Headless web analytics for AI agents. A broad range MCP tools for traffic, events, funnels, conversions, sources, and performance. No dashboard — agents query structured JSON directly.

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

Korean equity intelligence MCP for AI agents and analysts. Answers KOSPI/KOSDAQ/KRX DART filings (전자공시), 5%-rule shareholding disclosures with named-entity classification — Korean activists (KCGI / Align Partners / Truston / Anda / Cha / VIP / Life / Platform + ValueAct/Elliott when filing in Korea) and global foreign holders (BlackRock / Vanguard / State Street / Fidelity / Capital Group / T. Rowe Price / Wellington / Norges Bank / GIC / Temasek / Goldman / JPMorgan / Morgan Stanley / Citadel / Millennium / Bridgewater + 4 more), Korean industry news across 16 sectors (semiconductor / shipbuilding / battery / biotech / defense / auto / EV / AI / steel / petrochem / construction / fintech / gaming / e-commerce / telco / energy). On-demand English translation cached server-side. Streamable HTTP at https://mcp.koreanpulse.dev/mcp — connect from Claude.ai / ChatGPT / Cursor / OpenAI Responses API. 7 tools: 5 free + 2 paid (Solo $29/mo, billed via Polar).

Load and parse webpages using natural language queries to extract structured data. Manage browser sessions for interactive automation and retrieve usage metrics.

MCP server for Archivarix Tube Search — search archived YouTube videos including deleted content. Channel discovery, full-text search, video metadata, transcripts, and AI-generated summaries via the Wayback Machine. 1.5B+ videos indexed since 2005.

MCP server for querying Janus analytics — let your AI agent check your dashboard, events, funnels, and usage.

Connect AI agents to your test results, insights, and targets. Query test runs, failures, flaky tests, and regressions across frameworks including Playwright, Jest, Pytest, Cypress and more.

One API for Search, Crawling, and Sitemaps

The match graph for AI. Search 100,000+ capabilities across 13,000+ AI artifacts — models, agents, MCP servers, APIs, frameworks, CLIs, and more. Every query learns from the graph, making the next search smarter. 10 tools: search, find_mcps, get_artifact, compare, find_stack, resolve_capability, trust_passport, feedback, subscribe, unsubscribe. Install: npx -y @unfragile/mcp-server

Your AI forgets everything between sessions. Rekindle fixes that with two tools that close the continuity loop: boot_report orients the assistant at session start (identity, checkpoints, gaps, orientation score), and end_session captures structured handoff at session end (decisions, open loops, constraints, relational context). 7 MCP tools, 64 tests, local SQLite, no cloud, no API keys. New in v0.2.0: • Orientation domain layer with gap detection and 100-point scoring • end_session tool with typed continuity records (checkpoint, decision, open_loop, constraint, preference, warning, relational_delta, next_session_focus) • Schema migration adding type, source, and session_id columns • Project-aware scoring • Full outside review from an independent AI reviewer

Institutional cross-border settlement rail for AI agents — any currency pair, ~75-120 bps via Base mainnet. 11 tools: quote, ESG scoring, oracle status, fee verification, competitor benchmarking, and on-chain settlement. ESG-linked fees, MiCA/FCA/Basel III-aligned, on-chain verifiable receipts.

3D Filament DB is a community database of 3D printer filaments with search, pricing, and store availability. The MCP server gives AI agents direct access to the database with four tools: search_filaments — filter by material (PLA, PETG, ABS, TPU, …), manufacturer, color, store, tag, or country; sort by name or cheapest price; returns paginated results with specs and pricing get_filament — full detail for a single filament: all color variants with hex codes, technical specs (tensile strength, elongation, print temps, …), TDS data, and per-store prices list_manufacturers — all manufacturers in the database with ratings list_materials — all material types in the database No authentication required. Free to use.

Give brains to your small models. MCP server that enforces step-by-step Chain-of-Thought — turns 4B models into methodical reasoners

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Browser automation and web scraping

PropContext gives AI assistants real-time access to Bangalore's new launch residential market — sourced directly from the Karnataka RERA government portal. Every project is RERA-verified. Tools: search_projects, get_project, search_fulltext, get_builder_projects, get_recent_registrations, search_by_commute, book_site_visit No API keys required. Remote MCP server — just add the URL.

petromcp is a small MCP server that lets Claude (or Cursor, or Codex CLI, or anything else that speaks MCP) read .las well log files directly. If you have ever tried asking an LLM about a well log you know the workflow today is to copy-paste curve values into the chat. Petroleum file formats are binary or semi-structured and the hosts can't open them. The current release wraps lasio (the established open-source LAS parser) and exposes five tools: read_las_file, summarize_las_curves, read_las_curve, compare_well_logs, and convert_units. There is a strict path allowlist by default, the server makes zero outbound network calls, and the only data that leaves your machine is whatever the host application would have sent to its language model anyway. DLIS, SEG-Y headers, and pump card data are queued for the next releases. Repo, install instructions, and tool reference are in the README. Feedback on the QC heuristics from anyone with a petrophysics background would be particularly welcome. They are defensible defaults but I would rather have them shaken out than discover problems after a launch demo. If you have the repo cloned, the server config is: { "mcpServers": { "petromcp": { "command": "uv", "args": [ "run", "--no-sync", "--project", "/absolute/path/to/petromcp", "petromcp", "serve" ] } } } Else, you can use { "mcpServers": { "petromcp": { "command": "uvx", "args": [ "--from", "git+https://github.com/ameyxd/petromcp", "petromcp", "serve" ] } } }

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

MCP wrapper for Askew's x402 endpoints — 8 tools (3 free, 5 paid in USDC on Base): live DeFi yield comparison, SOL/ATOM staking routing, agent-economy research search, Guardian security threat intel, and a combined strategic feed.

Revuo is the B2B SaaS directory built for the AI-citation era. While G2 and Capterra were built for humans clicking through review pages, Revuo is built for the parallel reality where buyers' first stop is an LLM. Every listing carries a typed capability schema (integrations, standards support, pricing model, deployment options), is continuously re-verified by a weekly crawler, and is exposed via a public MCP server agents can call directly. Revuo's three launch verticals are PIM/PXM, Tender Management, and Billing & Invoicing — chosen for ACVs that justify vendor distribution spend and for AI-citation buyer behavior that already exists today. Capability-structured. Continuously verified. Agent-callable.

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

高德地图官方 MCP Server

summarize chat message

Retrieving and analyzing issues from Sentry.io

Place order with your e-commerce agent using Zadig&Voltaire MCP

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.