CrewAI EnterpriseCAUTION
MCP Server for kicking off and getting status of your crew deployments
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Overview
A Model Context Protocol (MCP) server implementation that provides deployed CrewAI workflows. This server enables kicking off your deployed crew and inspect the status giving the results of your crew.
Tools
- kickoff_crew
- getcrewstatus
Env Variables
retrieve from app.crewai.com MCP_CREWAI_ENTERPRISE_SERVER_URL MCP_CREWAI_ENTERPRISE_BEARER_TOKEN
Usage with Claude Desktop
To use this MCP server with Claude Desktop, follow these steps:
- Open Claude Desktop
- Go to Settings > Developer Settings
- Add a new MCP server with the configuration shown below
Locally, cloned repo:
Install mcp and mcp[cli] locally
{
"mcpServers": {
"crewai_enterprise_server": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"",
"/crewai_enterprise_server.py"
],
"env": {
"MCP_CREWAI_ENTERPRISE_SERVER_URL": "<>",
"MCP_CREWAI_ENTERPRISE_BEARER_TOKEN": "<>"
}
}
}
}TODO: Added on PyPI:
f8e5cdaf1367OBSERVED · 2026-10-08Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add crew-enterprise-mcp-server-app --env MCP_CREWAI_ENTERPRISE_BEARER_TOKEN=${MCP_CREWAI_ENTERPRISE_BEARER_TOKEN} -- uvx crew-enterprise-mcp-server-app{
"mcpServers": {
"crew-enterprise-mcp-server-app": {
"command": "uvx",
"args": [
"crew-enterprise-mcp-server-app"
],
"env": {
"MCP_CREWAI_ENTERPRISE_BEARER_TOKEN": "${MCP_CREWAI_ENTERPRISE_BEARER_TOKEN}"
}
}
}
}Exposed tools (2)
1 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_crew_status | read | Get the status of a crew task |
kickoff_crew | write | Start a new crew task |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- UNDECLARED (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
async with httpx.AsyncClient() as client:
async with httpx.AsyncClient() as client:
network use found in code, not declared in the description
Gates applied: no_behavioural_pass, no_license.
f8e5cdaf1367full audit observations/trust-audit/mcp-server/crewaiinc__crewai-enterprise.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 |
|---|---|---|---|---|---|
| 2026-10-08 | f8e5cdaf1367 | CAUTION | B | 89 | first audit |
Questions
What is the CrewAI Enterprise MCP server?
MCP Server for kicking off and getting status of your crew deployments
What tools does CrewAI Enterprise expose?
2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is CrewAI Enterprise safe to connect to an agent?
With care. The audit graded it B (89/100) and found 4 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does CrewAI Enterprise need?
It reads MCP_CREWAI_ENTERPRISE_BEARER_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (f8e5cdaf1367), read on 2026-10-08. The repository is watched and re-audited when it changes.