crewai_install_deps
AI agents invoke crewai_install_deps to trigger actions in CrewAI MCP Orchestrator. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Installing dependencies typically involves executing shell commands (e.g., pip install, npm install) that run external processes and modify the system environment. This falls under Execute as it triggers external operations. Severity is high because installing arbitrary packages could introduce malicious code or alter the runtime environment significantly.
From the tool's definition Tool name 'crewai_install_deps' — 'install_deps' implies installing dependencies (e.g., running pip install or similar package manager commands).
Attacks that exploit this kind of access
crewai_install_deps. It is categorised as a Execute tool in the CrewAI MCP Orchestrator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CrewAI MCP Orchestrator MCP server in PolicyLayer and add a rule for crewai_install_deps: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CrewAI MCP Orchestrator. Nothing to install.
crewai_install_deps is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the crewai_install_deps rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for crewai_install_deps. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
crewai_install_deps is provided by the CrewAI MCP Orchestrator MCP server (ssolis-ti/crewai-mcp-hq). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →