[Scenario 4: Developer Productivity with Claude] You are building developer productivity tooling on the Claude Agent SDK: helping engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate, and automate repetitive tasks — using the built-in tools (Read, Write, Edit, Bash, Grep, Glob) plus MCP servers.

The team shares a GitHub MCP server that needs an auth token, and you also run a personal, experimental MCP server you don't want to impose on anyone. How should these be configured?

Question

[Scenario 4: Developer Productivity with Claude] You are building developer productivity tooling on the Claude Agent SDK: helping engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate, and automate repetitive tasks — using the built-in tools (Read, Write, Edit, Bash, Grep, Glob) plus MCP servers.

The team shares a GitHub MCP server that needs an auth token, and you also run a personal, experimental MCP server you don't want to impose on anyone. How should these be configured?

Accepted Answer

The shared server in project-scoped .mcp.json using environment variable expansion (e.g., ${GITHUB_TOKEN}) so no secret is committed; the personal server in user-scoped ~/.claude.json

Answer

Both servers in .mcp.json, with the token pasted in so teammates don't have to set variables

Answer

Both servers in ~/.claude.json, with setup instructions in the wiki

Answer

The shared server in CLAUDE.md and the personal one in .claude/commands/

Paper 3 · Question 34

Related Tool Design & MCP Integration questions