BATON
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BATONRelay this conversation to team room"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🏃 BATON
Hand off AI work — with a receipt.
An AI did the work. How does the next person — or the next AI — know it actually works, not just that the build passed? BATON seals a unit of AI work into a portable capsule, and an independent verifier replays it and issues a server-signed Verification Receipt. The receiver trusts observed evidence, not a claim.
Never trust an agent handoff without a receipt.
BATON is a standard MCP (Model Context Protocol) server — any MCP-capable tool (Claude Code, Codex CLI, Gemini CLI, Cursor …) connects with one URL. The producer and the verifier can be different models, machines, and people.
Why this, and not the dozen orchestration tools?
Running Claude + Codex + Gemini together (swarms, rooms, agent messaging) is a crowded space. BATON isn't that. The one thing almost nobody does: bind the handoff artifact to independent execution evidence as a single, forgeable-proof trust unit. That's the receipt.
Claude did the work
↓ baton_pass → sealed capsule (BTN-H-…)
Codex / a teammate receives it
↓ baton_verify → replay in a clean env, observe the real flow
↓
🕸️ VERIFIED — signed receipt: who verified · what was observed · in what env · with what artifacts
↓
trust (or reject)The real buyer isn't "me switching Claude→Codex" (just re-read the repo). It's outsourcer→in-house, leaver→joiner, KO team→US team — where "an AI made this, does it really work?" is a question worth paying to answer.
Related MCP server: passoff
The receipt (the differentiator)
baton_verify doesn't return a ✅ sticker. It returns a signed record:
{
"kind": "baton.verification-receipt/v1",
"capsule": "BTN-H-…", // the handoff this verifies
"verifier": "receiver-spider", // WHO verified — independent of the producer
"environment": { "os": "ubuntu-24.04", "node": "24.2" },
"observed": [{ "claim": "payment succeeds", "observed": true,
"detail": "POST /pay 200 + order row +1" }],
"artifacts": ["playwright.trace.zip", "network.har"],
"verdict": "verified",
"signature": "…hmac-sha256…" // server-signed → tamper the verdict, break the sig
}Flip verdict to "verified" without re-signing and the badge is refused. A passing build never earns verified on its own — only observed E2E does (this is what catches a silent upsert that returns 200 but writes nothing).
Tools
Group | Tools | What it does |
Handoff |
| Seal a work capsule into a code ( |
Verify |
| Independent verifier replays and issues the signed receipt (no observation, no 🕸️); |
Team rooms (supporting) |
| A persistent room the owner manages; people enter via rotating invite codes ( |
Operations |
| Cycle-safe private task DAG, Git commit/diff/test evidence binding, and idempotent provider/model/task cost ledger |
Operations dashboard: /ops.html. It stores only task metadata, Git evidence, and cost facts; BATON never asks for repository credentials.
Network dashboard: /network.html. Shared Memory encrypts bodies under the account key and searches metadata only. MCP Hub rejects credential-bearing URLs. Marketplace reputation accepts only independent, server-signed VERIFIED receipts.
모든 공개 화면은 한국어를 기본으로 제공하며 /dash.html(협업방), /board.html(검증 결과), /ops.html(작업·Git·비용), /network.html(기억·MCP·에이전트)을 상호 연결한다.
Design principles (from the security review)
Code-derived encryption. The server stores only
ciphertext + code_hash. Without the code, even the operator can't read the plaintext — the proof of "we can't lock you in."Signed receipts. Verdicts are HMAC-signed server-side (
BATON_RECEIPT_SECRET); no client can forgeverified.Prompt-injection containment. Inbound capsules/messages are returned fenced as untrusted data; secrets are auto-masked before storage.
Codes are ≥128-bit secrets, one-time codes redeem atomically, alias-spoofing blocked.
A passing build ≠ working behavior.
verifiedrequires observed side effects, never static analysis alone.
Run
npm install
npm test # 15/15 E2E groups pass
node src/server.js # stdio (local / any CLI)
BATON_HTTP=1 PORT=8080 node src/server.js # remote Streamable HTTPRegister (remote)
claude mcp add --transport http baton https://baton-mcp-production.up.railway.app/mcpBilling/gating is off by default (dogfooding phase). Set BATON_BILLING=on to re-enable quotas. See USAGE.md for the full guide.
Storage
MVP uses SQLite (better-sqlite3) — self-host single binary. The hosted service drops a Postgres adapter into the narrow interface in src/store.js.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared memory across AI dev tools: each session hands its context to the next, not starting cold.
Verified memory for AI agents. Signed assertions, billing attestation, session continuity.
Cross-device AI memory with encrypted activity capture and context handoff between AI tools
The team layer for AI coding agents: shared contracts, collision alerts, E2EE sessions.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceEnables AI coding assistants like Claude Code, Cursor, and Codex to share chat logs, terminal history, and session context with each other. Eliminates the need to re-explain context when switching between different AI coding tools.2-
- AlicenseNot gradedqualityDmaintenanceEnables handoff of context between AI coding agents like Claude Code, Cursor, Codex, and Windsurf with built-in provenance tracking.10,385MIT
- AlicenseNot gradedqualityDmaintenanceThe simplest way to bridge and collaborate across AI Agent sessions like Claude Code, Codex, Gemini, or Cursor. It allows your agents to combine their strengths to solve your most difficult tasks without leaving their current context.2766MIT
- AlicenseNot gradedqualityBmaintenanceBridges disconnected AI sessions with persistent project memory and automatic session handoff, integrating GitHub workflows for context-aware development.11220MIT