// SCAN REPORT

CrewAI MCP Orchestrator

15 tools. 13 can modify or destroy data without limits.

13 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

13 can modify or destroy data

2 read-only

15 tools total

Community server · catalogue entry verified 02/07/2026

How to control CrewAI MCP Orchestrator ↓

TOOL MAP

What CrewAI MCP Orchestrator exposes to your agents

Read (2) Write / Execute (13) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous CrewAI MCP Orchestrator tools

Execute · High crewai_flow_run Executing a CrewAI flow runs arbitrary multi-agent workflows that can perform read/write/external operations. Execute · High crewai_install_deps Installing dependencies typically involves executing shell commands (e.g., pip install, npm install) that run external processes and modify the system environment. Execute · High crewai_kickoff In CrewAI, 'kickoff' is the primary method to start a crew's execution, triggering multi-agent workflows. Execute · High crewai_replay_task Based on the tool name and server context, this tool likely re-executes or replays a previously run CrewAI task.

13 of CrewAI MCP Orchestrator's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control CrewAI MCP Orchestrator

PolicyLayer is an MCP gateway — it sits between your AI agents and CrewAI MCP Orchestrator, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "crewai_apply_template": {
    "limits": [
      {
        "counter": "crewai_apply_template_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "crewai_project_info": {
    "limits": [
      {
        "counter": "crewai_project_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register CrewAI MCP Orchestrator — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CREWAI MCP ORCHESTRATOR →

Instant setup, no code required.

FULL CATALOGUE

All 15 CrewAI MCP Orchestrator tools

EXECUTE 6 tools

Execute crewai_flow_run crewai_flow_run Execute crewai_install_deps crewai_install_deps Execute crewai_kickoff crewai_kickoff Execute crewai_replay_task crewai_replay_task Execute crewai_test_crew crewai_test_crew Execute crewai_train_crew crewai_train_crew

WRITE 7 tools

Write crewai_apply_template crewai_apply_template Write crewai_create_project crewai_create_project Write crewai_define_agent crewai_define_agent Write crewai_define_task crewai_define_task Write crewai_edit_crew_py crewai_edit_crew_py Write crewai_flow_plot Generate an HTML visualization of a Flow project. Write crewai_manage_memory crewai_manage_memory

READ 2 tools

Read crewai_project_info Read the structure and core configurations of a CrewAI project. Read crewai_query_knowledge Query the internal CrewAI documentation RAG engine.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about CrewAI MCP Orchestrator

How do I prevent bulk modifications through CrewAI MCP Orchestrator? +

The CrewAI MCP Orchestrator server has 7 write tools including crewai_apply_template, crewai_create_project, crewai_define_agent. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach CrewAI MCP Orchestrator.

How many tools does the CrewAI MCP Orchestrator MCP server expose? +

15 tools across 3 categories: Execute, Read, Write. 2 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on CrewAI MCP Orchestrator? +

Register the CrewAI MCP Orchestrator MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every CrewAI MCP Orchestrator tool call.

Deterministic rules across all 15 CrewAI MCP Orchestrator tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CREWAI MCP ORCHESTRATOR →

Instant setup, no code required.

15 CrewAI MCP Orchestrator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.