ProofSlip benchmark report
ProofSlip has a benchmark score of 32/100 based on installability, startup reliability, MCP capability discovery, documentation quality, and safety signals.
Benchmark score
32
Docs score
0
Config score
0
Safety score
0
Benchmark status
| Install | unknown |
|---|---|
| Startup | unknown |
| Capability discovery | passed |
| Last tested | Jul 27, 2026 |
Installability
- npxconfidence: medium
npx skills add Johnny-Z13/proofslip --skill proofslip-release-proof - npxconfidence: medium
npx -y @proofslip/mcp-server - pipconfidence: medium
pip install langchain-proofslip - gitconfidence: medium
git clone https://github.com/Johnny-Z13/proofslip.git
Capabilities
tool
check_receipt_status
Lightweight status poll for a ProofSlip receipt. Returns only status, is_terminal, and next_poll_after_seconds — no payload or summary. Use this instead of verify_receipt when you only need to know if a receipt state has changed. If is_terminal is false, wait next_poll_after_seconds before checking again. No API key required.
tool
create_receipt
Create a ProofSlip receipt to record that something happened. Use 'action' for completed events, 'approval' for decisions awaiting review, 'handshake' for agent-to-agent coordination, 'resume' for continuation bookmarks, 'failure' for structured error records. Returns a receipt_id and verify_url. Receipts expire after 24 hours by default.
tool
signup
Get a free ProofSlip API key. Returns the key directly — save it immediately, it cannot be retrieved later. Only needed once. After signup, configure the key as PROOFSLIP_API_KEY environment variable to use create_receipt. Free tier: 500 receipts per month.
tool
verify_receipt
Verify a ProofSlip receipt and retrieve its full data (type, status, summary, payload, ref, expiry). Use this to check what happened before deciding what to do next. Returns the complete receipt if valid, or a not_found error if expired or missing. No API key required.
Related pages
Frequently asked questions
What does the ProofSlip benchmark score include?
It combines install status, startup status, capability discovery, documentation score, configuration score, and safety score into a 0-100 benchmark_score.
Does MCP Server Finder call ProofSlip tools during discovery?
No. Capability discovery lists tools, resources, and prompts when possible, but does not invoke tools or read sensitive resources.
Why are some checks skipped?
Checks are skipped when they cannot be run safely without credentials, local configuration, or non-destructive execution guarantees.
Last updated