Reference
MCP
Connect agents to external tools and data sources
Conductor can connect agents to external tools and data sources through the Model Context Protocol (MCP). MCP servers can expose tools, databases, APIs, and other context to agents.
Learn more about MCP in the Claude Code MCP docs and the Codex MCP docs.
Add an MCP server
Claude Code
Add an MCP server for Claude Code with the Claude Code CLI:
claude mcp add <server-name> -s user -- <command> [args...]For example, add Context7 for documentation search:
claude mcp add context7 -s user -- npx -y @upstash/context7-mcpCodex
Add an MCP server for Codex with the Codex CLI:
codex mcp add <server-name> -- <command> [args...]For example, add Context7 for documentation search:
codex mcp add context7 -- npx -y @upstash/context7-mcpCodex stores MCP configuration in ~/.codex/config.toml. The Codex CLI and IDE extension share this configuration.
You can also edit config.toml directly:
[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp"]Codex also supports streamable HTTP MCP servers:
codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcpFor more options, see the Codex configuration reference.
Project-level MCP servers
If a repository has an .mcp.json file at its project root, Conductor agents in that workspace inherit those MCP servers.
For Codex, you can scope MCP servers to a trusted project with .codex/config.toml.
If you're moving project-level MCP config from Cursor, see Work with Cursor and VS Code.
Good candidates
MCP works best for tools an agent needs repeatedly, such as documentation search, issue tracking, databases, and internal APIs.
Common examples include Context7 for documentation search and Linear for issue management.
Privacy
MCP servers can send data to external services. Review the server you install and disable custom MCP servers when your repository requires enterprise data privacy.