GooseTeamSAFE
Look, a flock of geese! An MCP server and protocol for Goose agent collaboration.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Enabling Goose Agents to Collaborate
Protocol:
An operational procedure for agents to follow, expressed in two flavors:
- Natural Language: Streamlined, human-readable instructions about how to behave and use the tools.
- Mermaid Markdown: A concise flowchart for expected behavior, described in an efficient text format.
Extension:
Goose extension (MCP Server) that provides tools for the agents to use for tasks and messaging.
- Agent Registration: Facilitates agent registration with unique ID assignments and message sending.
- Message Management: Stores messages from agents, making them available for retrieval.
- Task Management: Project Coordinator role creates and assigns tasks and roles to other agents.
- Agent Waiting: Allows connected agents to wait for a specified period before taking another action.
- Remote Server: With an MCP Proxy, multiple agents can connect to the same MCP server, necessary for collaboration.
Work in Progress
- Current focus is on Goose CLI integration, so you must have it installed.
- Other agent platforms could integrate with this project easily.
- The protocol and the MCP server are not tightly coupled to goose, only the npm
agent:scripts and in the protocol preamble.
NEW: Behavioral Control with Mermaid markdown!
- Agent protocol expressed as a [mermaid chart](https://mermaid.live/edit#pako:eNp1VG1v2jAQisnf-kX2hVKAkRTJwSbhjRa1FJVW0CVl5gQQWxmO3Rdynf2YkTyrp8iM5399w992IXJBIxIwFJJN2tYT5ecMDvXlOpQtfwvn5NdyxJFWaydAJQBPG9cef8sO1FpAwDZPxsgTXLgY4ZihlKWezUVjLFhblUmIImI0QVyKPnC14omajYaTTPSsmCvSaSQaUWzS1agROpTYxtdAX2_EK8zpht3ukbQRQOwNa4UQG-Ce8TiAswnQDLh4NtHRdLZ8N9p3pl7hmxA7x9SFtjSNIfzMTclbFOtyjN46jNYs2kyZUtg0FdoTSBa5BmaVpcr9xtv
7635ff21d77bOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add goose-team -- npx -y [email protected]
{
"mcpServers": {
"goose-team": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (12)
9 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_message | write | Add a new message |
add_task | write | Add a new task |
agent_leave | read | Allow an agent to leave the team |
agent_wait | read | Wait for a specified number of seconds |
assign_task | read | Assign a task to an agent |
clear_messages | destructive | Clear all messages |
complete_task | read | Complete a task |
list_agents | read | List all registered agents |
list_messages | read | Retrieve all messages |
list_tasks | read | List all tasks |
recent_messages | read | Retrieve recent messages |
register_agent | read | Register a new agent |
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (11)
clear_messages
import AgentStore from "../../stores/AgentStore.ts";
import MessageStore from "../../stores/MessageStore.ts";
import TaskStore from "../../stores/TaskStore.ts";
import AgentStore from "../../stores/AgentStore.ts";
import { Task } from "../../common/types.ts";const decoded = JSON.parse(atob(base64));
@modelcontextprotocol/inspector, @modelcontextprotocol/sdk, @types/express, mcp-proxy, node-fetch, @types/cors, @types/jest, @types/node-fetch
dist/sse.js
dist/streamableHttp.js
Gates applied: no_behavioural_pass, no_license.
7635ff21d77bfull audit observations/trust-audit/mcp-server/cliffhall__gooseteam.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 7635ff21d77b | SAFE | B | 88 | first audit |
Questions
What is the GooseTeam MCP server?
Look, a flock of geese! An MCP server and protocol for Goose agent collaboration.
What tools does GooseTeam expose?
12 in total: 9 read-only, 2 that write, and 1 that can delete or overwrite (clear_messages). Every one is listed on this page with its risk.
Is GooseTeam safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does GooseTeam need?
No credential environment variables were found in its source, so it appears to need none.
How does GooseTeam run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as goose-team at 0.3.0.
How current is this page?
The grade is for one exact copy of the source (7635ff21d77b), read on 2026-10-07. The repository is watched and re-audited when it changes.