The tools agents can call
150,210 unique MCP servers across ten major directories and registries, each with its sources and history.
Deduplicated: a server listed on several directories counts once. Includes MCP Toplist’s dataset (CC BY 4.0) for Glama, mcp.so and PulseMCP. 14,157 listings from bulk publishers wait for review.
Orbit
orbit-search
The most in-depth, source-backed context about a person for deep personalization and research.
Listed on MCP RegistrySmithery
Forkmate
forkmate
Free AI calorie & macro tracker: tell your AI what you ate and it logs it to your private food diary
Listed on MCP RegistrySmithery
Anyway Possible Agent Utilities
anywaypossible
A free tool recommender plus eight x402 tools for payments, merchants, wallets, and web evidence.
base_balancebatch_check_urlscheck_url+6Listed on MCP RegistrySmithery
ToolBench Cnowyourlink public Spotlights
arneffm
Anonymous read-only access to settled advertising Spotlights, with an MCP Apps card.
create_sandbox_jobget_current_spotlightget_sandbox_job+2Listed on MCP RegistrySmithery
Wiggle
jamesonhussey99
Privacy-first coordination for autonomous agents: rooms, messaging, inbox, and per-agent memory.
assign_rolecreate_pollcreate_role+21Listed on MCP RegistrySmithery
Radicado Uno
radicadouno
Colombian company and procurement data by NIT, each field with its official source. Free checks.
Listed on MCP RegistrySmithery
SERPHouse
serphouse
SERPHouse MCP Server enables real-time web search inside your AI applications. Fetch structured results from Google, Bing, and Yahoo to power RAG, SEO tools, and intelligent agents without dealing with scraping. Fast, reliable, and built for developers, it delivers clean SERP data to help your AI stay accurate and up-to-date. Learn more: https://www.serphouse.com/web-search-api
Listed on Smitherymcp.so
ToolBench FZeroMind (OrigoZero game engine)
origozero
Build, run and publish 3D games in the Zero engine from Claude Code, Cursor or Codex, over MCP.
Listed on MCP RegistrySmithery
ToolBench FKenwea — Sandbox Attestation & Agent Marketplace
kenwea
Signed sandbox verdicts on any artifact, plus an agent marketplace. No key, no signup, no payment.
kenwea.agent.getIdentitykenwea.agent.sendHeartbeatkenwea.analytics.getForecast+25Listed on MCP RegistrySmithery
AIMarket — live agent marketplace
alexar76
Search and invoke real AI capabilities on modelmarket.dev. Free trial, then USDC on Base.
air_quality_nowfair_randommarket_invoke+10Listed on MCP RegistrySmithery
agent-offset-clearinghouse
jdhart81
Verified conservation credits matched to agent compute emissions — the conservation flywheel of the
bookbuy_offsetbuy_offset_budget+16Listed on MCP RegistrySmithery
+1 groupedCAIT
bitfreak
# CAIT - Core AI Toolkit A modular [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that extends AI assistants with practical capabilities: file I/O, a persistent Python REPL, AST-aware code analysis, semantic text search, document conversion, Wikipedia & arXiv tools, a persistent vector memory database, and other general utilities. A total of **37 tools across 9 modules**. Each module can be disabled independently via the `CAIT_DISABLE` environment variable. Made by AI for AI. ## Requirements - Python 3.11+ - Core: `fastmcp`, `chromadb` - Online research: `wikipedia-api`, `arxiv` - Document conversion: `docling` or `markitdown` - Scientific computing (optional, for REPL use): `sympy`, `scipy`, `matplotlib`, `plotly`, `vispy` ## Installation Install the requirements into your Python environment then copy [copilot-instructions.md](https://github.com/JacobBruce/CAIT/instructions/copilot-instructions.md) or [CLAUDE.md](https://github.com/JacobBruce/CAIT/instructions/CLAUDE.md) into the correct location (more details below). The instructions include general guidance for how to behave, how to use CAIT tools, and how to use the Firecrawl search tools. The instructions may need to be adapted to suite different setups. If you are working in a Python environment you may want to make use of this agent prompt: [python-coder.agent.md](https://github.com/JacobBruce/CAIT/agents/python-coder.agent.md). There is also [research-assistant.agent.md](https://github.com/JacobBruce/CAIT/agents/research-assistant.agent.md) for deep research. There is also a skill file called [project-planning.md](https://github.com/JacobBruce/CAIT/skills/project-planning.md) which is helpful for planning the implementation details of a project. The agent produces a PLAN.md file and TASKS.md file. ### Environment Variables | Variable | Default | Description | |----------|---------|-------------| | `CAIT_FILES_PATH` | `~/.cait/files/` | Directory for downloaded files and document cache | | `CAIT_DISABLE` | _(empty)_ | Comma-separated module names to exclude at startup (e.g. `wiki,arxiv`) | ## Client Configuration ### VS Code (GitHub Copilot) Add to your workspace `.vscode/mcp.json` or user `settings.json`: ```json { "servers": { "bitfreak/cait": { "type": "stdio", "command": "/absolute/path/to/.venv/bin/python", "args": ["-m", "cait.server"], "cwd": "/absolute/path/to/CAIT" } } } ``` > For user `settings.json`, nest the above under `"mcp": { ... }`. Copy [copilot-instructions.md](https://github.com/JacobBruce/CAIT/instructions/copilot-instructions.md) into your project's `.github/` folder to give Copilot guidance on using CAIT tools effectively. ### Claude Desktop Edit `claude_desktop_config.json`: - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` - **Linux**: `~/.config/claude/claude_desktop_config.json` - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "bitfreak/cait": { "command": "/absolute/path/to/.venv/bin/python", "args": ["-m", "cait.server"], "env": { "PYTHONPATH": "/absolute/path/to/CAIT" } } } } ``` ### Claude Code ```bash claude mcp add cait -e PYTHONPATH=/absolute/path/to/CAIT \ -- /absolute/path/to/.venv/bin/python -m cait.server ``` Copy [CLAUDE.md](https://github.com/JacobBruce/CAIT/instructions/CLAUDE.md) to your project root (or to `~/.claude/CLAUDE.md` for global use) to give Claude Code guidance on using CAIT tools effectively. ## Recommended MCP Servers ### Firecrawl [Firecrawl](https://firecrawl.dev) is a web scraping and search API that pairs naturally with CAIT, adding powerful web search, full-page scraping, and site crawling. A free API key is available at [firecrawl.dev](https://firecrawl.dev). ### Serena [Serena](https://github.com/oraios/serena) provides many tools for semantic code retrieval and editing. Both CAIT and Serena include a similar memory system so it is recommended to disable one of them. ## Tool Reference ### File System — `fs` | Tool | De
Listed on SmitheryPulseMCP
Whimbrel MedTech Analyst
glowbalpartners
Your MedTech BD analyst on demand: US medtech grants, contracts, FDA clearances, linked to source.
Listed on MCP RegistrySmithery
ToolBench C+1 groupeddriflyte-mcp-server
driflyte
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Listed on MCP RegistrySmithery
HeyMetra
heymetra
Ask across your ads, analytics, store, CRM and subscription accounts; writes wait for approval.
Listed on MCP RegistrySmithery
Sendsets
sendsets
Cold email API for AI agents: connect mailboxes, warm up, run campaigns and handle replies.
Listed on MCP RegistrySmithery
Kika
usekika
Shared memory for client engagements: decisions with reasons, blockers, promises, what was tried.
Listed on MCP RegistrySmithery
ChainGPT MCP
kohasummons
Bring ChainGPT capabilities into your AI Agent to access the latest crypto news, prices, market trends, and market news. Enhance your AI workflows with real-time Web3 data and insights. Easily integrate with your existing MCP client to stay updated on the crypto world.
Listed on SmitheryGlama
ToolBench Fone-brain
prophet-git
Shared memory for a team in Claude Code: what one person records, everyone has.
Listed on MCP RegistrySmithery
+1 groupedMCPfinder
mcpfinder
MCPfinder is an MCP server for AI. It helps an assistant discover, evaluate, and install other MCP servers. An MCP that finds MCPs. Open-source discovery for agents.
Listed on SmitheryGlama
Find your role first
yashnam15
New jobs from 13,000+ company career sites, newest first, for Claude Code, Codex and any agent.
count_jobsget_changesget_job+3Listed on MCP RegistrySmithery
ToolBench DJP Bids
a-kabe-1qio
Read-only MCP server for searching Japan government procurement bid information from the KKJ portal.
Listed on MCP RegistrySmitheryGreenlit Books
greenlitbooks
Search the Greenlit AI books, read any chapter one free, and look up the terms they define.
check_claimcite_sourcedefine_term+9Listed on MCP RegistrySmithery
ToolBench C3DPACK.ING — Container & Truck Load Planning
3dpack
Container load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in the chat.
Listed on MCP RegistrySmithery
Latest changes
Typed diffs between observations- North End Law Official MCP Registry open_matter: description changed (+"For a business associate agreement (tool "baa", $350): the client must be established in the United States, the governing law is CALIFORNIA, the client's role is BUSINESS_ASSOCIATE, and receivesPhi must be false; a vendor whose services handle protected health information should use request_consultation.")
- North End Law Official MCP Registry get_deliverable: description changed (+"A business associate agreement comes in the same formats.")
- Instilus small-business decision tools Official MCP Registry forge_competitor_research_method: tool added
- Charmnomicon Official MCP Registry whoami: description changed (+"key, your glimmer balance, and what glimmers can buy." -"key.")
Coverage
- Directory listings
- 55,435
- Brands resolved
- 23,471
- On two or more hosts
- 5,362
- Remote MCP servers
- 25,626
- Tools listed by probe
- 10,150 servers
Where are you listed?
Paste your MCP server, plugin or company URL to see your listings, tools and scan findings in one place.