What it does
The server checks AI outputs against real sources. For each checked output it returns a trust signal and a permanent document number, which can be used to refer back to the verification record.
A developer working with MCP-connected AI tools might reach for it when the output of a model needs to be checked against sources before it is used. The publisher's description is brief, so the exact checking method, supported source types and output format are not described in the available material.
Running it requires an MCP-compatible client that can connect to the server. The source material does not list other setup steps.
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.oathlayer/oathlayer
Verify AI outputs against real sources. Returns a trust signal and permanent doc number.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it