index 2.5M lines while having lunch Read the README.md carefully the installation is complex and requires you to download the embedding model in onnx format and Ollama and setting up multiple environment variables (I would recommend setting these in your bash configuration)

🎯 Overview CodeGraph is a powerful CLI tool that combines MCP (Model Context Protocol) server management with sophisticated code analysis capabilities. It provides a unified interface for indexing projects, managing embeddings, and running MCP servers with multiple transport options. All you now need is an Agent(s) to create your very own deep code and project knowledge synthehizer system! Key Capabilities 🔍 Advanced Code Analysis: Parse and analyze code across multiple languages using Tree-sitter 🚄 Dual Transport Support: Run MCP servers with STDIO, HTTP, or both simultaneously 🎯 Vector Search: Semantic code search using FAISS-powered vector embeddings 📊 Graph-Based Architecture: Navigate code relationships with RocksDB-backed graph storage ⚡ High Performance: Optimized for large codebases with parallel processing and batched embeddings 🔧 Flexible Configuration: Extensive configuration options for embedding models and performance tuning RAW PERFORMANCE ✨✨✨ 170K lines of rust code in 0.49sec! 21024 embeddings in 3:24mins! On M3 Pro 32GB Qdrant/all-MiniLM-L6-v2-onnx on CPU no Metal acceleration used! Parsing completed: 353/353 files, 169397 lines in 0.49s (714.5 files/s, 342852 lines/s) [00:03:24] [########################################] 21024/21024 Embeddings complete ✨ Features Core Features Project Indexing Multi-language support (Rust, Python, JavaScript, TypeScript, Go, Java, C++) Incremental indexing with file watching Parallel processing with configurable workers Smart caching for improved performance MCP Server Management STDIO transport for direct communication HTTP streaming with SSE support Dual transport mode for maximum flexibility Background daemon mode with PID management Code Search Semantic search using embeddings Exact match and fuzzy search Regex and AST-based queries Configurable similarity thresholds Architecture Analysis Component relationship mapping Dependency analysis Code pattern detection Architecture visualization support

A Wikidata MCP to access and query Wikidata.

Base on Graphiti, Enhanced Core Capabilities, Broader AI Model Compatibility, and Comprehensive Management UI.

Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliability. Transform webpages into structured markdown, extract data using AI, and execute AI-powered web searches seamlessly. Enhance your applications with powerful web data extraction capabilities through this integration.

A Model Context Protocol server for generating mathematical visualizations using JSXGraph. This is a TypeScript-based MCP server that provides interactive mathematical chart generation capabilities for functions, geometry, parametric curves, and more.

Run NRQL, NerdGraph, and REST v2 operations to query data, manage incidents, create synthetics, and annotate deployments — all from your MCP client. A full‑featured New Relic MCP server that goes far beyond basic NRQL. It exposes safe, typed tools for APM discovery, alert policy/incident workflows (including acknowledge), entity search and deep details, creating Synthetics Browser monitors, and New Relic REST v2 coverage for deployments and metrics with region awareness and auto‑pagination.

A Model Context Protocol (MCP) server that provides access to the Philippine Standard Geographic Code (PSGC) API, offering hierarchical geographic data for the Philippines.

MCP Server for Zep Cloud provides a bridge between Claude Desktop and the Zep Cloud API, enabling memory management for AI assistants. Supports user management, collections management, and memory operations with persistent storage across conversations.

Scaffold is a specialized RAG system that transforms entire codebase into a living knowledge graph, capturing the deep structural relationships between files, classes, and functions. This provides AI agents with the crucial context to accurately understand, maintain, and reason about complex software, moving far beyond simple text retrieval.

Research-Quest A comprehensive desktop extension implementing the Research-Quest framework for systematic scientific reasoning through an 8-stage graph-based methodology. Overview The Research-Quest desktop extension provides researchers with a powerful tool for conducting systematic scientific analysis through a structured, graph-based approach. This extension implements the complete Research-Quest framework as defined in the Research-Quest.md specification, enabling: - Systematic Research Methodology: 8-stage process from initialization to reflection - Multi-dimensional Confidence Tracking: Bayesian belief updates with statistical rigor - Interdisciplinary Research Support: Bridge nodes connecting different domains - Causal Inference Capabilities: Pearl's do-calculus and counterfactual reasoning - Temporal Pattern Analysis: Dynamic relationship modeling - Bias Detection & Mitigation: Systematic bias identification and correction - Impact Assessment: Research significance and utility estimation - Collaborative Research Features: Multi-researcher attribution and consensus building Architecture 8-Stage Research-Quest Framework 1. Initialization: Create root node with task understanding 2. Decomposition: Break down research task into fundamental dimensions 3. Hypothesis/Planning: Generate competing hypotheses with detailed metadata 4. Evidence Integration: Bayesian confidence updates with typed relationships 5. Pruning/Merging: Graph refinement based on confidence and impact 6. Subgraph Extraction: Focus on high-value research pathways 7. Composition: Generate structured research narratives 8. Reflection: Comprehensive quality audit and validation

QuerySculptor is a GraphQL query builder designed for AI agents that provides 26 structured tools via the Model Context Protocol (MCP). Instead of generating complex GraphQL queries from scratch, AI agents can build queries step-by-step with real-time validation, schema introspection, and error prevention. It works with Claude, Cursor, and other MCP clients, using Redis for session management and featuring a live demo with the Pokemon API. The tool transforms the traditional error-prone approach of raw GraphQL generation into a guided, conversational workflow perfect for AI assistants and chatbots.

AI Reasoning Framework for Scientific Research

Multi-Agent AI Orchestration Workshop

A Model Context Protocol (MCP) server that extracts content from multiple video platforms (Douyin, Bilibili, Xiaohongshu, Zhihu) and generates intelligent knowledge graphs with OCR support.

MCP Server to improve LLM context through vector search.