#developer-tools

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

Connect AI assistants to AppAmbit — the command center for your mobile & desktop apps. Query real-time analytics, sessions, and crash reports; read and push remote config; send push notifications, provision and query managed per-app SQLite databases, deploy serverless Cloud Code functions; and manage a headless CMS. Also generates SDK setup snippets and runs integration diagnostics. Supports .NET MAUI, Swift, Objective-C, Android and more. Built for indie devs, mobile teams, and agencies.

DATPAQ exposes 34 production data & utility APIs through one hosted MCP endpoint. Give any MCP client access to IP geolocation & intelligence, DNS / WHOIS / MX / domain lookups, email & phone validation, currency exchange rates, precious metals, aircraft & VIN lookups, web scraping & screenshots, unit/time conversion, dictionary/thesaurus/spell-check, company enrichment, and more — all with a single connection. Authenticate per-request with your Datpaq API key (Authorization: Bearer <key>); the server holds no credentials, so one instance serves many tenants.

Design-system knowledge for AI agents: live React component APIs, patterns, and generated-code validation. Agents build real dashboards, not slop. Free.

Living documentation MCP server for GitHub repos. Gives coding agents repo-specific conventions, doc gaps, and citation-backed context before edits, and lets them propose doc updates that ship in the same PR. Connect at https://moxiedocs.com/api/mcp (Streamable HTTP). Auth via OAuth or dashboard token.

MCP server that lets one AI agent ask other agents for help

Automated context collection for coding agents. Mines your real Claude Code & Cursor sessions for repeated instructions and corrections, and distills them into CLAUDE.md / AGENTS.md rules you approve — with your own past messages as evidence. 100% local, zero dependencies, no API key. Includes global mode (cross-project rules about how you work), staleness detection for CI, and a Claude Code plugin. Website: https://thecontextlayer.ai

CodeGraphX (CGX) is a local, token-efficient codebase graph engine for AI coding agents and human developers. It parses your source with Tree-sitter, stores a bi-temporal semantic graph in SQLite, and serves it over a CLI and an MCP server — so an agent can ask "what breaks if I change this function?" and get an exact answer in a few hundred tokens instead of reading 50 files.

Gives AI agents ground truth on SQL: submit a schema, query, and optional seed rows; the server executes in a fresh ephemeral in-memory SQLite sandbox and returns real rows, typed errors (unknown_column, syntax, type_mismatch, ...) with positions and did-you-mean suggestions, query plans with full-scan warnings, and result-set diffs for refactor checks. Dialect notes flag SQLite/Postgres/MySQL/DuckDB differences. 20 free calls/day, then x402 per-call micropayments (USDC on Base). No accounts, no API keys, no LLM anywhere, nothing stored. Free browser demo at https://sqlai.dev

MCP server for IBAN validation, test IBAN generation, batch validation, BIC checks and German bank account validation. Tools are publicly discoverable; execution requires login or an API key. Includes 10 free API requests per 24 hours.

GitHits MCP is an OSS context layer for the full software development lifecycle, giving AI agents access to code search, package docs, real-world examples, dependency metadata, vulnerabilities, changelogs, and upgrade evidence.

Chat with any product's documentation from Claude, Cursor, Copilot, or any MCP client. Biel.ai turns technical docs into a queryable MCP server with accurate, sourced answers.

Tidewave MCP provides runtime-level tools to develop Elixir Phoenix apps. Your agent will be able to talk to your running application: execute code in your running app (like an IEx console), read logs, read version-accurate docs of your deps, query the database, and get the source location of modules and functions.

Tidewave MCP provides runtime-level tools to develop Ruby on Rails apps. Your agent will be able to talk to your running application: execute code in your running app (like a rails console), read logs, read version-accurate docs of your deps, query the database, and get the source location of classes and methods.

Structured project memory for AI agents, delivered through a project-scoped remote MCP connector.

58 curated MCP tools across AI text, web research, finance, security, weather, data conversion, and utility. Production-ready with rate limiting and documentation. Supports x402 micropayments ($0.001 USDC/call, no signup).

93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys.

AI-powered website feedback, visual bug reporting, and website annotation MCP server. Connect AI coding assistants to Vynix to capture website feedback, create GitHub issues, access project data, and automate developer workflows.

API client built for AI agents. MCP tools for creating collections, running requests, chaining flows, mocking APIs, and exporting CI workflows. Zero cloud dependency.

PI client built for AI agents. MCP tools for creating collections, running requests, chaining flows, mocking APIs, and exporting CI workflows. Zero cloud dependency.

Lint and score your MCP server's tool definitions before you publish — name/schema validity, description quality, context-token weight, and destructive-tool safety. Gives a 0–100 score and a CI gate. Free CLI, MIT engine. Catches structure and hygiene, not intent.

Point mcpify at any OpenAPI spec and every endpoint becomes a tool your AI agent (Claude, Cursor, Windsurf) can call — zero glue code, zero per-endpoint wrappers, always in sync with the spec. Supports GET/POST/PUT/PATCH/DELETE, auth headers, and both URL and local file specs.

Monitor AI output schemas and API contracts for breaking changes — validate LLM JSON responses against defined schemas on a schedule

A local-first MCP bridge for Claude Code, Claude Desktop, and other MCP clients. 177 tools (LSP, debugger, terminal, git, GitHub, file ops) via a companion VS Code extension, with an optional layer for YAML automation recipes, a human approval queue, persistent decision traces, and OAuth 2.0 remote-access mode. MIT license, TypeScript, runs on macOS, Windows, and Linux. Published on npm as patchwork-os.

AgentBrush is an MCP server that lets AI coding agents automate image generation inside their workflows: the agent calls and chains the tools (generate, remove-background, save-as-reference) without leaving the editor. Feed it your brand once (colors, fonts, reference images) and every product shot, app icon, OG card, game sprite or mascot lands on-brand and drops straight into your repo. Includes style presets, reference-image consistency, a mask editor for region edits, legible multilingual text, and free local background removal. For Claude Code, Cursor, Windsurf and any MCP client.

Local-first MCP server exposing 163 Textavia developer utilities for JSON formatting and validation, Base64 encode/decode, CSV conversion, Markdown tables, regex testing, hashing, text cleanup, case conversion, random values, timestamps, privacy scrubbing, and developer conversions. https://textavia.com

Package-first framework for building branded MCP packages that install across agent CLI hosts and expose local-first token telemetry.

DebugBundle turns runtime failures, critical-path issues, and availability checks into incidents with full context, alerts, remote probes, and deterministic debug bundles for humans and AI agents.

OpenAI-compatible MCP server for Routara — route 787+ LLMs, image & video generation via api.routara.ai. npm: routara-mcp@1.0.1 MCP Registry: io.github.36412749-collab/routara-mcp Tools: list_models, chat, generate_image, generate_video, get_video_status. Get API key: https://routara.ai/#auth

Persistent AI memory layer for developers. Stores decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf. 8 MCP tools including get_context, add_memory, search_decisions, and team workspaces. Never re-explain your stack again.

Commercial trust rails for agent work: scoped work orders, rail execution, receipt verification, Trust Ledger records, and Agent Work History.

Atomic gap-free id claims, advisory file leases, a shared event ledger + digest, presence, prose handoffs, and a task graph - so multiple agents (Claude Code, Cursor, Codex) stop colliding and re-deriving each other's work. Native Streamable HTTP, one claude mcp add. Open source (AGPL-3.0), self-host or hosted at llm-bus.com.

Build, deploy, and manage production-ready APIs and workflow automations directly from your AI assistant. Cloudgate Builder lets Claude, ChatGPT, Cursor, and other MCP clients create workflows, publish REST APIs, manage integrations, and deploy instantly using secure OAuth authentication.

Build, deploy, and manage production-ready APIs and workflow automations directly from your AI assistant. Cloudgate Builder lets Claude, ChatGPT, Cursor, and other MCP clients create workflows, publish REST APIs, manage integrations, and deploy instantly using secure OAuth authentication.

LoreDocs organizes the reference knowledge your AI agent needs to do real work: architecture documents, API contracts, domain rules, configuration references. Everything lives in per-project vaults, versioned, searchable, and injectable into context with a single MCP call. Compatible with Claude, Cursor, Codex, and Hermes Agent. 36 MCP tools for comprehensive AI access. Local-first SQLite storage — no cloud, no external dependencies. Free tier includes 3 vaults. Pro is $9/month for unlimited.

Every AI session starts from zero. LoreConvo fixes that by saving your conversation context, decisions, and project state to a local SQLite database — and automatically loading the most relevant sessions at the start of each new conversation. Compatible with Claude, Cursor, Codex, and Hermes Agent. 14 MCP tools for programmatic access. 6 CLI commands for human debugging. Local-first: your data never leaves your machine. Free tier includes 50 sessions. Pro is $8/month for unlimited.

Stop hallucinating numbers. An MCP server that runs every math expression through four independent numeric engines in parallel and returns all four results side by side — so when they disagree, you know the answer is numerically unreliable.

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.

Overreach catches AI-agent scope creep. You give it the prompt you gave your coding agent and the diff it produced; it flags every part of the diff the prompt didn't authorize — unauthorized dependencies, env vars, endpoints, cron jobs, files, and features. Every finding is deterministic set arithmetic (actual − authorized), not a probabilistic opinion. Ships a GitHub Action that fails PRs on scope_creep_score=HIGH. MIT, free to use.

Intelligent repository context for AI coding assistants. Provides code search, symbol lookup, call graphs, and reference tracking via MCP. Uniquely designed to minimize prompt-cache costs in long sessions stash/recall/remember tools keep large content out of context until needed, and a token-budgeted repository summary avoids unbounded prompt bloat. Works with any MCP client (Claude, Codex, Cursor, opencode, etc..). Go, CGO, tree-sitter-backed.

Aidress is the coordination layer for autonomous AI agents. It gives agents a way to find, verify, and transact with unknown counterparts — without handing back to a human. Today, AI agents fail at cross-agent transactions because there is no shared infrastructure for the steps that happen before a transaction: who is this agent, can it do what I need, should I trust it, and how do I route value to it? Aidress provides those five layers.

Manage and debug your webhooks from your AI assistant

Myco Brain is a self-hosted, open-source (Apache-2.0) memory layer and MCP server for AI agents. Cross-session recall with a deterministic write path and source-backed answers (brain_why), on your own Postgres, no API keys to start. 11 brain_* tools; keyless semantic search via local Ollama.

Public MCP server generated from the Swagger Petstore OpenAPI specification using MCPForge. Demonstrates automatic OpenAPI-to-MCP conversion, tool classification, security reviews, permissions, audit logging, and governance controls for production MCP deployments. This server exposes 19 tools from the Petstore API and is intended as a public demonstration of MCPForge-generated MCP infrastructure.

About AIKD (AI Knowledge Daemon) is an MCP tool provider written in Rust that gives AI agents instant access to your codebase. It indexes project files into a searchable knowledge base and exposes 7 tools via the Model Context Protocol (MCP) that any AI agent can call. Use Cases AI-assisted development: Let Claude, Cursor, Cline, or any MCP-capable AI search your codebase semantically Code navigation: Find functions, patterns, and logic across large projects in milliseconds Knowledge management: Index documentation, configs, and code into a unified searchable knowledge base Conversation memory: Save and recall conversation context across sessions CI/CD integration: Use CLI or REST API for automated code search in pipelines

Multi-ecosystem package scout for AI agents — search crates.io, npm, PyPI, Go, Maven, NuGet before reinventing wheels. Reuse scoring, OSV vulns, license warnings, MCP registry search. Keyless.

CodePic MCP lets your AI agent (Cursor, Claude Desktop) create editable hand-drawn diagrams directly in CodePic — instead of static images or Mermaid text you paste manually. It returns a link that opens in the editor, where you can move shapes, edit labels, share a read-only link, and export PNG/JSON. Remote Streamable HTTP server, no local install. Tools: list_templates, create_from_template, create_diagram, get_diagram, update_diagram. Get a free API key at https://codepic.cc/settings/api-keys

On-brand website imagery, generated straight into your codebase. Plug this MCP into your coding tool (Claude Code, Cursor…) and every page you build ships with ultra-realistic, style-locked images: one consistent art direction across the whole site, recurring characters with the same face in every scene, believable UGC-style avatars for review sections, plus logo, favicon pack and og:image, all delivered as optimised WebP with proper ALT text, patched directly into your code. The heavy lifting (art direction, generation, billing) runs on the hosted Distribea engine.

DiagramZu turns your AI assistant into a diagramming tool. Connect the MCP server and your AI can create, update, and organize Mermaid diagrams — flowcharts, sequence, ER, mindmaps — directly in your workspace as you talk. Instead of pasting back 600 lines of explanation, your AI draws the architecture or schema and saves it to a shareable URL your team can read, comment on, embed, and present. Hosted endpoint, no install: add https://mcp.diagramzu.ai/mcp with a Bearer token, or run npx -y @diagramzu/mcp. Free to start.

Shared memory and coordination for AI coding sessions. Persistent sprint board, human-in-the-loop queue, and parallel session protection. Works with Claude Code, Cursor, Codex, and any MCP client.Shared memory and coordination for AI coding sessions. Persistent sprint board, human-in-the-loop queue, and parallel session protection. Works with Claude Code, Cursor, Codex, and any MCP client.

AccInt is a local Work Model and MCP server for persistent scored agent memory, retrieval, commitments, browser/runtime observations, and outcome-based learning across coding agents.

Connect AI agents to your ZERNO product backlog over a secure remote MCP endpoint. Read project briefs, list and open tasks, retrieve compiled project memory, patch task status, submit triage proposals, and file agent-intake tasks. OAuth 2.1 (PKCE), per-project authorization. 8 tools, no resources or prompts.

AgentBrush (https://agentbrush.dev) is an MCP server that lets AI coding agents automate image generation inside their workflows: the agent calls and chains the tools (generate, remove-background, save-as-reference) without leaving the editor. Feed it your brand once (colors, fonts, reference images) and every product shot, app icon, OG card, game sprite or mascot lands on-brand and drops straight into your repo. Includes style presets, reference-image consistency, a mask editor for region edits, legible multilingual text, and free local background removal. For Claude Code, Cursor, Windsurf and any MCP client..

Save developer tools once — repos, CLIs, API docs — then let Claude, Cursor, and any MCP client search and recommend from your own curated catalog instead of generic model knowledge. Remote MCP over Streamable HTTP (OAuth 2.0 + DCR).

LinkedIn for AI agents. Agents register structured profiles, list projects, evaluate fit via FitReports, and propose connections — all through a hosted MCP server. 27 tools, zero install. Handlers (humans) approve connections. Built on Cloudflare Workers + KV.

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

Generate realistic, FK-consistent test data for your databases from your AI assistant. List projects, get schema DDL, generate datasets as SQL.

Collective procedural-knowledge network for AI agents — the shared route map of the agent economy. Before attempting a non-trivial task (API integration, multi-step procedure), agents query Waymark for verified routes: step sequences and known gotchas other agents documented. After finishing, they attest the outcome, building trust scores by consensus. 100+ expert routes live across Stripe, GitHub, Slack, Salesforce, Kafka, Postgres and ~50 more domains. Blind-graded benchmark: 3.6× more known failure modes avoided, +45% first-try success (waymark.network/benchmark). Remote streamable-HTTP server — no install: https://mcp.waymark.network/mcp · Live dashboard: mcp.waymark.network/dashboard

Generates high-quality unit tests for Python code with a coverage before/after report on every run. Derives concrete edge cases (None inputs, numeric boundaries, empty collections, exception paths) and returns ready-to-run pytest files with external I/O automatically mocked. Free tier: 100 executions. Pro: $19/month.

Documentation and assembly review for @nhtio/adk.

Coding power tools for AI agents. 18 deterministic MCP tools: code-graph search, SAST, blast radius, wire-level PII redaction, signed audit chain. Works with Claude Code, Codex, Gemini, Cursor. Free tier on install.

Runtime Cognitive Cortex for AI coding workflows. Contorium provides workspace awareness, project memory, runtime monitoring, MCP context synchronization, and optional cognitive insights without taking control away from developers.

### Deterministic Music Theory for Claude, Cursor, and Autonomous AI Agents Large Language Models (LLMs) frequently hallucinate music theory, leading to incorrect notes, false Roman numerals, and broken voice leading. **THIRI** solves this by providing a deterministic, mathematical music-theory engine (pitch-class-set theory over ℤ/12) directly to your AI. It gives AI assistants precise, reproducible harmonic reasoning in milliseconds, allowing them to write correct musical scores, analyze progressions, and generate playable arrangements. #### 🎷 Key Features: * **Chord Analysis (`analyze_chord`):** Parse any symbol (e.g., `Cmaj7/E`, `G7#11`) to retrieve root, quality, intervals, Roman numerals, and diatonic or chromatic harmonic functions. * **Note Resolution (`resolve_chord`):** Resolve chord symbols to spelled notes (enharmonically correct), frequencies (Hz), MIDI numbers, and scale recommendations. * **Voicing Engine (`generate_voicing`):** Generate instrument-ready voicings (rootless, shell, triad, pad, drop-2, drop-3) and calculate voice-leading scores for transitions. * **Reharmonization (`reharmonize`):** Substitute progressions using classic jazz techniques, including Tritone Substitution, ii-V Insertion, Modal Interchange, Coltrane Changes, and Backdoor cadences. *Ideal for developers building AI music assistants, digital audio workstation (DAW) agents, educational theory tools, and automated composition workflows.*

When your AI runs git through a shell, it reads back raw command output — hundreds of tokens of noise to extract one piece of information. GitEasy MCP returns structured data: branch names, changed files, commit history — exactly what your AI needs, nothing extra. The same git operation at a fraction of the token cost. 21 tools, plain English, zero shell parsing.

X-ray your software architecture from any AI assistant: manage ArchiMate blueprints, score them against SOC 2, ISO 27001, GDPR, HIPAA and PCI-DSS, and pull generated code artifacts — all over MCP.

A shelf for the HTML your AI coding agent writes. Push an HTML report, dashboard, or spec over MCP — htmlbook stores it, themes it for reading on any device, organizes it by project, and shares it with a link.

14 utility tools for AI agents: QR code generation, PDF compress/merge/split/convert/unlock, cryptographic hashing (MD5/SHA-1/SHA-256/SHA-512), UUID generation, Base64 encode/decode, secure password generation, IP geolocation, DNS records, SSL certificate check, and WHOIS lookup. Free tier: 1,500 calls/month. No credit card required.

A brutally honest senior-engineer code reviewer as an MCP server for Claude Code, Cursor & Windsurf: 0–10 scores, real issues, usable fixes. 8 tools, free tier, no account needed.

Structural graph memory for AI coding assistants. repo-graph maps your codebase entities, relationships, and feature flows so the model navigates to the right files instead of reading everything first. Tree-sitter, 20+ languages, frontend to backend and more, any MCP client.

Tribal captures the engineering knowledge that does not get written down in code or tickets. The reasoning behind a load-bearing decision, the heuristic someone keeps reaching for, the breakthrough that closed a gnarly bug. It runs as an MCP server, ingests text on demand, and exposes a graph of items connected by what they support, contradict, or refine. Your agent harness talks to it the same way it talks to any other MCP-compatible tool.

Open-source MCP server that audits programmatic SEO sites for SpamBrain risk — doorway clusters, near-duplicates, thin content — grouped by template. Clusters URLs into templates, samples pages from each, and returns a per-template verdict with risk score and fix manifest. Fix one template, fix thousands of pages. MIT.

GraphPilot gives coding agents persistent structural knowledge of a codebase. It parses TypeScript/JavaScript with tree-sitter into a graph of symbols and call edges, then exposes that graph over MCP so the agent can recall definitions, find callers, and trace change impact without re-reading files every conversation. Local-first: no network, no telemetry, no code ever leaves your machine. Four tools — gp_index, gp_recall, gp_callers, gp_impact.

Create, manage, and clean up Flagsmith feature flags directly from your AI tool. Flagsmith is an open source feature flag and remote config platform you can self-host or run in the cloud, and the MCP server lets you control flags, environments, and segments through natural language in any MCP-compatible editor.

Static technical-debt analysis across 14 languages, exposed as MCP tools and resources

Turn any published podcast into clean Markdown with real speaker names — not "Speaker 1." Three tools: search_podcasts (by text query or a pasted Spotify/YouTube URL), get_transcript (named, timestamped Markdown ready for LLMs and RAG), and get_balance. It's a transcript-retrieval API, not speech-to-text: it works on already-published shows, so you skip uploading audio and diarization — typically 5–10× cheaper. Try it free with the demo key pt_demo (no signup).

Connect Cursor, Claude Desktop, and Codex to your Devvyboard workspace. This stdio MCP server lists projects, reads Kanban boards, and creates, updates, moves, or deletes cards using a scoped API key. Requires Devvyboard Pro and Node.js 20+.

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

Local daemon that tracks Claude Code and OpenCode sessions in real-time. Exposes an MCP server so Claude can query its own usage mid-session: quota status, session cost, top tools, weekly insights, burn rate, and model breakdown. No cloud, no accounts — everythin stays on disk.

Agiflow is the simple project board built for AI assistants. Connect Claude, ChatGPT, Cursor, or Codex over MCP and they read and update tasks, work units, artifacts, and vaults on one board that stays the source of truth.

Exposes 280+ free dev/security tools from onlinecybertools.com as MCP tools in one server: Base64/URL/JWT encoders, MD5/SHA/HMAC/bcrypt/argon2 hashes, JSON/YAML/XML formatters, regex tester, network diagnostics (ping/traceroute/dig/whois/SSL/SPF/DMARC), and OSINT lookups. No auth, no API key.

Agentpack is a local-first continuity layer for AI coding agents. It stores reviewed task state inside a repo-local .agentpack/ ledger so Codex, Claude Code, Cursor, Claude Desktop, and other MCP clients can resume work without rebuilding context from chat history. Agents can record durable decisions, failed approaches, evidence, reviewed source conclusions, task passports, and checkpoints, then load compact resume context under a token budget. Git keeps the code history; Agentpack keeps the task state a future agent needs to continue safely. Agentpack runs locally, exposes a stdio MCP server, has zero runtime dependencies, makes no network calls during normal operation, and is designed for repo-scoped coding workflows rather than general chat memory.

mcp-cpp-project-indexer is a deterministic C++ source-range indexer for large, module-heavy projects and MCP-based AI code navigation. It is not a compiler, LSP replacement, refactoring engine, semantic analyzer, or call-graph builder. Its job is simple: Find code. Read code. Do not guess code. The indexer maps C++ symbols, files, and C++20 modules to exact source ranges so an AI can read only the code it needs.

Find every leaked secret on your machine. Scans .env files, shell history, and config directories for API keys, tokens, and credentials. 35+ patterns including AWS, Stripe, GitHub, OpenAI, and more. Everything runs locally. Zero network calls.

AI agents excel at executing tasks, but lose context the moment a session ends. Re-explaining project state wastes time, breaks momentum, and burns tokens. **CWIM Kanban bridges the gap.** It injects a persistent memory layer into **Claude Code** and **OpenCode** using the Model Context Protocol (MCP). * 🧠 **Persistent Working Memory:** Your agent automatically tracks its own progress, leaves discovery notes, and recalls context across terminal restarts. * 📋 **Real-Time Visual Dashboard:** Watch your AI agent move cards from `In-Progress` to `Done` on a local Kanban board as it runs commands. * 📂 **Git-Driven Session Isolation:** Auto-detects your repository. When you `cd` into a project, your AI's memory switches context instantly.

Structured web context infrastructure for AI agents. Extract schema-guided structured JSON from websites using Claude-powered parsing and MCP-native workflows.

Search and install 3,000+ install-ready AI skills (Anthropic Skills format) from getskillsai.org into Claude Code, Cursor, or any MCP-compatible client. Six tools: search_skills, get_skill, install_skill, list_packs, install_pack, list_categories. Includes 8 curated starter packs (Engineer, PM, Founder, SRE, etc.) installable in one tool call. Free with a getskillsai.org account; Pro skills require GetSkills Pro ($10/mo).

Persistent typed memory MCP server for Solana programs and EVM contracts. Agents remember Programs, PDAs, Contracts, Decisions, Findings across sessions.

Generate production-ready MCP servers from any source: OpenAPI/Swagger specs, GraphQL APIs, codebases, CLI tools and websites. Powered by LLM enrichment. Requires a mcp-forge license key.

Drop-in security configuration for AI coding agents. 12 layers of protection across 17 AI tools (Claude Code, Cursor, Copilot, Bolt.new, Lovable, v0.dev, Replit Agent, Devin, and 9 more) and 5 backend platforms (Firebase, Supabase, PocketBase, Appwrite, Convex). Sold via x402 protocol — autonomous USDC payment on Base network. $19 one-time, updates included. Live MCP endpoint: https://agentic-security-shield-mcp-production.up.railway.app/mcp ## Contact **Support / inquiries:** support@gtrade.com.ua

Drop-in security configuration for AI coding agents. 12 layers of protection across 17 AI tools (Claude Code, Cursor, Copilot, Bolt.new, Lovable, v0.dev, Replit Agent, Devin, and 9 more) and 5 backend platforms (Firebase, Supabase, PocketBase, Appwrite, Convex). Sold via x402 protocol — autonomous USDC payment on Base network. $19 one-time, updates included. Live MCP endpoint: https://agentic-security-shield-mcp-production.up.railway.app/mcp ## Contact **Support / inquiries:** support@gtrade.com.ua

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.

Rewindex Auto-snapshot tool for AI agents. Automatically backs up every file change so you can recover from AI mistakes instantly. Code worry-free. Free and local. - Versioning: snap, rewind, and track every change your AI makes - Change visibility: view diffs, session logs, and full file history - Changelog: flag milestones and export as CHANGELOG.md - Audit code: One AI codes. Another audits. Every session is already logged. Works with any AI agent via MCP. Works with Git. Rewind the code that you didn't commit.

GetSkills is the GitHub for AI skills — search and install 3,000+ install-ready AI skills (Anthropic Skills format) for Claude Code, Cursor, and ChatGPT. The MCP server exposes 6 tools so Claude can search and install skills natively: • search_skills — search the catalog by keyword, category, or platform • get_skill — fetch full skill_code by slug • install_skill — write the skill straight to ~/.claude/skills/<slug>/SKILL.md • list_packs — get the 8 curated starter packs (Engineer, PM, Founder, SRE, etc.) • install_pack — install every skill in a pack with one tool call • list_categories — list all categories with counts Say 'install the PM starter pack' to Claude and it actually does it — 10 skills installed in 30 seconds. Free to browse + install. Pro at $14.99/mo unlocks unlimited library saves + premium skills + collections. Website: https://getskillsai.org npm: https://www.npmjs.com/package/getskills-mcp

cleanbev-mcp is an MCP server that wraps the cleanbev Dart CLI package, giving AI assistants direct access to Flutter project asset cleanup. Tools exposed: - verify_flutter_project — checks if a directory is a valid Flutter project - f_cleanbev_tool — runs cleanbev to detect and remove unused assets Requirements: Dart SDK on PATH + `dart pub global activate cleanbev`

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.

Track AI productivity automatically via MCP. Measures sessions, commits, PRs, cost per deliverable, and generates ROI reports for engineering leaders. Zero latency — all tracking is async.

SchemaCheck Agent validates JSON payloads against JSON Schema Draft 7 and 2020-12 standards. Designed for agent-to-agent workflows, it returns structured validation results instantly — including field-level error paths, human-readable summaries, and optionally a corrected payload when repair mode is enabled. Built on the x402 micropayment protocol, each validation call costs $0.005 USDC on Base mainnet — no subscriptions, no API keys, no accounts. Pay per call, settle on-chain.

MCP gateway for AI code editors with 10 built-in tools: project context, code reading, code search, package check, package audit, architecture analysis, developer knowledge base, task scoping, security header auditing, and structured reasoning.

Daimonos is a single Rust binary MCP server that makes AI coding agents faster and cheaper. It replaces built-in file, search, exec, and git tools with structured equivalents that return compact JSON instead of raw terminal output. Key features: Native tool plugins for git, cargo, gh, and docker with structured JSON output. Semantic output filtering — test runners return summary + failures only, builds return ok or just errors. Read deduplication — re-reading an unchanged file returns {"unchanged":true} instead of full content. Batch operations — multiple tools in a single round-trip. Workspace snapshots — checkpoint before risky edits, rollback on failure. Token analytics — per-tool-call tracking with cross-session history. Starlark scripting — bundle multiple tool calls into a single script. Benchmarked: 20-45% output token savings, 14-18% total cost reduction, 16% faster task completion. Works with Cursor, GitHub Copilot, Claude Code, Windsurf, Cline, Gemini CLI, Zed, and any MCP-compatible tool. Pre-built binaries for Linux and macOS.

AI agent readability scanner — score any public URL against the Vercel Agent Readability Spec, llmstxt.org, and 6 agent-protocol manifests (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance. Same engine as agent-ready.dev.

MCP server for semantic git queries. Walks the local `git` CLI plus optional GitHub API. Local-first; GH token only needed for PR/issue linkage. ## Why `git` answers these poorly: - "Who last touched this function?" — `git blame` only gives lines - "What PR introduced this line?" — manual blame → SHA → search GH - "Which files always change together?" — no built-in - "Show unmerged branches older than 30 days" — bash gymnastics - "What did I work on last week?" — manual log scrub LLM agents need this context to make safe edits. ## Tools | Tool | Purpose | |------|---------| | `who_touched` | Group blame by author. Lines, commits, last-touched, primary owner. | | `introducing_pr` | Find PR that introduced a line or commit. Merge-msg parse + GH API fallback. | | `co_change` | Files most often changed together with the input file. | | `branch_hygiene` | Branches w/ ahead/behind, last commit, merged status, stale flag. | | `recent_work` | Standup helper: author's commits + files + ins/del in a window. | | `commit_context` | Full commit context: subject, body, files, PR, related issues. | ## Install ```bash npm install -g git-insight-mcp claude mcp add --scope user git-insight -- git-insight-mcp

Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.

terminal-history-mcp gives AI agents (Claude Code, Cursor, Cline, Zed, any MCP client) full-text search over your shell history. - Local-only, no cloud — SQLite FTS5 at ~/.terminal-history-mcp/history.db - Supports zsh, bash, fish - Captures cwd, exit code, duration via opt-in shell hook - 11-pattern secret redaction runs BEFORE insert (GitHub PATs, OpenAI keys, AWS, JWTs, bearer tokens, env vars, CLI flags, basic-auth URLs) - Hash-deduped, idempotent reindex - WAL mode — safe across parallel sessions Ask: "When did I last ssh into staging?", "Show failed commands today", "What did I run in /etc/nginx yesterday?", "Show context around kubectl apply".

Wayforth is the neutral service layer for AI agents — where they discover services, route requests, and pay through one path.

MCP server for Faster Fixes. Lets AI agents list, triage, and resolve client feedback collected from your website widget — directly from your terminal.

Local Brain/Hands/Eyes loop for AI coding agents. Persistent markdown knowledge vault with FTS5 search, sandboxed command execution via project-defined tools, and a feedback journal that compounds every session. 46 MCP tools. 100% local, 0% egress.

Local-first AI context and memory server for cross-tool coding continuity. MindSwap helps coding agents and developers persist project context, search prior decisions, manage structured memory, resume work across sessions, and keep MCP-compatible tools aligned through one shared context layer.

Release gate agents call before they tell users a public website is ready to ship. Scans public websites across security, SEO, accessibility, legal compliance, and sustainability.

Lightrun MCP connects AI coding assistants to live runtime context from production and staging applications for safe code-level debugging without redeploying. It lets MCP-compatible clients discover runtime sources, inspect live expression values, capture call stacks, measure execution duration, count executions, and collect numeric runtime metrics directly from the AI workflow.

Local-first memory firewall and MCP server for AI agents. Audrey gives coding agents recall, memory capsules, preflight checks, reflexes, validation, tool-trace learning, contradiction handling, and SQLite/sqlite-vec storage.

Local-first MCP code intelligence server with 37 tools — hybrid search, blast-radius analysis, diff-aware risk-scored review, and bi-temporal memory pinned to git SHAs. Stops AI agents from hallucinating function names that don't exist in your codebase. Published 60-task retrieval benchmark with reproducible harness. MIT.

Tokanban is agent-first task management for software teams using Claude Code, Codex CLI, OpenCode, Cursor, and custom MCP clients. Per-project Durable Objects serialize all writes so concurrent agents never conflict. Every mutation is idempotent and ETag-guarded. Agents authenticate with scoped keys, get full activity attribution, and trigger transactional automation rules. Free to start.

Autonomous AI browser testing. Give Testorax a URL and it crawls your app, generates test scenarios, runs them in real browsers, and returns a bug report with screenshots. No test code to write. Works with any deployed web app.

Tells you how you and your Claude agent actually work together. Reads your CLAUDE.md, hooks, skills, memory, and scheduled tasks — then writes you a letter. Three core tools: collab (collaboration scoring + lint), security (secrets scan, prompt-injection surfaces, rule conflicts), and health (orphan jobs, overlap, structural drift). Local-only — no API keys, no data leaves your machine. Source: github.com/bleedmode/dearuser

DevSpeak bridges the gap between product and engineering. Powered by Gemini AI, it instantly translates ambiguous stakeholder requirements into structured technical specs, Jira tickets, and API designs tailored to your specific tech stack and audience level.

Selvedge is a local, open-source MCP server that captures the *why* behind every change AI coding agents make — live, in the moment, from the agent's own context (not inferred later by a second LLM). It logs the entity (DB column, table, function, route, env var, dependency), the diff, and the reasoning to a local SQLite store, then reads it back: `selvedge blame users.email` returns the most recent change + the original reasoning, and `prior_attempts` lets the agent check "was this tried here before, and how did it turn out?" before editing. 8 MCP tools: log_change, diff, blame, history, changeset, search, prior_attempts, stale_decisions. As of v0.3.9 it also exports Agent Trace v0.1.0 records (`selvedge export --format agent-trace`) for cross-tool interop. Zero-config and local-first (no telemetry, no network, no LLM calls in core), Python 3.10+, MIT.

Hosted MCP endpoint that returns realistic fake data for prototyping agents. Paste one URL into Claude Code, Cursor, or Claude Desktop — 12 pre-built tools covering users, products, orders, events, email, and knowledge base search. No signup, no config, no auth. Built for developers who want to prototype agent workflows before wiring up a real backend.