Mnemom Safe House API

Safe House threat detection and quarantine.

GitHub OpenAPI

Operations 39

POST /agents/{agent_id}/reverify/protection Retro-correct past Protection screening verdicts against the current card #
GET /compliance/safe-house-report Compliance-formatted Safe House report #
GET /orgs/{org_id}/agents/safe-house-summary Fleet view of each member agent's Safe House posture #
POST /orgs/{org_id}/safe-house/enable Enable or change the Safe House posture for an org #
GET /safe-house/audit Audit log for Safe House actions #
GET /safe-house/campaigns List detected threat campaigns #
POST /safe-house/campaigns/{campaign_id}/resolve Resolve a detected campaign #
GET /safe-house/canaries List canary credentials for an agent #
POST /safe-house/canaries Create a canary credential #
GET /safe-house/canaries/{canary_id}/status Check whether a canary has been triggered #
GET /safe-house/cbd/evaluations Query outbound (egress) Safe House evaluations #
GET /safe-house/cbd/evaluations/{evaluation_id} Get a single outbound (egress) evaluation #
POST /safe-house/config/bulk-apply Bulk apply a Safe House config to up to 500 agents #
GET /safe-house/context-cards List customer-authored context cards used for trust inference #
GET /safe-house/evaluations Query inbound Safe House evaluations #
GET /safe-house/evaluations/{evaluation_id} Get a single Safe House evaluation #
GET /safe-house/feed Server-Sent Events stream of Safe House evaluations #
POST /safe-house/ingest-pattern Ingest a customer-supplied threat pattern #
GET /safe-house/metrics/risk-dist Risk-score distribution over a window #
GET /safe-house/metrics/summary Aggregate verdict counts over a window #
GET /safe-house/metrics/threats Threat-type histogram over a window #
GET /safe-house/metrics/timeseries Time-series of verdict counts #
GET /safe-house/outbound/evaluations Query outbound (egress) Safe House evaluations #
GET /safe-house/outbound/evaluations/{evaluation_id} Get a single outbound (egress) evaluation #
GET /safe-house/patterns List active threat patterns #
POST /safe-house/patterns Add a new threat pattern #
GET /safe-house/quarantine List quarantined messages #
GET /safe-house/quarantine/{quarantine_id} Get a single quarantined message #
DELETE /safe-house/quarantine/{quarantine_id} Delete a quarantine item without releasing #
POST /safe-house/quarantine/{quarantine_id}/release Release a quarantined message back to the agent #
POST /safe-house/quarantine/{quarantine_id}/report Confirm a quarantined message as a threat #
POST /safe-house/report-incident Report a security incident #
GET /safe-house/reviews List the calling agent's review-hold lifecycle #
GET /safe-house/reviews/{review_id} Get a single review-hold lifecycle row by id #
POST /safe-house/reviews/{review_id}/held-content Reveal the decrypted withheld content of a review-hold #
POST /safe-house/reviews/{review_id}/resolve Resolve a human-tier review-hold (allow/deny/escalate) #
GET /safe-house/sessions List Safe House sessions (threat clusters) #
GET /safe-house/stats Aggregate Safe House evaluation stats #
GET /safe-house/threshold-suggestions Adaptive threshold recommendations #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/mnemom-ai:mnemom-ai-safe-house-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

mnemom-ai-safe-house-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Mnemom Safe House API
  description: Trust infrastructure for AI agents. Transparent alignment verification, behavioral drift detection, and accountability primitives.
  version: 1.0.0
  contact:
    name: Mnemom
    url: https://mnemom.ai
    email: support@mnemom.ai
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://api.mnemom.ai/v1
  description: Production
security:
- BearerAuth: []
- ApiKeyAuth: []
tags:


# --- truncated at 32 KB (72 KB total) ---
# Full source: https://artifacts.apis.io/mnemom-ai/openapi/mnemom-ai-safe-house-api-openapi.yml