mcpboundary / setup / crewai
Setup guide
Set up MCPBoundary in CrewAI
communitystdiounknownno verified config · noindex
A local proxy that wraps your MCP servers and checks every tool call against your policy and current state before it runs — allow, block, or hold for review, with a structured reason the agent can act on. Restrict specific arguments, limit response sizes, throttle runaway loops, and bind writes to observed state; every call, decision, and outcome is inspectable in a local dashboard.
01Configuration
# MCPBoundary via CrewAI
# transport: stdio
# launch: the server's install method
CrewAI connects to MCP servers in code. Use its MCP client with the command/URL below; exact API varies by version.
02Steps
- Make sure CrewAI is installed and up to date.
- Wire the server into CrewAI using its MCP client API.
- Provide any required API keys/credentials as environment variables.
- Restart CrewAI and confirm MCPBoundary’s tools appear.
03Other runtimes
04Provenance
config_sourcegenerated from captured install method
last_checked2026-07-13 06:31Z
sourcesUser submissions [p7]
Next step
Want agents that act within guardrails? Apex is the live governed-agent product — paced, capped, and fully-logged actions with approvals before anything runs.
Explore Apex →See also: server page · is it safe? · alternatives