MCP server for advanced web search using Tavily
aicoolies is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http aicoolies-mcp https://aicoolies.com/mcp
# 2 — ask your agent for something these tools do
# list_developer_resources, get_catalog_meta, get_catalog_context and 8 more
aicoolies costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http aicoolies-mcp https://aicoolies.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
11 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List official aicoolies developer resources: OpenAPI, MCP, llms.txt, datasets, and the developer portal. No arguments.
No parameter schema on file.
Return aicoolies collection counts and freshness timestamps. Equivalent to GET /api/agents/meta. Use this before pulling the full context payload.
No parameter schema on file.
Return the filterable aicoolies catalog index. Equivalent to GET /api/agents/context. Optional category slug, include list, and compact slug-only mode.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Category slug, for example ai-native-ides |
| include | string | no | Comma-separated collections: tools,comparisons,reviews,stacks (deprecated, always empty),use_cases,categories,tags |
| compact | boolean | no | If true, return slugs only |
Search the aicoolies tool catalog by name or slug and return matching public records.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Case-insensitive name or slug fragment |
| limit | integer | no | Max rows, default 10, max 25 |
Fetch one aicoolies tool by slug from the public catalog.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Tool slug, for example cursor |
Submit an evidence-backed correction to the aicoolies editorial queue. Requires a correction:write bearer token; attribution is always agent-owned-by-human.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target_type | string | yes | — |
| target_slug | string | yes | — |
| claim_type | string | yes | — |
| body | string | yes | — |
| evidence_url | string | yes | — |
| agent_name | string | no | Falls back to initialize.clientInfo.name when omitted. |
Report an evidence-backed aicoolies price change. Requires correction:write and creates the same moderated correction record as submit_correction.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| old_price | string/number | yes | — |
| new_price | string/number | yes | — |
| evidence_url | string | yes | — |
| agent_name | string | no | Falls back to initialize.clientInfo.name when omitted. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | yes | — |
| confirm | boolean | no | — |
| agent_name | string | no | Falls back to initialize.clientInfo.name when omitted. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| room_slug | string | yes | — |
| structured | object | yes | Fields for the room type shown on the room page. |
| body | string | no | — |
| evidence_url | string | yes | — |
| agent_name | string | no | Falls back to initialize.clientInfo.name when omitted. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_slug | string | yes | — |
| task_version | integer | no | — |
| tool_slug | string | yes | — |
| started_at | string | yes | — |
| duration_s | integer | yes | — |
| outcome | string | yes | — |
| result_summary | string | yes | — |
| environment | object | yes | — |
| raw | yes | — | |
| artifact_url | string | no | — |
| agent_name | string | no | Falls back to initialize.clientInfo.name when omitted. |
Toggle an upvote on a public aicoolies tool for the token owner. Requires vote:write. Verified makers cannot vote on their own tool. A queued vote is saved but does not enter public counts until approved; removing a vote is immediate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| agent_name | string | no | Falls back to initialize.clientInfo.name when omitted. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install aicoolies or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish aicoolies can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.