Agent Receipts Mcp

io.github.dhanushs1912-svgPublished by GitHub account dhanushs1912-svgv0.1.2Updated Oct 24, 2026

EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local MCP server that issues cryptographically signed, hash-chained receipts of AI agent actions and exports signed audit bundles for compliance review.

What you can do
Issue signed, timestamped receipts recording an action's type, summary, actor and principal, with payloads reduced to a SHA-256 hash and discarded rather than stored. Verify receipts presented by other agents or systems against the embedded Ed25519 signature. Export a signed audit bundle for a date range, including a tamper-evidence report flagging sequence gaps and chain breaks. Retrieve service info such as the public key to pin for offline verification.
When to use it
Useful when an assistant performs consequential actions that must be provable later — approvals, payments, record changes — and you need tamper-evident evidence for auditors, regulators or counterparties, including EU AI Act record-keeping conversations. Also useful when you must check that a receipt from another agent has not been altered.
Requirements
Runs locally over stdio via npx, requiring Node.js 22.13 or newer (uses the built-in node:sqlite). The AGENT_RECEIPTS_DATA environment variable sets the directory holding the SQLite vault and signing key, defaulting to ./data. No account or network access is needed; verification works offline.
Before you install
The vault directory holds the SQLite database and the signing key, so protect it: anyone with the key can forge receipts. Receipts are only as complete as the agent's discipline in issuing them, and gaps are reported as deletion evidence. The README states it is not legal advice and that whether a system is high-risk is a question for counsel.

Installation

In SourceWeft

  1. Open Agent Receipts Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agent-receipts

[npm] [license]

Prove what your AI agents did.

On August 2, 2026, the EU AI Act's record-keeping obligations for high-risk AI systems became enforceable: automatic event logging (Article 12), deployer log retention of at least six months (Article 26), and penalties up to €15M or 3% of global turnover. The question your auditor, regulator, or counterparty will ask is simple:

"Your AI agent approved this. Prove exactly what it did — and prove nobody edited the record."

An ordinary log file can't answer that: whoever owns the log can edit it. agent-receipts gives every consequential agent action a cryptographically signed, timestamped receipt that anyone can verify offline — and exports signed audit bundles you can hand directly to a compliance officer.

What a receipt proves

  • What happened, when — action type, summary, actor, principal, ISO 8601 timestamp
  • It hasn't been altered — Ed25519 signature over canonical JSON; change one character and verification fails
  • Nothing was deleted — receipts are hash-chained with monotonic sequence numbers per vault; every audit export automatically flags gaps (deletions) and chain breaks
  • Without exposing your data — hash-only privacy: payloads are SHA-256 fingerprinted and immediately discarded, never stored or transmitted

Built for the audit conversation

export_audit_bundle produces what compliance actually needs: all receipts in a date range, a tamper-evidence report (sequence gaps, chain breaks), the signing public key, and a manifest signature over the whole bundle. Retention is yours to control — the vault is a local SQLite file you keep as long as Article 26 (or your policy) requires.

You don't have to trust us. Receipts verify offline against a pinned public key with the bundled CLI — no account, no network call, no dependence on this service existing tomorrow. That's what makes the evidence durable.

Quick start (MCP — local, free)

jsonc
// Claude Desktop / Claude Code / any MCP client{  "mcpServers": {    "agent-receipts": {      "command": "npx",      "args": ["-y", "agent-receipts-mcp"],      "env": { "AGENT_RECEIPTS_DATA": "<where-to-keep-the-vault>" }    }  }}

Requires Node.js >= 22.13 (uses the built-in node:sqlite — zero native dependencies). Prefer one-click? Grab the .mcpb bundle from Releases and open it with Claude Desktop.

ToolWhen an agent should call it
issue_receiptImmediately after any consequential action. Returns the signed receipt.
verify_receiptBefore trusting a receipt presented by another agent or system.
export_audit_bundleWhen a human asks for the audit trail of a date range.
get_service_infoTo fetch the public key worth pinning for offline verification.

Quick start (HTTP API)

bash
npm install && npm run buildnpm run serve        # http://localhost:8787
bash
# 1. Create a vault (returns your API key — shown once)curl -X POST localhost:8787/v1/vaults -d '{"name":"acme-compliance"}'
# 2. Issue a receipt after an agent actioncurl -X POST localhost:8787/v1/receipts \  -H "Authorization: Bearer ark_..." \  -d '{"action_type":"invoice.approved","summary":"Approved INV-1042 for EUR 1,250",       "payload":{"invoice":"INV-1042","amount":1250},"actor":"agent:ap-bot@acme"}'
# 3. Anyone can verify — no authcurl -X POST localhost:8787/v1/verify -d '{"receipt":{...}}'
# 4. Export a signed audit bundle for the compliance officercurl "localhost:8787/v1/export?from=2026-01-01" -H "Authorization: Bearer ark_..."

Service manifest for machine discovery: GET /.well-known/agent-receipts.json.

Offline verification

bash
npx -y -p agent-receipts-mcp agent-receipts-verify receipt.json --pubkey <base64-spki-der># exit 0 = authentic, exit 1 = invalid/tampered

Receipt format (agent-receipts/v1)

jsonc
{  "schema": "agent-receipts/v1",  "id": "rcpt_...",  "vault_id": "vlt_...",  "sequence": 42,                      // monotonic per vault; gaps = deletion evidence  "issued_at": "2026-07-15T12:34:56.789Z",  "action": {    "type": "invoice.approved",    "summary": "Approved invoice INV-1042 for EUR 1,250",    "actor": "agent:ap-bot@acme",      // optional    "principal": "acme-gmbh",          // optional    "context": { "jurisdiction": "EU" } // optional  },  "payload_hash": "sha256:...",        // or null; contents never stored  "prev_receipt_hash": "sha256:...",   // hash chain to the previous receipt  "key_id": "key_...",  "public_key": "<base64 SPKI DER>",   // embedded for offline verification  "signature": "<base64 Ed25519 over canonical JSON of everything above>"}

Canonicalization is JCS-style: lexicographically sorted keys, no whitespace. The JSON Schema lives at docs/receipt.schema.json.

EU AI Act mapping (informational)

ObligationHow agent-receipts helps
Art. 12 — automatic event loggingissue_receipt on every consequential action; timestamps, actor, traceable chain
Art. 26 — keep logs ≥ 6 monthsLocal vault you retain on your terms; signed export_audit_bundle for handover
Traceability / integrityEd25519 signatures, hash chain, deletion detection, offline verification

Not legal advice. Whether your system is "high-risk" and what you must log is a question for your counsel. agent-receipts produces evidence infrastructure.

Status & roadmap

  • Core: issue / verify / export with hash chain + Ed25519
  • MCP stdio server + HTTP API + offline verifier CLI + MCPB bundle
  • Hosted vaults with per-receipt pricing
  • RFC 3161 / transparency-log timestamp anchoring
  • Key rotation and multi-key verification

MIT License.

Source: README.md at commit 3e40a58

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts