REST API overview

Every Mneva tool is reachable over HTTPS. The MCP wrapper (mneva-connect) is one client; your own code is another. Use whichever fits.

Base URL

https://mneva.dev/v1

All endpoints are under /v1/. Requests are JSON in, JSON out. UTF-8. Content type application/json on POSTs.

Authentication

One header on every request:

x-mneva-key: mnv_...your_key...

For multi-agent brains, also:

x-mneva-agent: alice

…to attribute observations and (in the future) call-level scoping. See Authentication for key handling and rotation.

Surface map

The 16 MCP tools map to these endpoints. The REST shape is closer to "what the engine does" than to "what the agent says"; some plurals are nouny.

Method + pathToolWhat it does
POST /v1/rememberrememberrecord a memory
POST /v1/recallrecallsemantic search memories
GET /v1/dreamsrecall_dreamsunread overnight thoughts
POST /v1/believebelieveassert a belief
POST /v1/reviserevisesupersede a belief
POST /v1/evidenceevidencerecord SPRT evidence
GET /v1/evidence/:idevidence_forbelief audit trail
POST /v1/flagflagrecord a danger memory
POST /v1/assessassessgut-check + track record
POST /v1/predictpredictrecord a prediction
POST /v1/resolveresolveclose a prediction
GET /v1/predictions/openpredictions_openunresolved predictions
GET /v1/calibrationcalibrationper-domain track record
GET /v1/beliefscurrent beliefs
GET /v1/statestateallostatic verdict
POST /v1/note_aboutnote_aboutmulti-agent observation
GET /v1/outside_viewsoutside_viewsrecall observations

Detail by group:

Errors are documented at Errors. All non-2xx return a JSON object with an error string field.

Was this page helpful?