Connect Cortex — patented semantic memory for AI agents — to Claude or any MCP c
Connect Cortex — patented semantic memory for AI agents — to Claude or any MCP client. Free trial, 2-minute setup.
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp |
|---|---|
| Source | https://github.com/FilippoPilo/cortex-connector |
| Transport | http |
| Tools | 7 |
| Auth | none |
| First seen | 2026-08-22 20:06:49 |
| Last checked | 2026-11-17 21:48:53 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 320 / 568 ms |
| Last successful check | 2026-11-17 21:48:53 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (7)
search— Use this at the start of a conversation when the user's request about their own work, projects or plans could benefit from relevant contextfetch— Use this when a search result looks relevant and you need its full text before answering. Takes the id returned by search, and returns the mcortex_recall— Use this when the user asks about a topic as a whole ("what do you know about X", "where are we with X", "catch me up on X"): returns one nacortex_write— Use this when the user explicitly asks you to remember, note down, keep or save something, in any language: save the requested content withicortex_write_status— Use this when a previous cortex_write returned a job_id as queued and the user asks whether it was saved: returns the quality gate verdict fcortex_forget— Use this when the user asks to delete a specific memory, given the id returned by search. Ask the user to confirm before calling it: the delcortex_conflicts— Use this when the user asks what contradicts what in their memory, or when a memory you just read is flagged as conflicting and the user has
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:48:53 | ✓ | ✓ | 416 ms | 91 | active |
| 2026-11-17 21:33:46 | ✓ | ✓ | 381 ms | 91 | active |
| 2026-11-17 21:18:35 | ✓ | ✓ | 393 ms | 91 | active |
| 2026-11-17 21:03:29 | ✓ | ✓ | 184 ms | 94 | active |
| 2026-11-17 20:48:11 | ✓ | ✓ | 234 ms | 94 | active |
| 2026-11-17 20:33:05 | ✓ | ✓ | 512 ms | 91 | active |
| 2026-11-17 20:18:04 | ✓ | ✓ | 321 ms | 91 | active |
| 2026-11-17 20:02:32 | ✓ | ✓ | 232 ms | 94 | active |
| 2026-11-17 19:47:09 | ✓ | ✓ | 260 ms | 94 | active |
| 2026-11-17 19:32:05 | ✓ | ✓ | 410 ms | 91 | active |
| 2026-11-17 19:16:58 | ✓ | ✓ | 321 ms | 91 | active |
| 2026-11-17 19:01:19 | ✓ | ✓ | 438 ms | 91 | active |
| 2026-11-17 18:46:15 | ✓ | ✓ | 514 ms | 91 | active |
| 2026-11-17 18:31:12 | ✓ | ✓ | 403 ms | 91 | active |
| 2026-11-17 18:16:09 | ✓ | ✓ | 618 ms | 91 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/skynetlab-cortex-saas-mcp-cortex-320-workers-dev-mcp # JSON