BotConnector
Sign in Workspace Open App

MCP permissions

Beta

Principle

Capability ≠ permission. A model can request a tool call; your allowlist decides whether it may execute.

Permission layers

  1. Server-level allowlist — which tools of a server exist at all.
  2. Permission mode — the application can require an explicit decision for sensitive calls.
  3. Lifecycle isolation — timeouts and process exits are contained; tool results carry server/tool provenance.

Defaults

Action typeDefault
Read / searchAllowed when tool is allowlisted
Write / deleteExplicit per-tool opt-in; use an approval mode where available
Shell / process executionNot exposed by default — avoid unless strictly necessary
Network calls from toolsExplicit opt-in per server

Never do this

  • Do not register * wildcards for filesystem or shell servers.
  • Do not disable logging "temporarily".
  • Do not let a model's own output add servers to the registry.

Auditing

Review the server and tool state in the application's MCP surface and local diagnostics. A botconnector mcp log command is not part of this release, so do not rely on it.