The supplied materials describe an Apache-2.0 licensed, version 0.2.0 MCP server using stdio transport for local cognitive memory. Its main capabilities are LLM-free semantic search and knowledge graphs, together with memory, session, todo, project, reminder, statistics, and backup management.
Strongest · Documentation 14/20 Weakest · Reliability 9/20
Static review · not runListed 2026-08-14
Read the FMRS scoring method →Runtime：Node.js · Prebuilt binary
SHODH_API_KEY
API key for backend authentication; auto-generated locally, only needed for remote servers.
SHODH_API_KEYS
Comma-separated API keys for production deployments; generated by the admin.
SHODH_API_URL
URL of the shodh-memory backend, default http://127.0.0.1:3030; not needed for local runs.
SHODH_USER_ID
Logical memory namespace, default "default"; not an authorization tenant.
SHODH_ENV
Set to production to enable production mode.
SHODH_HOST
Server bind address, default 127.0.0.1.
SHODH_PORT
Server port, default 3030.
SHODH_MEMORY_PATH
Data directory, e.g. /var/lib/shodh.
SHODH_IPC_ENABLED
Local IPC is enabled by default; set to false to disable.
SHODH_IPC_ENDPOINT
Optional platform-specific IPC socket path override.
SHODH_IPC_REQUIRED
Set to true to fail closed instead of falling back to HTTP.
SHODH_REQUEST_TIMEOUT
Request timeout in seconds, default 60.
SHODH_MAX_CONCURRENT
Max concurrent requests, default 200.
SHODH_ROCKSDB_BLOCK_CACHE_MB
Shared RocksDB block cache in MiB, default 256.
SHODH_CORS_ORIGINS
Allowed CORS origins, e.g. https://app.example.com.
SHODH_ZENOH_ENABLED
Set to true to enable Zenoh transport for robotics.
SHODH_ZENOH_MODE
Zenoh mode: peer, client, or router.
SHODH_ZENOH_LISTEN
Zenoh listen endpoints, e.g. tcp/0.0.0.0:7447.
SHODH_ZENOH_CONNECT
Zenoh connect endpoints, e.g. tcp/1.2.3.4:7447.
SHODH_ZENOH_PREFIX
Key expression prefix, default shodh.
SHODH_ZENOH_AUTO_TOPICS
JSON array configuring auto-subscribed ROS2 topics via zenoh-bridge-ros2dds.
Ensure the local Shodh-Memory backend is running at the default address, http://127.0.0.1:3030, then add the server with: claude mcp add shodh-memory -- npx -y @shodh/memory-mcp. Claude Desktop or Cursor can use the supplied MCP configuration. For a remote backend, set SHODH_API_URL and, when required, SHODH_API_KEY; SHODH_USER_ID defaults to default.
{"mcpServers":{"shodh-memory":{"command":"npx","args":["-y","@shodh/memory-mcp"]}}}
Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"shodh-memory": {
"command": "npx",
"args": [
"-y",
"@shodh/memory-mcp"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add shodh-memory -- npx -y @shodh/memory-mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
After running claude mcp add shodh-memory -- npx -y @shodh/memory-mcp, the shodh-memory tools such as remember and recall should appear in your client's tool list. Ask the assistant to remember a preference, then ask for it back — a correct answer confirms the connection.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
Shodh-Memory provides persistent cognitive memory for AI agents and robots. It performs semantic search, Hebbian learning, memory decay, knowledge-graph construction, causal tracing, and related-memory activation with local algorithms, without cloud services, external databases, or LLM calls during storage and recall. The server uses stdio MCP transport and connects to a backend that defaults to http://127.0.0.1:3030.
Connect ClickHouse to your AI assistants
Unofficial MCP server providing advanced access to the ChEMBL chemical database
Google's official database MCP toolbox — define AI-accessible database tools via config
Bytebase's official, minimalist two-tool database MCP server
Source revision 902daf8394e7 Data synced 2026-10-11 Read the FMRS scoring method