// teleport guide · DevOps · official

Teleport Git MCP — read-only, P2P, zero cloud

The official Git MCP server operates on a local working copy. Teleport the inspection tools and an outside agent can review your uncommitted work end-to-end — while add/commit/reset never leave your machine. This guide maps all 11 tools of @modelcontextprotocol/server-git by blast radius, then gives you the exact command to share it with a remote teammate's AI agent — capability without credentials.

6SAFE to expose

2CAUTION

3KEEP LOCAL

0servers involved

host terminal — read-only share command

npx -y mcpwire share --allow "git_status,git_log,git_diff_unstaged,git_diff_staged,git_diff,git_show" --redact-secrets --ttl 30m -- npx -y @modelcontextprotocol/server-git --repository ~/code/myapp

Only the 6 read-only tools are exposed; the other 5 are invisible to the peer (filtered from tools/list and blocked if forced). Tunnel dies in 30 minutes. Add --confirm to approve every call, or --max-calls 20 for a hard budget.

peer config — claude_desktop_config.json / .cursor/mcp.json

{
  "mcpServers": {
    "teleported-git": {
      "command": "npx",
      "args": [
        "-y",
        "mcpwire",
        "join",
        "wire://<TICKET_FROM_HOST_BANNER>"
      ]
    }
  }
}

🛡️ tool risk map — Git

tool	risk	notes
`git_status`	SAFE	Working tree status.
`git_log`	SAFE	Commit history.
`git_diff_unstaged`	SAFE	Diff of unstaged changes.
`git_diff_staged`	SAFE	Diff of staged changes.
`git_diff`	SAFE	Diff between refs.
`git_show`	SAFE	Shows a commit.
`git_add`	HIGH RISK	Stages files.
`git_commit`	HIGH RISK	Creates commits.
`git_reset`	HIGH RISK	Unstages/resets state.
`git_create_branch`	CAUTION	Branch creation.
`git_checkout`	CAUTION	Switches branches.

🔒 Why not just share your token?

Git's credential would grant the full toolset to a foreign LLM — including git_add and git_commit. With mcpwire the credential stays in your env; the peer only ever holds an expiring wire:// capability scoped to 6 tools.

🎥 Audit everything

Add --record session.wirelog and every call, block and redaction is logged locally. Drag the file into mcpwire.co/replay for a DevTools-style waterfall of what the remote agent actually did.

🔁 Works with every MCP client

Claude Desktop, Cursor, Windsurf, Cline — anything speaking MCP over stdio. Your peer pastes the snippet above; you keep the kill-switch (Ctrl+C) in your terminal.

What happens if the peer's agent tries to call a blocked Git tool?

The request never reaches your MCP server. mcpwire answers with a JSON-RPC error (-32601 [MCPWire Firewall]) and logs the attempt — the tool doesn't exist from the agent's point of view, so well-behaved agents won't even try.

Can I expose the caution-level tools too?

Yes — just add them to --allow or run with --confirm so each call waits for your y/n in the host terminal. The risk map above tells you exactly what you'd be signing up for.

Is the traffic really serverless?

Yes. Discovery goes through the public Hyperswarm DHT; the data path is a direct Noise-encrypted socket between the two machines (UDP hole punching). If both NATs are stubborn, Hyperswarm routes through community relays — which only see ciphertext.

← all teleport guides ⚡ open the policy builder

🔒 MCPWire Enterprise & Team Mesh (Early Access)

Need persistent wire://your-company/db namespaces, SSO / GitHub identity verification before the P2P handshake, and centralized audit logs for compliance (SOC2 / ISO)?