44,011 MCP Servers, Scored and Updated Daily

High-precision finance & business calculations for AI agents — exact decimals, never floats.

Generate fake user profiles and companies for tests, seed data, and AI agent demos.

Cryptographic proof of existence for AI agents. Base x402, NEAR anchored. Free tier.

Opendot

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects to 1000+ app tools and MCP servers.

Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.

Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Give an AI agent its own email address: send, reply, read, and wait for mail.

Context sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.

Audit whether an AI agent can read a site: llms.txt, robots AI rules, structured data.

Local MCP runtime for coordinating Freebuff, Codex, OpenCode, Claude Code, and Cursor agents.

Flight and hotel search for the terminal, Python, and AI assistants.

Tamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.

One identity across Claude Code, Codex, Cursor, Gemini, Windsurf: shared inbox and handoffs.

Chat with your Zihin.ai agents, list them and load platform skills from any MCP client.

MCP Server for CapSolver - captcha-solving capabilities for AI agents

Cross-venue prediction markets for AI agents: Polymarket + Kalshi, costed and attributed

AI agents use your Obsidian secrets by name — values never reach their context.

ChatGPT Web2API

OpenAI-compatible API proxy for ChatGPT web — expose ChatGPT as an MCP server, REST API, and OpenAI SDK endpoint via CDP-driven browser automation