Verifiable, signed, immutable receipts for autonomous agent actions
Agent Receipts MCP server exists for a simple reason — assistants are far more useful when they can act on Agent Receipts directly instead of describing what you should do. Verifiable, signed, immutable receipts for autonomous agent actions.
Persistent memory for AI agents, backed by cryptographic receipts. Every fact your agent learns is signed, traceable, and independently verifiable. No cloud required.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Agent Receipts is connected, these are the calls the assistant has available:
Timestamps — when it happened, when it completedMem0 — great memory, but no proof. It remembers things, but can't prove when or why it learned them. Memories are mutableLangfuse — great observability, but it's tracing, not proof. Logs are internal to your system, not verifiable by third partiesZep — temporal knowledge graph, but hosted and opaqueMemory — Signed entity-observation graphProof — Ed25519 signed receiptsVerification — Offline, by anyone, no serverInfrastructure — npx and done. Zero configCost — Free forever (local)Export — Portable bundles with crypto verificationtrack_action — Track an agent action with automatic hashingcreate_receipt — Create a receipt with pre-computed hashesYou will need 3 environment variables: AGENT_RECEIPTS_AGENT_ID, AGENT_RECEIPTS_ORG_ID, RECEIPT_SIGNING_PRIVATE_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Agent Receipts's toolset — Timestamps, Mem0, Langfuse and 11 more — is a fair guide to whether it matches your workflow. It is maintained by webaesbyamin; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Agent Receipts's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Timestamps | when it happened, when it completed |
| Mem0 | great memory, but no proof. It remembers things, but can't prove when or why it learned them. Memories are mutable. |
| Langfuse | great observability, but it's tracing, not proof. Logs are internal to your system, not verifiable by third parties. |
| Zep | temporal knowledge graph, but hosted and opaque. |
| Memory | Signed entity-observation graph |
| Proof | Ed25519 signed receipts |
| Verification | Offline, by anyone, no server |
| Infrastructure | npx and done. Zero config. |
| Cost | Free forever (local) |
| Export | Portable bundles with crypto verification |
| track_action | Track an agent action with automatic hashing |
| create_receipt | Create a receipt with pre-computed hashes |
| complete_receipt | Complete a pending receipt with results |
| verify_receipt | Verify the cryptographic signature |
{
"mcpServers": {
"agent-receipts": {
"command": "npx",
"args": ["-y", "@agent-receipts/mcp-server"],
"env": {
"AGENT_RECEIPTS_AGENT_ID": "your-value",
"AGENT_RECEIPTS_ORG_ID": "your-value",
"RECEIPT_SIGNING_PRIVATE_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| AGENT_RECEIPTS_AGENT_ID | Configuration value read at startup. | Optional |
| AGENT_RECEIPTS_ORG_ID | Configuration value read at startup. | Optional |
| RECEIPT_SIGNING_PRIVATE_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.