MCP servers
Pane inherits Claude Code's MCP server configuration. Run Context7, Linear, and any MCP server with zero extra setup.
MCP (Model Context Protocol) lets your agent talk to external tools like GitHub, Linear, Jira, and Slack. Pane doesn’t do anything special here. When you run Claude Code in a Pane terminal, it picks up MCP servers from .mcp.json (project-level) or ~/.claude.json (user-level), the same as it would in any terminal.
How it works
A Pane is a real terminal. Claude Code running inside it reads .mcp.json exactly like it would in a standalone terminal. The same goes for any other agent that supports MCP. Pane’s job is to give each agent an isolated shell. The agent handles MCP on its own.
Example: Context7 docs lookup
Drop an .mcp.json at the root of your worktree:
{
"mcpServers": {
"context7": {
"command": "npx",
"args": ["-y", "@upstash/context7-mcp@latest"]
}
}
}Claude Code will connect automatically the next time you start it.
Source: github.com/upstash/context7
Example: Linear ticket to PR
{
"mcpServers": {
"linear": {
"command": "npx",
"args": ["-y", "linear-mcp-server"],
"env": {
"LINEAR_API_KEY": "${LINEAR_API_KEY}"
}
}
}
}Workflow inside a Pane terminal:
- Agent reads the Linear issue via MCP.
- Agent writes code in the worktree.
- Agent commits and opens a PR with
gh pr create. - You review in the adjacent panel without switching windows.
Source: linear.app
Different MCPs per pane
Each pane runs in its own worktree directory. That means each worktree can have its own .mcp.json. One pane can connect to Context7 while another connects to an internal MCP server. No conflicts, no shared state.
my-repo/ ← main worktree (.mcp.json → context7)
../api-pane/ ← worktree for API work (.mcp.json → internal-mcp)
../web-pane/ ← worktree for UI work (no .mcp.json)Where to put credentials
| Config file | Scope | Use for |
|---|---|---|
~/.claude.json | All sessions | Personal API keys, MCPs you use everywhere |
.mcp.json in worktree | This project | Repo-specific MCPs, team-shared config |
~/.claude.json is shared across all Pane sessions for the same OS user. .mcp.json in the worktree is for project-specific servers. Commit .mcp.json to your repo if the whole team uses those servers. Put secret env vars in .env and add it to .gitignore.
Related
- AI providers — set provider API keys per pane
- Security & permissions — what Pane does and does not send off-device