MCP Integration Guide
The smart-memory-mcp package is an MCP server that exposes SmartMemory operations to MCP-compatible clients (Claude Desktop, Cursor, Maya, custom agents). It is a separate package from smart-memory-core and ships its own tool catalogue.
For the full tool catalogue with signatures, see api/tools.md.
Install
pip install smartmemory-mcpThe console script is smartmemory-mcp (registered in pyproject.toml):
smartmemory-mcp # stdio transport (default)
smartmemory-mcp --http # HTTP transport on 0.0.0.0:8011
smartmemory-mcp --http --port 9100 # custom HTTP portYou can also invoke the module directly: python -m smartmemory_mcp.
Backends
The server can route every tool call to one of two backends; the choice is independent of the tier model.
| Backend | When | How it's selected |
|---|---|---|
| Local | You have smartmemory (and FalkorDB / Redis) installed locally. | Default. Uses the in-process SmartMemory API. |
| Remote | You want to talk to a hosted smart-memory-service deployment. | smartmemory setup --mode remote (from the desktop app), or set SMARTMEMORY_API_KEY and ensure smartmemory_app config has mode=remote. |
whoami() reports the active backend.
Tiers
Tools are registered into three tiers at server startup. Restarting the server is required after any tier-changing event (login, env var change).
| Tier | Tools (cumulative) | Unlock |
|---|---|---|
| FREE | 13 | Default — no auth required |
| PRO | 58 (+45) | login(api_key) (or SMARTMEMORY_API_KEY env) |
| PRO+ | 89 (+31) | PRO and SMARTMEMORY_MCP_FULL_TOOLS=true |
FREE
login, whoami, switch_team, memory_ingest, memory_search, memory_recall (deprecated), get_working_context, memory_get, memory_export, memory_import, memory_migrate, memory_auto, memory_feedback.
PRO
PRO unlocks PRO-tier memory_* (CRUD: memory_add, memory_update, memory_delete, memory_clear, memory_list, memory_stats, memory_distill, memory_ingest_conversation, memory_search_advanced, memory_search_by_metadata) and the full decisions, code indexing, anchors, plans / failure recall, agent profiles, and structured ingestion suites.
PRO+
PRO+ adds reasoning, evolution, insights, dev workflow, and zettelkasten suites.
See api/tools.md for the complete per-tier list with signatures.
Authentication
Three sources are checked in order — the first non-empty value wins:
SMARTMEMORY_API_KEYenvironment variable.- The
smartmemory_appdesktop keyring (if installed). - The fallback file
~/.config/smartmemory/.api_key(written by thelogintool).
Calling the login tool stores the key into the file fallback and validates it against the API. The server only re-reads credentials at startup, so:
restart the MCP server after login()is mandatory.
switch_team(team_id) writes the new team ID into the smartmemory_app config and likewise requires a restart. Without the desktop app installed, set SMARTMEMORY_TEAM_ID instead.
Client configuration
Claude Desktop / Cursor
In the MCP client's config file (e.g. claude_desktop_config.json):
{
"mcpServers": {
"smartmemory": {
"command": "smartmemory-mcp",
"env": {
"SMARTMEMORY_API_KEY": "sm_live_...",
"SMARTMEMORY_MCP_FULL_TOOLS": "true"
}
}
}
}HTTP transport
For multi-process deployments or browser clients, run in HTTP mode:
smartmemory-mcp --http --port 8011Then point your MCP client at http://localhost:8011.
Calling a tool
Standard MCP tools/call:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "memory_search",
"arguments": { "query": "auth caching", "top_k": 5, "multi_hop": true }
}
}All tools return strings, except get_working_context which returns a structured surfacing-response dict.
Service-embedded MCP
A second MCP surface ships inside smart-memory-service at smart-memory-service/smartmemory_mcp/. It re-exposes a subset of the same tools (memory CRUD, decisions, anchors, plans, code, structured, evolution, reasoning, insights, agent, plus a graph_tools module) through the API service's auth layer. It is registered separately from the standalone smartmemory-mcp server and inherits its lifecycle from the FastAPI app — see smart-memory-service for deployment.
Troubleshooting
- PRO tools missing after
login— restart the MCP server. Tier is resolved once at startup. whoamireportsBackend: remote (smartmemory package not installed)— installsmartmemoryfor local backend, or this is expected if you intend remote-only.- Tools time out — for local backend, ensure FalkorDB (9010), Redis (9012), and (for the service backend) MongoDB (9013) are reachable.
- Permission warning on
~/.config/smartmemory/.api_key— the loader logs a warning if the file is group/other-readable.chmod 600it.
See also
- MCP Tools API — every tool with its signature.
- SmartMemory API — Python API the tools wrap.
smart-memory-mcprepo — source of truth.