MCP scoping lets you expose a given MCP server only to the subagents that should see it. The main session - and other subagents - don't even know it exists.

What it does

You declare the MCP servers a subagent has access to in its frontmatter. Other agents and the main session operate without those tools loaded. This is how you keep a database-writing MCP out of the researcher role, or a secrets-access MCP limited to a single privileged agent.

When to use it

Isolating sensitive MCP servers to a narrow set of roles.
Reducing context overhead by not loading irrelevant MCP tools in every agent.
Building specialist agents that pair naturally with specific integrations.
Team setups where different roles should see different data.

Gotchas

Scoping is enforced at load time. If you change scopes mid-session, restart.
Unknown MCP server names in frontmatter fail silently. Double-check spelling.
Don't rely on scoping alone for secrets - combine with network and auth boundaries.

Official docs: https://code.claude.com/docs/en/sub-agents.md#scope-mcp-servers-to-a-subagent