Subagent MCP Scoping - Claude Code
Route specific MCP servers only to specific subagents.
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
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Newsletter
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools, delivered free every week.
Was this helpful?
Related Guides
Related Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory...
View Tool
Codeburn
Interactive TUI dashboard that shows exactly where your Claude Code and Cursor tokens are going, in real time.
View Tool
Claude Opus 4.7
Anthropic's flagship reasoning model. Best-in-class for coding, long-context analysis, and agentic workflows. 1M token c...
View Tool
Conductor
Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at onc...
View ToolRelated Videos
Open Design: Turn Websites into Design Assets for Cursor & Claude Code
Open Design: Open-Source n8n App That Turns Any Website into a Brand Kit, Design System, HTML + Images The video introduces Open Design, an MIT-licensed full-stack template that combines AI and n8n a
Nimbalyst: The Open-Source Visual Workspace for Building with Codex and Claude Code
Nimbalyst Demo: A Visual Workspace for Codex + Claude Code with Kanban, Plans, and AI Commits Try it: https://nimbalyst.com/ Star Repo Here: https://github.com/Nimbalyst/nimbalyst This video demos N
Composio: Connect OpenClaw & Claude Code to 1,000+ Apps via CLI
Composio: Connect AI Agents to 1,000+ Apps via CLI (Gmail, Google Docs/Sheets, Hacker News Workflows) Check out Composio here: http://dashboard.composio.dev/?utm_source=Youtube&utm_channel=0426&utm_
Related Posts
Claude Outages Are a Workflow Design Problem
Claude outages and 529 overloads expose whether your AI coding workflow has checkpoints, receipts, model-switch paths, a...
Claude Opus 4.8 Is an Agent Honesty Release
Claude Opus 4.8 looks like a benchmark bump, but the developer story is better honesty, dynamic workflows, and effort co...
Anthropic Sonnet 4.5 in Claude Code
Anthropic's Claude Sonnet 4.5 isn't just another model increment. The company claims they've observed it maintaining foc...
ChatGPT Work vs Claude Cowork 2026 - Complete Comparison
OpenAI launched ChatGPT Work to compete with Claude Cowork. Here is how they compare on features, pricing, integrations,...
Vera Shows Agent Safety Needs Test Oracles, Not Vibes
A new Vera paper tests Codex, Claude Code, OpenClaw, and Hermes with executable safety cases. The useful lesson is not p...
Bun Rewrites 535K Lines of Zig to Rust in 11 Days Using Claude
The Bun runtime completed an AI-assisted rewrite from Zig to Rust, fixing memory safety issues and improving performance...
