Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
MewCP 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
Giving your AI agent access to Gmail, GitHub, Notion and the rest usually means setting up every app separately, pasting API keys where the agent can see them, and having no idea what it actually did. And the more apps you add, the slower and more expensive your agent gets.
MewCP fixes that. Connect each app once and your agent can use all of them from a single link. Your keys never reach the agent, you choose exactly what it's allowed to do, and every action is logged so you can see what happened. Your agent only loads the tools it needs for the task in front of it, which cuts tool overhead by up to 95%.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http mewcp-mcp https://gateway.mewcp.com/personal/mcp --header 'Authorization: Bearer ${MEWCP_API_KEY}'
# 2 — ask your agent for something these tools do
# search, get_schema, list_accounts and 1 more
It needs MEWCP_API_KEY (Get a key at https://mewcp.com/dashboard/api-keys): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
MewCP costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
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, read from the address; if the publisher says otherwise, swap that one word. Claude Code reads MEWCP_API_KEY (Get a key at https://mewcp.com/dashboard/api-keys) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx MEWCP_API_KEY … and open a new terminal (Windows).
claude mcp add --scope user --transport http mewcp-mcp https://gateway.mewcp.com/personal/mcp --header 'Authorization: Bearer ${MEWCP_API_KEY}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Get a key at https://mewcp.com/dashboard/api-keys. You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
4 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.
Find tools across this toolset's member servers by keyword. Use the default detail="brief" to pick candidates: it returns names and descriptions, trimmed to 700 characters (ending in …) to save context. Then call get_schema on the tools you will use for their full description and parameters. detail="detailed" adds parameter lists to every hit and detail="full" adds complete JSON schemas; both cost
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | keywords to match against tool names/descriptions |
| detail | string | no | verbosity: brief (default, recommended: names + trimmed descriptions), detailed (+parameters), full (+complete JSON schema). Prefer brief, then get_schema on chosen tools. |
| limit | number | no | max results to return (default 10, max 50) |
Get parameter details for specific member tools identified by search. Defaults to a compact parameter list; pass detail="full" for the complete input and output JSON schemas.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tools | array | yes | the (server_maskedId, tool_name) pairs to describe |
| detail | string | no | verbosity: brief, detailed (default), full (complete JSON schema) |
List the connected accounts available for a provider, each with its alias and account identity. Accounts whose token can no longer be refreshed are flagged as needing reconnection. Pass an alias to call_tool to choose which account a call uses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | provider slug, e.g. google-gmail |
Call a tool on a member server. Identity comes from the request (never args); alias only selects which connected account to use when several exist.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| server_maskedId | string | yes | member server maskedId (from search results) — routing key |
| tool_name | string | yes | tool name on that server (from search results) |
| args | object | no | tool arguments |
| alias | string | no | connected-account alias (from list_accounts) — required only when multiple accounts exist |
- 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 MewCP 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 0.1.0.
- The version this listing went live with, after review.
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 MewCP 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.