MCP Installation Scopes - Claude Code
Local, project, user, and plugin-level MCP configurations.
MCP servers can live at different scopes - just this session, just this project, all your projects, or bundled in a plugin - and the scope determines who and what sees them.
What it does
Local scope loads a server for a single session. Project scope commits it to the repo so everyone on the team gets it. User scope lives in your home config and follows you across repos. Plugin scope bundles MCP as part of a distributable plugin. Claude Code resolves scopes in a predictable order so overrides work intuitively.
When to use it
- Project scope for team-wide integrations (CI, internal APIs).
- User scope for personal tools (your notes system, your calendar).
- Local scope for quick experiments.
- Plugin scope when shipping reusable MCP + skills bundles.
Gotchas
- Project-scoped MCP config commits to the repo. Don't put secrets in it - use env var references.
- Conflicting scopes resolve by precedence. Read the doc if unexpected tools are loading.
- Plugin-scoped MCP may conflict with project-scoped ones. Namespace your tool names.
Official docs: https://code.claude.com/docs/en/mcp.md#mcp-installation-scopes
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.
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 ToolCodeburn
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 ToolConductor
Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at onc...
View ToolRelated Videos
Self Improving Applications with Claude Code & Codex
Build a Self‑Improving Next.js App: Supabase + Vercel Eve + GitHub Issues + Agent Loops Check out Supabase: https://supabase.plug.dev/1wWOTGS The video demonstrates how to build and deploy a self-im...
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...
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...
Anthropic Cuts Fable 5 Biology Fallbacks by 85%: What the Safeguard Tuning Means for Developers
Anthropic retuned Claude Fable 5's biology classifiers on August 7, cutting biology-related fallbacks by about 85% while...
Prime Agent: A Self-Improving Coding Harness Where Everything Is Python
Prime Intellect open-sourced Prime Agent on August 5, 2026. It gives the model exactly one tool - a persistent IPython k...
Beyond the Pelican Test: Opus 5 Renders the Lord of the Rings With a 1M-Token Budget
Andrej Karpathy gave Opus 5 the first paragraph of the Lord of the Rings, a 1M-token budget (about $10), and asked for a...
