MCP.so
Sign In
M

Memory Mcp 1file

@pomazanbohdan

Repository

About Memory Mcp 1file

A high-performance, pure Rust Model Context Protocol (MCP) server that provides persistent, semantic, and graph-based memory for AI agents.

#vector-search#knowledge-graph#code-indexing

Basic information

Category

Memory & Knowledge

Transports

stdio

Publisher

pomazanbohdan

Submitted by

Богдан Помазан

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": [
        "run",
        "--init",
        "-i",
        "--rm",
        "-v",
        "mcp-data:/data",
        "-v",
        "/absolute/path/to/your/project:/project:ro",
        "ghcr.io/pomazanbohdan/memory-mcp-1file:latest"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Memory Mcp 1file?

Memory Mcp 1file is a high‑performance, pure Rust Model Context Protocol (MCP) server that provides persistent, semantic, and graph‑based memory for AI agents. It is a single, self‑contained executable with no external database, no Python dependencies, no API keys, and requires zero setup—just run a Docker container or binary.

How to use Memory Mcp 1file?

Run the Docker container or the compiled binary. No configuration keys are mentioned in the README; the server starts with built‑in vector search (FastEmbed), a knowledge graph (PetGraph), code indexing, and hybrid retrieval.

Key features of Memory Mcp 1file

  • Embeds SurrealDB for persistent storage
  • Vector search (FastEmbed) for semantic similarity
  • Knowledge graph (PetGraph) for entity relationships
  • Code indexing to understand a codebase
  • Hybrid retrieval via Reciprocal Rank Fusion
  • All models run locally on CPU, no API keys required

Use cases of Memory Mcp 1file

  • AI agents that need persistent, semantic memory across sessions
  • Searching codebases by meaning, not just keywords
  • Storing and retrieving entity relationships in a knowledge graph
  • Offline‑first memory without internet or cloud dependencies

FAQ from Memory Mcp 1file

What dependencies does Memory Mcp 1file require?

None. It is self‑contained: no Python, no external database, and no API keys. All embedding models run via an embedded ONNX runtime on CPU.

Does Memory Mcp 1file need an internet connection?

No. All models run locally on CPU, so no online API calls are made.

How is data stored?

Data is persisted using an embedded SurrealDB instance inside the single executable.

What transports or protocols does Memory Mcp 1file use?

It implements the Model Context Protocol (MCP); no other transport details are provided in the README.

Comments

More Memory & Knowledge MCP servers

Anytype MCP Server

anyproto

An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.

467

Obsidian MCP Server

StevenStavrakis

A simple MCP server for Obsidian

717

MCP Apple Notes

RafalWilinski

Talk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.

401

Jupyter Notebook MCP Server (for Cursor)

jbeno

Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files

157

Context Portal MCP (ConPort)

GreatScottyMac

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

763