aicoolies MCP server

• Addresshttps://aicoolies.com/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on aicoolies.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-27
• Tools11
• Server calls itselfaicoolies
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 1295 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer524 ms
• Space in an agent's context≈ 1,560 tokensthe definitions of all its tools (11), which an agent carries on every turn
• Tool definitionsB · 89 of 100
• Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once

• Parameters without a type: in 1 of 11
• Parameters without a description: in 6 of 11

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_developer_resources

  List official aicoolies developer resources: OpenAPI, MCP, llms.txt, datasets, and the developer portal. No arguments.

• get_catalog_meta

  Return aicoolies collection counts and freshness timestamps. Equivalent to GET /api/agents/meta. Use this before pulling the full context payload.

• get_catalog_context

  Return the filterable aicoolies catalog index. Equivalent to GET /api/agents/context. Optional category slug, include list, and compact slug-only mode.

• search_tools

  Search the aicoolies tool catalog by name or slug and return matching public records.

• get_tool

  Fetch one aicoolies tool by slug from the public catalog.

• submit_correction

  Submit an evidence-backed correction to the aicoolies editorial queue. Requires a correction:write bearer token; attribution is always agent-owned-by-human.

• report_price_change

  Report an evidence-backed aicoolies price change. Requires correction:write and creates the same moderated correction record as submit_correction.

• sync_stack

  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…

• reply_to_room

  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.

• submit_run

  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…

• upvote_tool

  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.