Open, reviewed skills + MCP for AI coding agents — verified, quality-gated memor
Open, reviewed skills + MCP for AI coding agents — verified, quality-gated memory that gets better instead of drifting.
active Production-safe Score 91/100 http no auth
At a glance
| Endpoint | https://remembrance.dev/api/mcp |
|---|---|
| Source | https://github.com/DreamArkInc/remembrance-skills |
| Transport | http |
| Tools | 11 |
| Auth | none |
| First seen | 2026-07-31 21:15:06 |
| Last checked | 2026-11-17 21:44:55 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 655 / 1551 ms |
| Last successful check | 2026-11-17 21:44:55 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (11)
query_skills— Searches the public Remembrance registry for skills and resources that match a task. Takes a task domain, a summary of the task and optionallist_skills— Lists skills in the public registry with their slug, name, summary, version and tags, without their full text. q filters by slug prefix, sluget_skill— Returns the full text and metadata of the current reviewed version of a public skill, by slug. query_id and result_id are optional and linkinvoke_skill— Returns the full text and metadata of a public skill by its exact slug: the current reviewed version, or the version named by version_id. Eaget_resource— Returns the details of a public resource listed in the registry, such as an API, MCP server, docs site, package or tool, by slug. query_id aget_value_proof— Fetches the signed token-savings proof behind a potential_savings estimate in search results and verifies its signature. A verified proof harun_connection_doctor— Checks this connection without changing anything: whether the server responds, which registry scope applies, and, with active_read_probe, whget_connection_status— Returns the transport, credential source and registry scope of this connection. It never returns credentials.submit_query_feedback— Rates how well the results of one search matched its task: an overall fit (good, partial or none) and a fit for each rated result_id (good,submit_feedback— Records whether a skill was useful after it was used, with an optional rating from 1 to 5. query_id and result_id are optional and link thereport_task_outcome— Records whether the task behind a search was completed or abandoned, whether it succeeded, and which result_ids from that search were used,
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:44:55 | ✓ | ✓ | 239 ms | 94 | active |
| 2026-11-17 21:29:51 | ✓ | ✓ | 478 ms | 91 | active |
| 2026-11-17 21:14:38 | ✓ | ✓ | 527 ms | 91 | active |
| 2026-11-17 20:59:19 | ✓ | ✓ | 260 ms | 94 | active |
| 2026-11-17 20:44:18 | ✓ | ✓ | 250 ms | 94 | active |
| 2026-11-17 20:29:17 | ✓ | ✓ | 372 ms | 91 | active |
| 2026-11-17 20:14:13 | ✓ | ✓ | 251 ms | 94 | active |
| 2026-11-17 19:57:36 | ✓ | ✓ | 373 ms | 90 | active |
| 2026-11-17 19:42:35 | ✓ | ✓ | 258 ms | 94 | active |
| 2026-11-17 19:27:34 | ✓ | ✓ | 294 ms | 94 | active |
| 2026-11-17 19:12:33 | ✓ | ✓ | 275 ms | 94 | active |
| 2026-11-17 18:55:42 | ✓ | ✓ | 401 ms | 90 | active |
| 2026-11-17 18:40:35 | ✓ | ✓ | 449 ms | 90 | active |
| 2026-11-17 18:25:29 | ✓ | ✓ | 282 ms | 94 | active |
| 2026-11-17 18:10:14 | ✓ | ✓ | 288 ms | 94 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://remembrance.dev/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/remembrance-dev-api-mcp # JSON