Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects
{
"mcpServers": {
"ai-proofslip-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 1 days ago.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Dynamic problem-solving through sequential thought chains
A Model Context Protocol server for searching and analyzing arXiv papers
An open-source AI agent that brings the power of Gemini directly into your terminal.
The official Python SDK for Model Context Protocol servers and clients
MCP Security Weekly
Get CVE alerts and security updates for ai.proofslip/mcp-server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Portable proof objects for agent workflows.
24-hour ephemeral receipts that let agents verify what happened before deciding what happens next. Create a receipt, check it later, let it expire. That's it.
Agents should not continue based on assumptions when they can continue based on receipts.
Live Site | API Docs | Example Receipt | MCP Server | llms.txt
Agentic workflows break in predictable ways: duplicate side effects, unclear approval states, unsafe retries, ambiguous resumability. Teams currently solve this with raw logs, brittle flags, ad hoc DB rows, and hand-rolled retry logic.
ProofSlip replaces all of that with a single primitive: a short-lived, machine-readable receipt — a portable proof object that travels with the workflow and answers the questions agents actually ask:
1. Agent completes a step → creates a receipt (POST /v1/receipts)
2. Next agent (or same agent later) → verifies the receipt before acting
3. Receipt expires after 24 hours → no cleanup burden
Every receipt includes polling guidance (is_terminal, next_poll_after_seconds) so agents know whether to stop, wait, or keep checking.
| Type | Use Case |
|------|----------|
| action | Record that something happened (always terminal) |
| approval | Track pending/approved/rejected decisions |
| handshake | Two agents confirming shared context |
| resume | Bookmark for safe workflow continuation |
| failure | Structured failure with retry guidance (always terminal) |
curl -X POST https://proofslip.ai/v1/auth/signup \
-H "Content-Type: application/json" \
-d '{"email": "you@example.com"}'
Save the returned key immediately — it cannot be retrieved later.
curl -X POST https://proofslip.ai/v1/receipts \
-H "Authorization: Bearer ak_your_key_here" \
-H "Content-Type: application/json" \
-d '{
"type": "action",
"status": "success",
"summary": "Sent welcome email to user@example.com",
"ref": {
"workflow_id": "onboarding-123",
"agent_id": "email-agent"
}
}'
Returns:
{
"receipt_id": "rct_abc123...",
"type": "action",
"status": "success",
"summary": "Sent welcome email to user@example.com",
"verify_url": "https://proofslip.ai/verify/rct_abc123...",
"created_at": "2026-03-25T12:00:00.000Z",
"expires_at": "2026-03-26T12:00:00.000Z",
"is_terminal": true,
"next_poll_after_seconds": null
}
# JSON (for agents)
curl https://proofslip.ai/v1/verify/rct_abc123?format=json
# HTML (for humans — paste the verify_url in a browser)
For approval workflows where a receipt starts as pending:
# Lightweight status check (no payload, no ref — just state)
curl https://proofslip.ai/v1/receipts/rct_abc123/status
{
"receipt_id": "rct_abc123...",
"status": "pending",
"is_terminal": false,
"next_poll_after_seconds": 30,
"expires_at": "2026-03-26T12:00:00.000Z"
}
| Method | Endpoint | Auth | Description |
|--------|----------|------|-------------|
| POST | /v1/receipts | API Key | Create a receipt |
| GET | /v1/verify/:id | None | Verify a receipt (JSON or HTML) |
| GET | /verify/:id | None | Shortcut verify (same behavior) |
| GET | /v1/receipts/:id/status | None | Lightweight polling endpoint |
| POST | /v1/auth/signup | None | Get an API key |
| GET | /health | None | Health check |
| Field | Required | Description | |-------|----------|-------------| | `type