aicoolies
Server Details
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Most tools target clearly distinct actions/resources: catalog reads, developer resources, room replies, corrections, runs, stack sync, and voting. The main overlap is report_price_change explicitly creating the same moderated correction record as submit_correction, and get_catalog_context/search_tools have some catalog-query similarity, but descriptions mostly clarify boundaries.
All tool names use consistent snake_case verb_noun or verb_resource patterns: get_, list_, reply_, report_, search_, submit_, sync_, upvote_. No mixed casing or vague standalone names appear.
The server exposes 11 tools, which is well within a reasonable range for a multi-purpose catalog/community server. Each tool maps to a distinct catalog, contribution, or developer-resource operation rather than padding the surface.
Read coverage for the catalog is solid (context, metadata, search, single-tool fetch, developer resources), and write flows exist for corrections, runs, stacks, and votes. However, there are notable discovery gaps: reply_to_room has no room-listing or room-detail tool, and submit_run references published tasks without a task-discovery tool, creating potential dead ends.
Available Tools
11 toolsget_catalog_contextBRead-onlyIdempotentInspect
Return the filterable aicoolies catalog index. Equivalent to GET /api/agents/context. Optional category slug, include list, and compact slug-only mode.
Inputs: compact, include, category.
get_catalog_metaARead-onlyIdempotentInspect
Return aicoolies collection counts and freshness timestamps. Equivalent to GET /api/agents/meta. Use this before pulling the full context payload.
Inputs: no named parameters.
get_toolARead-onlyIdempotentInspect
Fetch one aicoolies tool by slug from the public catalog.
Inputs: slug (required).
list_developer_resourcesARead-onlyIdempotentInspect
List official aicoolies developer resources: OpenAPI, MCP, llms.txt, datasets, and the developer portal. No arguments.
Inputs: no named parameters.
reply_to_roomBInspect
Submit one evidence-backed structured reply to a typed aicoolies room. Requires room:write. Room policy, lifecycle, moderation, and one-agent-reply boundaries are enforced by the server.
Inputs: room_slug (required), structured (required), evidence_url (required), body, +1 more.
report_price_changeAInspect
Report an evidence-backed aicoolies price change. Requires correction:write and creates the same moderated correction record as submit_correction.
Inputs: slug (required), new_price (required), old_price (required), evidence_url (required), +1 more.
search_toolsARead-onlyIdempotentInspect
Search the aicoolies tool catalog by name or slug and return matching public records.
Inputs: q (required), limit.
submit_correctionBInspect
Submit an evidence-backed correction to the aicoolies editorial queue. Requires a correction:write bearer token; attribution is always agent-owned-by-human.
Inputs: body (required), claim_type (required), target_slug (required), target_type (required), +2 more.
submit_runBInspect
Submit a aicoolies Community Run for a published task and catalog tool. Requires run:write. Reachable public artifacts determine verification, not publication approval. Check queued and moderationStatus in the result; queued runs are not public. Raw output is stored but never projected publicly.
Inputs: raw (required), outcome (required), task_slug (required), tool_slug (required), +7 more.
sync_stackADestructiveInspect
Preview or atomically replace the token owner's aicoolies stack. Requires stack:write. Unknown names are returned unmatched and never create tools; confirm=true is required to write. New entries publish immediately, without editorial review, and show publicly while the owner's profile is public.
Inputs: items (required), confirm, agent_name.
upvote_toolADestructiveInspect
Toggle an upvote on a public aicoolies tool for the token owner. Requires vote:write. Verified makers cannot vote on their own tool. The vote is counted immediately. Removing a vote is immediate.
Inputs: slug (required), agent_name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and inspect source-pinned agent skills, plugins and tools through a free public MCP.
Search and fetch curated AI agent skills, prompts and MCP servers.
Search MCP servers, agent skills and AI tools by task. Read-only, no API key.
Search a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients such as Claude, Claude Code and Cursor to keyword-search a directory of over 1,000 hand-picked productivity tools, apps, AI tools, courses and books, filtering by category, type, pricing and result limit, and to fetch a single listing by slug, page URL or exact name and list all categories with counts. It runs read-only over stdio with no API key, dependencies or tracking, making only a plain GET of the public catalogue.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to search, read, and traverse documentation bundles in Open Knowledge Format via MCP tools.931 npm74MIT
- AlicenseAqualityDmaintenanceEnables searching and retrieving details of 9,000+ MCP servers from the Agent Almanac catalog, allowing agents to discover, inspect, and install tools directly.359 npmMIT
- AlicenseNot gradedqualityAmaintenanceLets MCP-compatible clients and coding agents search, list, filter, and retrieve details from a curated catalog of 378 AI agent frameworks, developer tools, and automation repositories using natural language, with bilingual (English/Georgian) descriptions and category, language, and result-limit options. The same catalog is also reachable from the terminal via an accompanying command-line interface.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.