Skip to main content
Glama
Muscle Memory MCP Server

Muscle Memory MCP Server

by johannesloor

A tied shoelace bow next to the words Muscle Memory MCP Server

Muscle Memory MCP Server

PyPI Tests License: MIT

Your agent solves problems by writing scripts, then throws them away like they're nothing. Tomorrow it writes the same script again. Like having to figure out how to tie your shoelaces every morning. It lacks muscle memory.

The Muscle Memory MCP server gives your agent an empty library that it fills with its own tested scripts.

Install

Install in VS Code Install in VS Code Insiders Install in Cursor Install in LM Studio

Hermes

hermes mcp add muscle-memory --command uvx --args muscle-memory-mcp

Claude Code

claude mcp add muscle-memory -s user -- uvx muscle-memory-mcp

To keep the library somewhere other than the default, set MUSCLE_MEMORY_DIR in the server's environment.

Codex

Add to ~/.codex/config.toml:

[mcp_servers.muscle-memory]
command = "uvx"
args = ["muscle-memory-mcp"]
# env = { MUSCLE_MEMORY_DIR = "/absolute/path/to/library" }

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "muscle-memory": {
      "command": "uvx",
      "args": ["muscle-memory-mcp"]
    }
  }
}

Related MCP server: engram

Add to your AGENTS.md

Add this standing rule to your AGENTS.md, CLAUDE.md, SOUL.md or equivalent agent instructions:

Before writing helper code, check muscle-memory with mm_list and run a match with mm_run.
Before ending your turn, save reusable new helper scripts (not project code) with mm_save; use a background agent if available so the reply isn't delayed.
If you saved something, name it in the reply.

Tool descriptions contain the safety and testing specifics for each operation.

First run and storage

The server exposes mm_list, mm_run, mm_save and mm_setup. If the personal library has not been set up, the tools guide the agent to ask you once where it should live and then call mm_setup.

The personal library defaults to ~/.muscle-memory (%USERPROFILE%\.muscle-memory on Windows); MUSCLE_MEMORY_DIR selects another location. Scripts in the personal library are available across projects.

An optional .muscle-memory/ project library holds scripts specific to one codebase. Project-root detection depends on the MCP client's working directory. Set MUSCLE_MEMORY_PROJECT_DIR to the project's absolute path in the server environment to override detection explicitly. When a script name exists in both libraries, the project copy takes precedence; listings mark the personal copy as shadowed.

For personal libraries, saves write files locally if the folder is not in git. If the library is a git repo, each saved script is committed. Setup asks whether to also push scripts to the git remote automatically; run setup again to change your answer. Project libraries are never committed or pushed automatically: you commit them with your own work. On first project setup, the agent asks whether the library should be shared through git or kept private.

Tools

  • mm_list(area?) — list available areas and script counts, or list scripts in one area.

  • mm_run(script, args) — run a saved script, passing through arguments.

  • mm_save(name, code, test, area, usage, ...) — save or update a script after its test passes. Supports runner, test selection, and personal/project scope options; see the tool description for the full schema and safety behavior.

  • mm_setup(target, ...) — set up a personal library or optional project library. Ask the user before setup; see the tool description for modes and options.

Advanced: languages and tests

The runner is picked by file extension: Python, bash/zsh, Node, Ruby, Perl, PHP, Swift, Go, Lua, R, PowerShell, and .cmd/.bat on Windows. Other languages need an explicit runner argv when saved. Runtimes are never installed for you; a missing one gives an error naming the command.

By default a script's test uses the same extension and runner. test_name and test_runner allow independent test selection. Tests live under tests/test_<stem>.<ext>; selection metadata is stored beside the script. Tests receive MM_SCRIPT (absolute script path) and MM_LIBRARY (library root). Exit status 0 passes; failed tests prevent saving. Replacing a test extension removes the prior test only after the replacement passes.

Advanced: CLI

The same command is also a CLI:

uvx muscle-memory-mcp list [AREA]
uvx muscle-memory-mcp run SCRIPT [ARGS...]
uvx muscle-memory-mcp save NAME --code FILE --test FILE --area AREA --usage TEXT
uvx muscle-memory-mcp setup [--target personal|project] [OPTIONS]
uvx muscle-memory-mcp test [NAME]
uvx muscle-memory-mcp trust --project

With no arguments it starts the MCP server over stdio. --help lists the options.

Security and limits

  • Scripts and tests run as you, with your environment and no sandbox. Passing tests is not a security review.

  • A project library runs only after you approve the project once with uvx muscle-memory-mcp trust --project.

  • Project-library detection depends on the client's working directory; set MUSCLE_MEMORY_PROJECT_DIR if needed.

License

MIT — see LICENSE.

Available Tools

4 tools
mm_listA

List tested scripts; call before code at each reusable substep. Omit area to list areas, then select one. Same-name project scripts shadow personal. No matching script: write code. If unavailable, ask once before mm_setup.

Inputs: area.

mm_runB

Run code as you with inherited environment; no sandbox. Report output. [write]: --dry-run then readback. [irreversible]: --dry-run, show output, wait for explicit yes before execution. Repair via mm_save replace: true.

Inputs: script (required), args.

mm_saveA

Save reusable code and EXECUTE its test, unsandboxed; tests are not security reviews. Untrusted project library: nothing written or run; ask the user. Use args, env secrets, --dry-run for actions. Tests default to script runner/extension; test_name/test_runner override. MM_SCRIPT/MM_LIBRARY set; exit 0 passes. Failed new personal test saves nothing; replacement restores prior files. Personal commits, and pushes if chosen at setup; project never commits. Existing names: replace: true.

Inputs: area (required), code (required), name (required), test (required), +7 more.

mm_setupC

After asking which: personal (mode local/existing/clone) or project (shared true uses project git, false keeps private). push: user's answer to 'Push scripts to git remote automatically?'

Inputs: git, mode, path, push, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: mm_list discovers scripts, mm_run executes existing code, mm_save stores reusable code and runs its test, and mm_setup configures personal vs project storage. Although mm_run and mm_save both involve execution, the action boundaries are clearly described and unlikely to be confused.

    Naming Consistency5/5

    All tool names follow the same predictable mm_verb pattern: mm_list, mm_run, mm_save, and mm_setup. There are no naming style deviations.

    Tool Count5/5

    Four tools is well-scoped for a focused script-memory server. Each tool maps to a core operation: discover, execute, save, and configure.

    Completeness4/5

    The surface covers the main lifecycle of listing, running, saving/replacing, and configuring script storage. A delete/remove operation and possibly a direct get/inspect operation are missing, but most workflows remain workable through list, run, and save with replace.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to programmatically create, manage, and execute independent Python workflow scripts with full CRUD operations, allowing AI to build and modify automation workflows themselves rather than just executing pre-built ones.
      6
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables coding agents to store, recall, and manage persistent memory across sessions through MCP tools, with reviewable handoffs and SQLite-backed local storage.
      1
      MIT
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to save, retrieve, semantically search, and document code snippets through MCP tools, including multi-agent workflows for generating style guides and wiki documentation.
      -