What it does
The twothumbs MCP server is described by its publisher as a way to verify AI agent work end to end. According to the publisher's description, it checks real artifacts and outcomes instead of relying on the agent's own report that a task succeeded.
It would be reached for when an AI agent's output needs independent checking before it is accepted, for example in development workflows where the result of an agent's actions must be confirmed. The publisher's description does not list further supported tools or workflows.
The source provides a repository link but does not describe setup steps, runtime requirements or configuration details. Anyone wanting to run it should consult the publisher's repository.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.asselwan/twothumbs
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it