2889 Model Context Protocol servers — searchable, rated, ready to install.
Share text, markdown, code, or HTML as auto-expiring links
Local chronological memory banks you control; Claude recalls them via MCP.
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Build a game's 2D art layer with your agent: characters, animations, tilesets, levels, 5 engines.
MCP protocol enforcing explicit task acceptance and attestation-tagged completion claims.
Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
Pay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.
F1-grade MCP certification. 52 tests, 9 tiers (49 scored + T9 Receipt validation). Ecosystem: #2759
MCP server giving AI agents eyes on OpenImageDebugger buffers in live gdb/lldb sessions
Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Alces for Jira Data Center — MCP server bridging Jira DC/JSM with AI agents
Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.
One place to build, share, and govern the skills and tools your AI agents use at work.
Static analysis scanner for MCP server code and multi-tenant SaaS applications.
Rust MCP server and CLI for UniFi Network controller operations.
Shared memory for a team in Claude Code: what one person records, everyone has.
Chữ Nôm lookup, search and Vietnamese ↔ Nôm conversion, incl. 2,422 unmapped PUA codepoints.
Narrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.
Extract file and directory paths from config files and code, with their kind and position.
Discover funded agent work and prepare approval-gated TaskMarket delegations.
Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.
Read-only TwinCAT ST intelligence: resolve symbols, library APIs, docs, validate PLC code.
Read-only ProvenTools business ideas, evidence, build prompts, and validation reports.
POST /mcp