FRENES

Security · MCP server

OpenWorkProof: MCP server, setup and security

OpenWorkProof is an open-source MCP server published on GitHub that lets an AI agent verify agent tool calls using signed decisions and evidence chains. Its repository has 262 stars and its last commit is from September 12, 2026 and it is licensed under Apache-2.0.

Actively maintained

What OpenWorkProof does

According to its repository: “Verifiable execution protocol for agent tool calls: signed policy decisions, causal evidence chains and offline verification from a SQLite ledger.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. OpenWorkProof is listed under Security, a category of 133 servers in the directory, where it ranks #20 by stars.

Topics declared by the repository: agent-governance, agent-protocol, ai-agents, authorization, ed25519, llm-agents.

Installing and connecting OpenWorkProof

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to OpenWorkProof. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 27, 2026, the dengyier/OpenWorkProof repository has 262 stars and 0 forks, with 2 open issues. It has more stars than 81% of the servers in the directory. Last change 1 month ago. Version published in the registry: 1.4.0 (August 30, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

World MonitorWorld Monitor : 89.4K89.4KSemgrepSemgrep : 17.2K17.2KIda pro MCPIda pro MCP : 13.1K13.1KGhidraMCP (LaurieWired)GhidraMCP (LaurieWired) : 11.5K11.5KRobin: AI Powered Dark Web ORobin: AI Powered Dark Web O : 7.7K7.7KJadx ai MCPJadx ai MCP : 2.9K2.9KPower BI Authoring MCP ServePower BI Authoring MCP Serve : 1.2K1.2KSafeDep Vet MCPSafeDep Vet MCP : 1.1K1.1KOpenWorkProofOpenWorkProof : 262262
GitHub stars of the most followed servers in the category (log scale); OpenWorkProof in orange. Checked October 25, 2026.

Verdict

OpenWorkProof is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Widely followed: 262 stars
  • Listed in the official MCP registry
  • Permissive licence (Apache-2.0)

Frequently asked questions

How do I install OpenWorkProof?

OpenWorkProof is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of dengyier/OpenWorkProof.

Is OpenWorkProof free?

The code is published under the Apache-2.0 licence and can be used free of charge.

Is OpenWorkProof safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by dengyier on GitHub. Check who maintains it before giving it access.

What are the alternatives to OpenWorkProof?

In the same category: Semgrep, World Monitor, SafeDep Vet MCP, and Ida pro MCP. Semgrep and World Monitor score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score