com.agentoolrankPublished by agentoolrank.comOfficial publisherv1.1.1Updated Oct 28, 2026
Search and compare open-source AI agent tools ranked by live GitHub activity, with compare prompts.
Hosted AgentoolRank server that lets an assistant search, compare and find alternatives to open-source AI agent tools ranked by GitHub activity.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.agentoolrank%2Fagent-tools/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"agentoolrank": {
"type": "http",
"url": "https://agentoolrank.com/api/mcp"
}
}
}Search and compare open-source AI agent tools from your AI assistant, ranked by live GitHub activity.
AgentoolRank 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.
https://agentoolrank.com/api/mcp (Streamable HTTP, no auth required)com.agentoolrank/agent-toolsAuthorization: Bearer <key> to identify your agent.Ready-made prompts your MCP client can offer (prompts/list, prompts/get):
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project). See examples/cursor-mcp.json:
Add 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.
Add to ~/.codex/config.toml. See examples/codex-config.toml.
The same data is also available without MCP. See examples/curl.sh.
AgentoolRank is run by TENSO LLC. Questions or corrections: [email protected]. Privacy · Terms.
The contents of this repository (documentation and configuration examples) are MIT licensed. The AgentoolRank website, data and service are not part of this repository.
Source: README.md at commit cf0b4f9
[Tool directory] Search open-source AI agent tools (frameworks, coding agents, memory, RAG, observability, MCP servers) ranked by GitHub activity. Returns stars, 30-day star growth, capabilities and alternatives.
limitqueryrequired[Tool directory] Get details for one tool by slug (from search_tools): GitHub stats, capabilities, best-for, limitations and alternatives.
slugrequired[Tool directory] Use this when you need alternatives to a known AI agent tool, not launch directories. Pass slug, the tool identifier returned by search_tools (for example, dify), not a URL or directory domain. Returns the source tool slug and its recorded alternatives with GitHub stats for comparison.
slugrequired[Tool directory] List an AI agent tool (framework, coding agent, MCP server, memory/RAG, evals, browser agent...) on AgentoolRank for free. The free listing is queued; the response lists every paid option (price, days to go live, checkout_url for your human to pay) and recommends the cheapest one that fits max_budget_usd / deadline_days. Returns submission_id + status_token for get_submission_status, and message_for_human: a summary to forward to your human.
urlrequirednamerequiredemailrequiredtaglinerequiredgithub_urldeadline_dayswant_featuredmax_budget_usd[Tool directory] Use this when checking the AgentoolRank review status of a tool you submitted via submit_tool. Requires submission_id and status_token from that submission; returns review status, queue position and listing URL when available. Not for launch-directory progress — that is my_progress.
status_tokenrequiredsubmission_idrequired[Launch directories] Use this when you need a free overview of the best-fit launch directories for a product_type: top 5, no key required, with conditions and submission steps. An optional valid Submit Kit key ($29) returns the full overview and directories to avoid. To work through the full list one directory at a time with a Submit Kit key, use next_directory instead.
keylanguagesopen_sourceproduct_typerequired[Launch directories] Use this when working through launch directories with a required Submit Kit key. Returns exactly one next directory when available; submit there, then call report_result. May return report_first or done instead. At most 3 unreported sites, up to 50 per key; product_type is bound on first issuance. For a free overview list, use recommend_directories.
keyrequiredproduct_type[Launch directories] Use this when recording an outcome for a domain issued by next_directory, not submitting a tool to AgentoolRank. Requires the same Submit Kit key, that domain and status: submitted, listed, rejected, failed or skipped; listing_url and note are optional. Records the outcome and clears that site's unreported slot. Reporting 'listed' is only a lead: it counts toward listing rate only after our daily check finds it live.
keyrequirednotedomainrequiredstatusrequiredlisting_url[Launch directories] Use this after report_result or to resume a session; requires the Submit Kit key. Returns product_type, cap, sites, progress_page and counts: issued (total handed out), unreported, submitted, listed_reported, rejected, failed and skipped. Outstanding sites have status 'issued' in sites. Remaining allowance is cap minus issued, not a returned field or a guarantee of matching directories. Not for AgentoolRank listing review status — that is get_submission_status.
keyrequired100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
claude mcp add --transport http agentoolrank https://agentoolrank.com/api/mcp{ "mcpServers": { "agentoolrank": { "url": "https://agentoolrank.com/api/mcp" } }}GET https://agentoolrank.com/api/v1/tools?q=rag&limit=10GET https://agentoolrank.com/api/v1/tools/{slug}POST https://agentoolrank.com/api/v1/submissions