Claude Bridge MCP server
io.github.rahuljava2807/claude-bridge-mcp·v2.2.0·1 starsPipes Claude Code session output into Claude Chat — no more copy-paste between tools
1 stars56 downloads/wk
Reviews
Write oneNobody has reviewed Claude Bridge yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Claude Bridge tools (8, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
get_latest_outputRead the most recent assistant message from a Claude Code session log. If session_id is omitted, the most recently updated session is used.
get_session_contextReturn the last N messages from a session for full context injection. Defaults to 10.
list_sessionsList all recent Claude Code sessions with metadata, sorted by most recently updated.
send_to_sessionwrite actionQueue a prompt for a Claude Code session via ~/.claude/bridge-inbox/<session_id>.txt (cooperative dispatch). Overwrites any pending prompt for that session so the inbox always holds only the latest instruction. Also writes a human-readable receipt to ~/.claude/bridge-inbox/latest.md. Returns a setup_instruction string that the user pastes into their Claude Code terminal once per session; after tha
setup_drive_syncAuthorize Google Drive upload for the bridge context. Opens a browser consent screen using OAuth credentials at ~/.claude/bridge-google-credentials.json, stores the refresh token at ~/.claude/bridge-google-token.json, then performs an initial upload of the current bridge context as a Google Doc named 'claude-bridge-context'. Requires GOOGLE_DRIVE_ENABLED=true in the server environment for auto-syn
start_auto_syncStart a background loop that rewrites ~/.claude/bridge-context.md and ~/Documents/claude-bridge-context.md every N seconds (default 30) with the latest session output. Call again to restart with new options. The loop runs inside this MCP server process and stops when the server exits.
watch_sessionStart watching a session file (polls every 2s). On subsequent calls for the same session, returns any new messages that appeared since the last call.
write_contextwrite actionWrite the last N messages of a Claude Code session to ~/.claude/bridge-context.md and ~/Documents/claude-bridge-context.md as formatted markdown. If session_id is omitted, uses the most recently updated session. Designed to pair with a Google Drive-synced ~/Documents so Projects Claude can read live Claude Code output via its Drive connector.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan15 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 164 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Claude Bridge compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 63% of 48,255 servers
- Tools
- 8
- the typical server has 7
- Tools that change things
- 25%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,688 servers
- Downloads a week
- 56
- more than 46% of 12,191 servers with a package
What its tools let an agent do: 4 read · 1 create · 1 change · 1 send or post · 1 run or deploy
Install Claude Bridge in Claude Code, Cursor or VS Code
Runs npx -y @rahulonramp2807/claude-bridge-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add claude-bridge-mcp -- npx -y @rahulonramp2807/claude-bridge-mcp
What the publisher says
From the Claude Bridge repository's README, as published. We do not edit it. Read it on GitHub
claude-code-bridge-mcp
MCP server that pipes Claude Code session output directly into Claude Chat — no more copy-paste between tools.
claude-code-bridge-mcp is a Model Context Protocol (MCP) server that reads Claude Code's local session logs from ~/.claude/projects// and exposes them as tools to any MCP-compatible client (Claude Desktop, Claude Chat, Cursor, etc.). Run Claude Code in your terminal and pull its latest output into Claude Chat with a single tool call.
Features
- getlatestoutput — grab the most recent assistant message from any (or the most-recent) Claude Code session.
- listsessions** — enumerate all local sessions with project path, message count, and timestamps.
- getsessioncontext — fetch the last N messages from a session for context injection.
- watchsession** — poll a session file every 2 seconds and drain new messages on demand.
- writecontext (v2)_ — snapshot the last N messages into ~/.claude/bridge-context.md and ~/Documents/claude-bridge-context.md as clean markdown.
- startautosync (v2) — keep that markdown snapshot live: rewrites both files every 30 seconds (configurable) so a synced folder stays current without manual calls.
- setupdrivesync (v2.1) — authorize direct Google Drive upload. Each sync tick then upserts a Google Doc named claude-bridge-context via the Drive API — no Drive desktop client required.
- sendtosession (v2.2) — queue a prompt for a specific Claude Code session via a cooperative inbox at ~/.claude/bridge-inbox/.txt. Closes the read-only gap: Projects Claude → inbox → Claude Code acts on it.
What's new in v2.2 — sendtosession (cooperative dispatch)
v1 read sessions. v2 wrote context out to Drive. v2.2 lets the other side push prompts back in.
sendtosession overwrites ~/.claude/bridge-inbox/.txt with the latest prompt and writes a human-readable receipt to ~/.claude/bridge-inbox/latest.md. The target Claude Code session picks it up via a one-time setup instruction that sendtosession returns in its response — paste that once into your Claude Code terminal (or add it to your project's CLAUDE.md) and every subsequent prompt arrives automatically.
Why cooperative instead of direct injection: Claude Code's JSONL is append-only from the CLI's perspective — it doesn't re-read the file mid-session. A real dispatch channel exists (POST /v1/sessions/{id} via Anthropic's relay, the same channel /remote-control uses) but is undocumented and requires reading the CLI's OAuth token from the macOS Keychain. Shipping against an undocumented internal API would break on every Claude Code release and leak credentials from every install — so v2.2 uses the filesystem inbox instead. See GitHub issue for the v3 path.
Example:
// send_to_session → response
{
"session_id": "15ef12ba-851e-4591-bbd4-c23170e15919",
"project_path": "/Users/you/Documents/my-app",
"written": true,
"inbox_path": "/Users/you/.claude/bridge-inbox/15ef12ba-....txt",
"receipt_path": "/Users/you/.claude/bridge-inbox/latest.md",
"prompt_preview": "refactor the auth middleware to use Fluid Compute",
"setup_instruction": "Before each response, check ~/.claude/bridge-inbox/15ef12ba-....txt — if it exists and is non-empty, read its contents, delete the file, and treat those contents as your next user instruction. You only need to be told this once per session.",
"remote_control_url": "https://claude.ai/code/session_..."
}dry_run: true returns the same shape without touching the filesystem.
What's new in v2 — Google Drive bridge
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Claude Bridge: common questions
- Is Claude Bridge MCP server safe?
- Mostly: it is graded B (82/100). Read the Claude Bridge safety report
- How do I install Claude Bridge?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Claude Bridge need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Claude Bridge maintained?
- The last commit was 201 days ago (2026-04-17). The latest release is v2.2.0.
- How does Claude Bridge compare with other MCP servers?
- safety score 82/100 (higher than 63% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.