Smriti MCP Server

<strong>Graph-Based AI Memory System with EcphoryRAG Retrieval and Leiden Clustering</strong>

Local serverstdioGo

What is the Smriti MCP MCP server?

If you already use Smriti MCP, the smriti mcp mcp server is the piece that lets your assistant work with it directly. Graph-Based AI Memory System with EcphoryRAG Retrieval and Leiden Clustering.

What the server does

  • Graph-Based Memory — — Engrams (memories) linked via Cues and Associations in a property graph
  • EcphoryRAG Retrieval — — Multi-hop associative recall with cue extraction, vector similarity, and composite scoring
  • Leiden Community Detection — — Automatic clustering of related memories using the Leiden algorithm with smart-cached resolution tuning, enabling cluster-aware scoring for efficient retrieval at scale
  • Multi-Backend Support — — LadybugDB (embedded, zero-config), Neo4j (enterprise graph DB), or FalkorDB (Redis-based graph DB)
  • Multi-User Isolation — — Per-file (LadybugDB), per-tenant property or per-database (Neo4j), or per-tenant property or per-graph (FalkorDB)
  • Automatic Consolidation — — Exponential decay, pruning of weak memories, strengthening of frequently accessed ones, and periodic Leiden re-clustering

Available tools

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

  • Core — The Core tool exposed by this server
  • Embedding — The Embedding tool exposed by this server
  • Backup — The Backup tool exposed by this server
  • Consolidation — The Consolidation tool exposed by this server
  • smriti_store — The smriti_store tool exposed by this server
  • smriti_recall — The smriti_recall tool exposed by this server
  • smriti_manage — The smriti_manage tool exposed by this server
  • Neo4j — The Neo4j tool exposed by this server
  • FalkorDB — Schema migrations (e.g., adding cluster_id to existing databases) run automatically on startup

Credentials and setup notes

Configuration is passed through the environment: LLM_API_KEY, EMBEDDING_API_KEY, ACCESSING_USER, DYLD_LIBRARY_PATH, LD_LIBRARY_PATH, LLM_BASE_URL, EMBEDDING_BASE_URL, GIT_BASE_URL. 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.

  • Go 1.25+ — For building from source - Git 2.x+ — Required for GitHub backup provider (must be in PATH) - GCC/Build Tools — Required for CGO (LadybugDB backend) - macOS: xcode-select --install - Linux: sudo apt install build-essential - Windows: Use Docker (recommended) or MinGW - liblbug (LadybugDB shared library) — Runtime dependency for LadybugDB backend, downloaded

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Where it fits

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Smriti MCP's toolset — Core, Embedding, Backup and 6 more — is a fair guide to whether it matches your workflow. It is maintained by tejzpr; worth a glance at recent repository activity before you build anything load-bearing on it.

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

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Smriti 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.

Available tools

ToolWhat it does
CoreThe Core tool exposed by this server.
EmbeddingThe Embedding tool exposed by this server.
BackupThe Backup tool exposed by this server.
ConsolidationThe Consolidation tool exposed by this server.
smriti_storeThe smriti_store tool exposed by this server.
smriti_recallThe smriti_recall tool exposed by this server.
smriti_manageThe smriti_manage tool exposed by this server.
Neo4jThe Neo4j tool exposed by this server.
FalkorDBSchema migrations (e.g., adding cluster_id to existing databases) run automatically on startup.

How to install the Smriti MCP MCP server

**Multi-user mode:**

```json
{
  "mcpServers": {
    "smriti": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "/Users/yourname/.smriti:/home/smriti/.smriti",
        "-e", "LLM_API_KEY=your-api-key",
        "-e", "EMBEDDING_API_KEY=your-embedding-key",
        "-e", "ACCESSING_USER=yourname",
        "tejzpr/smriti-mcp"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Go 1.25+ — For building from source - Git 2.x+ — Required for GitHub backup provider (must be in PATH) - GCC/Build Tools — Required for CGO (LadybugDB backend) - macOS: xcode-select --install - Linux: sudo apt install build-essential - Windows: Use Docker (recommended) or MinGW - liblbug (LadybugDB shared library) — Runtime dependency for LadybugDB backend, downloaded
VariableDescriptionRequired
LLM_API_KEYCredential the server authenticates with.Yes
EMBEDDING_API_KEYCredential the server authenticates with.Yes
ACCESSING_USERConfiguration value read at startup.Optional
DYLD_LIBRARY_PATHFilesystem location the server is allowed to use.Optional
LD_LIBRARY_PATHFilesystem location the server is allowed to use.Optional
LLM_BASE_URLEndpoint or connection string the server talks to.Yes
EMBEDDING_BASE_URLEndpoint or connection string the server talks to.Yes
GIT_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Smriti MCP to Core.
  • Use Smriti MCP to Embedding.
  • Use Smriti MCP to Backup.

Frequently asked questions

It connects Smriti MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (Core, Embedding, Backup, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Smriti MCP directly.