Cogmemai MCP Server

CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory

Remote serverstreamable-httpPython

What is the Cogmemai MCP MCP server?

If you already use Cogmemai MCP, the cogmemai mcp mcp server is the piece that lets your assistant work with it directly. CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work.

What the server does

CogmemAi is a portable memory layer that gives any Ai system persistent recall across sessions, devices, users, and teams — and captures knowledge autonomously, even when your Ai forgets to save. 95.10% accuracy on LongMemEval — top published score on the field's hardest long-term memory benchmark. 91% on LoCoMo, above human performance (87.9%). Quantum-safe encryption. Works with Claude Code, Cursor, Windsurf, Cline, Continue, and any MCP-compatible tool. Switch editors, switch models, switch machines — your knowledge stays. Not just one score on a test — the most complete Ai memory system available.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • preflightProactive recall. Fast recall to check prior context before making any suggestion
  • save_memory — Store a fact explicitly (architecture decision, preference, etc.)
  • recall_memories — Search memories using natural language (semantic search)
  • extract_memories — Ai extracts facts from a conversation exchange automatically
  • get_project_context — Load top memories at session start (with smart ranking, health score, and session replay)
  • list_memories — Browse memories with filters (paginated, with untyped filter)
  • update_memory — Update content, importance, scope, type, category, subject, and tags
  • delete_memory — Permanently delete a memory
  • bulk_delete — Delete up to 100 memories at once
  • bulk_update — Update up to 50 memories at once (content, type, category, tags, etc.)
  • get_usage — Check your usage stats and tier info
  • export_memories — Export all memories as JSON for backup or transfer

Credentials and setup notes

Configuration is passed through the environment: COGMEMAI_API_KEY, COGMEMAI_MODE. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Cogmemai MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Cogmemai MCP's toolset — preflight, save_memory, recall_memories and 11 more — is a fair guide to whether it matches your workflow. It is maintained by hifriendbot; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Cogmemai MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
preflight**Proactive recall.** Fast recall to check prior context before making any suggestion
save_memoryStore a fact explicitly (architecture decision, preference, etc.)
recall_memoriesSearch memories using natural language (semantic search)
extract_memoriesAi extracts facts from a conversation exchange automatically
get_project_contextLoad top memories at session start (with smart ranking, health score, and session replay)
list_memoriesBrowse memories with filters (paginated, with untyped filter)
update_memoryUpdate content, importance, scope, type, category, subject, and tags
delete_memoryPermanently delete a memory
bulk_deleteDelete up to 100 memories at once
bulk_updateUpdate up to 50 memories at once (content, type, category, tags, etc.)
get_usageCheck your usage stats and tier info
export_memoriesExport all memories as JSON for backup or transfer
import_memoriesBulk import memories from a JSON array
ingest_documentFeed in a document (README, API docs) to auto-extract memories

How to install the Cogmemai MCP MCP server

{
  "mcpServers": {
    "cogmemai": {
      "command": "npx",
      "args": ["-y", "cogmemai-mcp"],
      "env": {
        "COGMEMAI_API_KEY": "your-value",
        "COGMEMAI_MODE": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
COGMEMAI_API_KEYCredential the server authenticates with.Yes
COGMEMAI_MODEConfiguration value read at startup.Optional

Example prompts to try

  • Use Cogmemai MCP to preflight.
  • Use Cogmemai MCP to save memory.
  • Use Cogmemai MCP to recall memories.

Frequently asked questions

It connects Cogmemai MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (preflight, save_memory, recall_memories, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Cogmemai MCP directly.