{"id":"9e17e9aa-01c8-4bf1-b087-2fee96aa505b","slug":"agentoolrank-mcp","kind":"mcp","name":"agentoolrank-mcp","summary":"Search and compare open-source AI agent tools from your AI assistant: hosted MCP server and JSON API by AgentoolRank","owner":"agent-gigmole","repoUrl":"https://github.com/agent-gigmole/agentoolrank-mcp","license":"MIT","licenseTier":"permissive","trust":"community","stars":0,"match":null,"fewStars":true,"format":"mcp","createdAt":"2026-10-04T13:26:02.000Z","addedAt":"2026-10-13T22:01:20.471Z","logoUrl":"https://avatars.githubusercontent.com/u/270148973?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["cloud-infra","search","memory-knowledge"],"tags":["agent-tools","ai-agents","open-source"],"runtime":"remote","local":false,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-17T04:56:23.124Z","sample":false,"url":"https://conduits.dev/tools/agentoolrank-mcp","language":"","transports":["http"],"install":{"remoteUrl":"https://agentoolrank.com/api/mcp"},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# AgentoolRank MCP server\n\n[![MCP Badge](https://lobehub.com/badge/mcp/agent-gigmole-agentoolrank-mcp)](https://lobehub.com/mcp/agent-gigmole-agentoolrank-mcp)\n\nSearch and compare open-source AI agent tools from your AI assistant, ranked by live GitHub activity.\n\n[AgentoolRank](https://agentoolrank.com) tracks hundreds of open-source AI agent tools (frameworks, coding agents, memory, RAG, evals, MCP servers) and ranks them by GitHub activity: stars, star pace, commits, releases and package downloads, refreshed daily. This repository documents how to connect to its hosted MCP server and JSON API. The server runs on agentoolrank.com; there is nothing to install or self-host.\n\n- **MCP endpoint:** `https://agentoolrank.com/api/mcp` (Streamable HTTP, no auth required)\n- **Official MCP Registry:** `com.agentoolrank/agent-tools`\n- **Optional API key:** one click, no signup, at [agentoolrank.com/api-key](https://agentoolrank.com/api-key). Send it as `Authorization: Bearer <key>` to identify your agent.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `search_tools(query, limit?)` | Find tools for a job, ranked by relevance then GitHub activity. |\n| `get_tool(slug)` | Stars, 30-day star growth, capabilities, limitations and who it is best for. |\n| `get_alternatives(slug)` | Open-source alternatives to a tool, with their GitHub stats. |\n| `submit_tool(url, name, tagline, email, …)` | List a tool. The response shows every pricing option up front, including the free one. |\n| `get_submission_status(submission_id, status_token)` | Review status of a submission. |\n| `recommend_directories(product_type)` | Launch directories our own products went through, with free-tier conditions and the steps only a person can do. The top 5 for each product type are free. |\n| `next_directory(key, product_type?)` | Submit Kit key (9): hands your agent the next directory that fits the product, one at a time (up to 50, at most 3 unreported). |\n| `report_result(key, domain, status, listing_url?)` | Submit Kit key: report what happened at a directory. Reports are leads; listing rates count only listings our own daily check verifies. |\n| `my_progress(key)` | Submit Kit key: every directory handed out so far and its reported status (also at agentoolrank.com/submit-kit/progress). |\n\n## Prompts\n\nReady-made prompts your MCP client can offer (`prompts/list`, `prompts/get`):\n\n| Prompt | Arguments | What it does |\n| --- | --- | --- |\n| `compare_tools` | `tool_a`, `tool_b` | Compares two tools side by side: GitHub stars, 30-day star growth, last release, downloads, best for, limitations |\n| `find_alternatives` | `tool` | Lists open-source alternatives to a tool, ranked by live GitHub activity |\n| `launch_plan` | `product_type` (`ai_tool`, `mcp_server`, `dev_tool`, `saas`, `other`), optional `product_url` | Plans where to list a new product: which launch directories fit it and which to skip |\n\n## Resources\n\n| URI | Content |\n| --- | --- |\n| `agentoolrank://about` | How the ranking works and what this server offers (Markdown) |\n| `agentoolrank://top-tools` | The current top 20 open-source AI agent tools by GitHub activity, live (Markdown table) |\n\n## Connect\n\n### Claude Code\n\n```sh\nclaude mcp add --transport http agentoolrank https://agentoolrank.com/api/mcp\n```\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json` (or `.cursor/mcp.json` in a project). See [examples/cursor-mcp.json](examples/cursor-mcp.json):\n\n```json\n{\n  \"mcpServers\": {\n    \"agentoolrank\": { \"url\": \"https://agentoolrank.com/api/mcp\" }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd it under Settings → Connectors as a custom connector with the URL above. Or use the `mcp-remote` bridge in `claude_desktop_config.json`. See [examples/claude_desktop_config.json](examples/claude_desktop_config.json).\n\n### Codex CLI\n\nAdd to `~/.codex/config.toml`. See [examples/codex-config.toml](examples/codex-config.toml).\n\n## JSON API\n\nThe same data is also available without MCP. See [examples/curl.sh](examples/curl.sh).\n\n```\nGET  https://agentoolrank.com/api/v1/tools?q=rag&limit=10\nGET  https://agentoolrank.com/api/v1/tools/{slug}\nPOST https://agentoolrank.com/api/v1/submissions\n```\n\n## About\n\nAgentoolRank is run by TENSO LLC. Questions or corrections: hello@agentoolrank.com. [Privacy](https://agentoolrank.com/privacy) · [Terms](https://agentoolrank.com/terms).\n\nThe contents of this repository (documentation and configuration examples) are MIT licensed. The AgentoolRank website, data and service are not part of this repository.\n"}