# Mnemom Safe House API

**Canonical:** https://apis.io/apis/mnemom-ai/mnemom-ai-safe-house-api/  
**Provider:** Mnemom — https://apis.io/providers/mnemom-ai/  
**Base URL:** https://api.mnemom.ai/v1  
**Documentation:** https://www.mnemom.ai/docs

Mnemom Safe House API is one of 59 APIs that [Mnemom](https://apis.io/providers/mnemom-ai/) publishes on the [APIs.io](https://apis.io/) network, described by a machine-readable OpenAPI specification. Tagged areas include Safe House. The published artifact set on APIs.io includes an OpenAPI specification.

Safe House threat detection and quarantine.

## Operations (39)

| Method | Path | Summary |
|---|---|---|
| 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 |

## Machine-readable artifacts (1)

- **OpenAPI** — https://artifacts.apis.io/mnemom-ai/openapi/mnemom-ai-safe-house-api-openapi.yml

## Other Mnemom APIs (12)

- [Mnemom A2A API](https://apis.io/apis/mnemom-ai/mnemom-ai-a2a-api/)
- [Mnemom Agent Containment API](https://apis.io/apis/mnemom-ai/mnemom-ai-agent-containment-api/)
- [Mnemom Agent Groups API](https://apis.io/apis/mnemom-ai/mnemom-ai-agent-groups-api/)
- [Mnemom Agents API](https://apis.io/apis/mnemom-ai/mnemom-ai-agents-api/)
- [Mnemom Aletheia Support API](https://apis.io/apis/mnemom-ai/mnemom-ai-aletheia-support-api/)
- [Mnemom Aletheia Voice API](https://apis.io/apis/mnemom-ai/mnemom-ai-aletheiavoice-api/)
- [Mnemom Alignment API](https://apis.io/apis/mnemom-ai/mnemom-ai-alignment-api/)
- [Mnemom Analyze API](https://apis.io/apis/mnemom-ai/mnemom-ai-analyze-api/)
- [Mnemom Attestation API](https://apis.io/apis/mnemom-ai/mnemom-ai-attestation-api/)
- [Mnemom Auth API](https://apis.io/apis/mnemom-ai/mnemom-ai-auth-api/)
- [Mnemom Billing API](https://apis.io/apis/mnemom-ai/mnemom-ai-billing-api/)
- [Mnemom Blog API](https://apis.io/apis/mnemom-ai/mnemom-ai-blog-api/)

## Tags

Safe House

## Use this from code or an agent

- **REST, no key:** `GET https://apis.io/api/v1/providers/mnemom-ai` returns the provider's full profile as JSON.
- **MCP:** `https://apis.io/mcp` (Streamable HTTP) — search the catalog, read any provider, compare providers, check agent readiness.
- **Free API key** for catalog-wide search, ratings and comparisons: sign in with GitHub, Google or LinkedIn at https://apis.io/developer/account/ (plans: https://apis.io/developer/plans/).

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/apis/mnemom-ai/mnemom-ai-safe-house-api/). The API's provider profile, Kin Score and agent-readiness rating are at https://apis.io/providers/mnemom-ai/.
