Memory Bank

A Model Context Protocol server for Claude Code enabling persistent memory, collaborative reasoning, and project-based knowledge management with export and revision features.

python

3

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "spideynolove-memory-bank-mcp": {
      "command": "uv",
      "args": [
        "run",
        "/path/to/memory-bank-mcp/main.py"
      ]
    }
  }
}

Memory Bank MCP is a Model Context Protocol server for Claude Code that enables persistent memory, structured thinking, team collaboration, and project-based knowledge management. It supports exporting, revision tracking, and advanced coding integration to leverage existing APIs and patterns, helping teams work more efficiently across sessions and projects.

How to use

You interact with Memory Bank MCP through practical sessions that capture insights, patterns, and code. Start a thinking session to define a problem, add memories with related notes and tags, and export your work when you’re ready. For coding tasks, open dedicated coding sessions to discover dependencies, validate approaches against existing libraries, and store proven code patterns for your team.

How to install

Prerequisites: Python 3.10 or newer; the MCP runtime tool (uv) is required to run the server locally.

Clone the project repository and navigate into it.
Install dependencies and start the environment.
Run the Memory Bank MCP server locally using the standard run command.
Test the installation to verify that the server is responding as expected.

Additional notes

The server is designed to work with both session-based memory management and coding integration workflows. You can start with basic memory sessions and progressively adopt coding sessions, validation checks, and code pattern storage to build a reusable knowledge base for your team.

Configuration and runtime example

{
  "mcpServers": {
    "memory-bank": {
      "command": "uv",
      "args": ["run", "/path/to/memory-bank-mcp/main.py"]
    }
  }
}

Available tools

create_memory_session

Start a new thinking session with optional session_type to tailor the workflow (coding_session, debugging_session, architecture_session).

store_memory

Save insights with tags and confidence, and optionally attach a code snippet for later reuse.

revise_memory

Update previously stored memories to refine understanding or correct errors.

create_collection

Group related memories into collections for better organization and retrieval.

merge_collection

Combine multiple collections into a larger, coherent set of insights.

analyze_memories

Run quality checks to identify contradictions, gaps, and overarching themes.

export_session_to_file

Export full sessions for sharing or archival purposes.

export_memories_to_file

Export filtered memories based on tags, dates, or other criteria.

load_project_context

Resume work by loading context from a prior project.

update_project_index

Document team progress and status within the project index.

discover_packages

Auto-scan installed packages and extract API signatures for reinvention prevention.

validate_package_usage

Validate code against existing libraries to promote reuse and prevent reinvention.

explore_existing_apis

Search for existing APIs that can fulfill a required capability.

prevent_reinvention_check

Provide warnings when similar implementations already exist, with references to established solutions.

store_codebase_pattern

Store reusable code patterns with metadata for team-wide access.

load_codebase_context

Load project structure and context into memory for seamless collaboration.