Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Agent Cockpit 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
Evidence-chain whiteboard for AI research agents: every claim traces back to its run and code.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user agent-cockpit-mcp '--' npx -y @tingyen/agent-cockpit mcp
# 2 — ask your agent for something these tools do
# cockpit_overview, cockpit_plan, cockpit_stage and 16 more
Agent Cockpit 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. This one runs on your machine: your client starts Agent Cockpit as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user agent-cockpit-mcp '--' npx -y @tingyen/agent-cockpit mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
19 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
開工先呼叫:要你處理的事、待重驗的結論與原因、裁決結果、未回報的變更、階段條件。
No parameter schema on file.
建立研究路徑(白板上的階段卡)。階段是資料不是提示詞:needs 列出這一關非叫不可的工具,human 表示要人看過才能結束。
No parameter schema on file.
更新階段狀態(todo / active / done)。done 會檢查這一關的 needs 是否都被呼叫過。
No parameter schema on file.
建立或更新你的任務卡(一件工作一張卡,每一輪更新同一張)。
No parameter schema on file.
執行實驗並記錄(命令、commit、用到的程式碼雜湊、寫出的檔案)。結論只能引用這裡記到的輸出。
No parameter schema on file.
登記一個結論。evidence 必須是 cockpit_run 寫出的檔案;JSON 檔可用 key 指定欄位(會讀出實際數值)。
No parameter schema on file.
建立或更新假設(方案空間)。改成 verified/refuted 前,必須先有證據鏈完整的結論撐著。
No parameter schema on file.
登記一個還沒驗證、卻被拿來當地基的前提。grounds 是它所依據的檔案,檔案一改風險自動升高。
No parameter schema on file.
請人裁決。blocking=true 時請停下來,告訴使用者到駕駛艙裁決,回來再呼叫 cockpit_decisions。
No parameter schema on file.
取回人類在駕駛艙的裁決與留言(含 cockpit 自動送出的)。
No parameter schema on file.
回報這一輪改了哪些檔案(沒改就給空陣列)。沒回報的變更會標紅並擋下 commit。
No parameter schema on file.
程式碼審查。不給 findings:裝了 open-code-review 就跑 ocr review,沒裝就用內建的規則審查(預設只看改到的行,all=true 看全部);給 findings:Delegation mode,由你審查後回報。審查結果會沿證據鏈標出受威脅的結論。
No parameter schema on file.
列出畫布(這個專案的研究白板)與各種卡片的數量。
No parameter schema on file.
讀一張卡片的內容(給 id),或整張白板的摘要(不給 id)。
No parameter schema on file.
在白板上搜尋卡片(標題、內文)。
No parameter schema on file.
建一般卡片(筆記、論文、網頁、文件、資料表)。結論、任務、執行等研究卡片請用 cockpit_* 工具。
No parameter schema on file.
連兩張卡片。kind:branch / reference / cites / similarity / flow / owns / uses / link。
No parameter schema on file.
用 md² 架構圖格式(meta / nodes / groups / edges)描述專案結構;paths 把圖的節點對應到真實路徑。
No parameter schema on file.
重建程式碼圖:裝了 graphify 就跑 graphify update .,沒裝就用內建的輕量版。回傳核心節點、社群、意外連結;給 file(與 funcs)就回傳改它會影響到哪些函式。
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- 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 Agent Cockpit 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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
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 Agent Cockpit 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.