Connects Claude to a machine-readable catalog of 100+ AI tool contracts formatted under the MAI-1 spec. Exposes search_tools, get_tool, and get_trending operations that return structured JSON blocks with input/output schemas, install commands, and live reliability scores computed from public repository metadata. Use this when you want an agent to discover and evaluate tools without parsing READMEs or hallucinating APIs. Each contract compresses what matters for tool selection into four sections: logic (I/O), trust (uptime and latency), action (installation), and identity. Also serves REST endpoints at aiaam.xyz/api/v1 and machine-readable discovery files like /llms.txt and /agent.json for non-MCP integrations.
A machine-readable tool catalog for AI agents. Search 100+ verified tool contracts — install command, I/O schema, live reliability score — in a single call instead of parsing READMEs.
When an AI agent needs to pick a tool ("which library do I use for web scraping?"), today it searches the web and parses README files — thousands of tokens per candidate, with no reliability data and plenty of room to hallucinate APIs.
MAI-1 compresses what an agent actually needs into four sections:
{
"identity": { "aid": "scrapy-v1", "version": null },
"logic": {
"input_schema": { "type": "url", "description": "URL(s) to scrape" },
"output_schema": { "type": "json", "description": "Structured extracted data" }
},
"trust": {
"reliability_score": 0.95,
"latency_ms": 100,
"status": "active"
},
"action": {
"install_cmd": "pip install scrapy",
"execute_cmd": "scrapy crawl <spider_name>",
"source_url": "https://github.com/scrapy/scrapy"
}
}
aiaam is listed in the official MCP registry. Connect from any MCP client:
Claude Code:
claude mcp add --transport http aiaam https://aiaam.xyz/mcp
Cursor / generic MCP config:
{
"mcpServers": {
"aiaam": {
"url": "https://aiaam.xyz/mcp",
"transport": "http"
}
}
}
Available MCP tools: search_tools, get_tool, get_trending, get_api_manifest, compile_api.
# Search the catalog
curl "https://aiaam.xyz/api/v1/tools?q=web+scraping"
# Get a full contract
curl "https://aiaam.xyz/api/v1/tools/scrapy-v1"
# Trending tools
curl "https://aiaam.xyz/api/v1/tools/trending"
Machine-readable discovery endpoints:
| Path | Purpose |
|---|---|
/llms.txt | Full catalog in llmstxt.org format |
/agent.json | Agent discovery manifest |
/.well-known/mcp.json | MCP server metadata |
/openapi.json | OpenAPI schema |
Contracts include a telemetry_protocol block: after using a tool, agents may POST execution feedback (HTTP status, latency). This feedback feeds the reliability scores — agents that report make the catalog more accurate for every other agent. No authentication, no tracking, entirely optional.
Active development. Catalog: 100+ verified contracts across PyPI, GitHub, npm and Hugging Face. See /llms.txt for the live list.
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp
io.github.sarahpark/google-search-console