KitScout

Categories › AI & Agents › Agent memory & context

Synap Memory

MCP serverVerified domain · maximem.aiRemote● LiveAPI key needed

Persistent memory for AI agents — log and recall conversation context over MCP.

Install

Remote server: your requests and data go to synap-mcp.maximem.ai. Claude Code: claude mcp add --transport http synap-memory https://synap-mcp.maximem.ai/mcp · Claude app: Settings → Connectors → Add custom connector.

What it can do

The tools this server listed when we connected to it, in its own words.

  • log_exchange — After each user message, send the exchange here so it can be remembered. You do not need to decide what is important, just forward the user
  • check_memory_status — Check whether a logged exchange has finished processing. Pass the ingestion_id returned by log_exchange. Returns the processing status and h
  • recall_context — Before replying, call this to recall anything already known about this user from past conversations. Use the user's latest message as the qu
  • list_recent_memories — List recent things remembered about this user. Useful for debugging or to confirm that memory is working. Pass user_id to scope to one perso

KitScout test notes

Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.

Similar tools

  • context-engineering 117,221 ★
    Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switc
  • claude-mem-install 116,897 ★
    Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cme
  • claude-mem-install 116,897 ★
    Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-
  • handoff 116,897 ★
    Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a
  • host-observer 116,897 ★
    Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation