
Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
Public tool metadata for what this MCP can expose to an agent.
owp_soc_sample_alertsGet the OpenWorkProof sample, whose alerts_jsonl is passed to owp_soc_analyze_slips.Get the OpenWorkProof sample, whose alerts_jsonl is passed to owp_soc_analyze_slips.
No parameter schema in public metadata yet.
owp_soc_analyze_slipsAnalyzes the sample alerts_jsonl and returns a bundle that is passed to owp_soc_verify_bundle.Analyzes the sample alerts_jsonl and returns a bundle that is passed to owp_soc_verify_bundle.
No parameter schema in public metadata yet.
owp_soc_verify_bundleVerifies the bundle returned by owp_soc_analyze_slips; UNKNOWN is expected without independent trust information.Verifies the bundle returned by owp_soc_analyze_slips; UNKNOWN is expected without independent trust information.
No parameter schema in public metadata yet.
Sponsors
English · 简体中文
Check what an AI agent was allowed to do, what it recorded, and whether its evidence holds up.
OpenWorkProof (OWP) is an open-source toolkit for developers and teams using AI agents. Use it to review signed work records, check exported evidence, or run a bounded Codex preview-editing task. Security engineers can also try a reference workflow for reviewing Slips alerts.
You keep the final decision to accept or reject the result. Connecting OWP to an agent gives it tools; protection of a Codex task requires a separate Guard setup.
Get started · Codex Guard · Docs · Community
Current release: 1.6.1 · PyPI · Release notes · MCP Registry
openworkproof