mcpField
B
baton

baton

Remote
github.com/vinsenzo83AI & Agents0Updated 15w ago
Repository

About baton

baton is an MCP server for handing off AI-produced work and checking it through independent replay. It binds each handoff to observed execution evidence in a server-signed Verification Receipt, for teams that need to assess work across people or agents.

Key features

  1. 01Seal and transfer work capsules
  2. 02Independently replay handoffs
  3. 03Issue signed Verification Receipts
  4. 04Collect handoffs by trust tier
  5. 05Manage team rooms and invites
  6. 06Bind Git and test evidence

Use cases

  1. 01Verify outsourced AI-produced changes before acceptance
  2. 02Hand work from one team member to another
  3. 03Review execution evidence across agent handoffs
  4. 04Consolidate verification results from multiple handoffs

MCP support

Any MCP-capable client can connect to baton to pass, receive, compare, and verify work capsules. It exposes handoff, verification, team-room, task, Git, and cost tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://baton-mcp-production.up.railway.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npmbaton-mcp0.2.0

Tools

45
ParameterTypeRequiredDescription
namestringNoRoom name
aliasstringNoRoom owner nickname (automatically joins if provided)
api_keystringNoRoom owner account key — grants room management (issuing invites, kick, approvals) permissions. Also automatically attached via the Authorization header
require_approvalbooleanNotrue=room owner approval required to join

Details

From the project README

🏃 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.

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

GroupToolsWhat it does
Handoffbaton_pass baton_receive baton_diff baton_revokeSeal a work capsule into a code (BTN-H-…), hand it over, diff versions. Body encrypted with a code-derived key — the server never sees plaintext
Verifybaton_verify baton_verify_plan baton_consolidate + spider_* ×6Independent verifier replays and issues the signed receipt (no observation, no 🕸️); consolidate gathers many handoffs into one result board by trust tier
Team rooms (supporting)baton_create_room baton_new_invite baton_join baton_send baton_inbox baton_who baton_leave baton_kick baton_approve baton_close_roomA persistent room the owner manages; people enter via rotating invite codes (BTN-R-…, 72h, re-issuable). Owner can kick, approve (optional gate), close. After join, activity is keyed by member_id
Operationsbaton_task_* baton_git_* baton_cost_*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 forge verified.
  • 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. verified requires 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 HTTP
Register (remote)
claude mcp add --transport http baton https://baton-mcp-production.up.railway.app/mcp

Billing/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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.