Log inSubmit server
M1nd logo

M1nd

Builds a local repository code graph for MCP agents, with trust checks, memory, structural analysis, and guarded Rust refactoring.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install M1nd

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "m1nd": {
      "command": "npx",
      "args": [
        "-y",
        "@maxkle1nz/m1nd@1.6.5"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @maxkle1nz/m1nd@1.6.5

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 11d ago.

Overview

The m1nd MCP server builds a local code graph for each repository and exposes it to coding agents through MCP. It combines repository structure, Git-derived relationships, anchored findings, trust verdicts, and agent-session presence in one local Rust binary. Tools cover orientation, impact analysis, structural questions, missing-pattern detection, hypotheses, and two-phase symbol transplantation. Reach for it when an agent needs repository context beyond text search, but retain compiler, test, and runtime checks because graph results are advisory.

Use cases

  • Orient an agent in an unfamiliar repository
  • Trace the impact of changing a function
  • Find hidden coupling from Git history
  • Check code for missing structural patterns
  • Move a Rust function with a preview and guarded commit

Key features

  • Local repository code graph
  • Trust verdicts and evidence tracking
  • Cross-session anchored memory
  • Git-derived ghost-edge detection
  • Structural hole and bug-pattern analysis
  • Two-phase Rust symbol transplantation

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

6/6 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @maxkle1nz/m1nd@1.6.5 (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars23Stargazers on the source repository.
npm downloads427Package downloads in the last 30 days.
Last commit6d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How M1nd works

What m1nd does

The m1nd MCP server gives coding agents a repository-specific structural model instead of requiring them to reconstruct relationships from repeated file searches. The graph represents where code lives, how symbols and files connect, and which findings have supporting evidence. It also retains knowledge between sessions, attaching conclusions to the code they describe and marking them when that code has changed.

Answers include a trust verdict. The system can report insufficient evidence, suggest verification, or identify a result that should not yet be trusted. Graph output remains guidance: the project explicitly requires file reads, tests, or runtime probes before a mission claim can be considered complete.

The local design keeps repository data on the developer’s machine. The project is distributed as one Rust binary and is licensed under MIT.

How it works

Agents can orient themselves with north, investigate questions with seek, and inspect relationships through tools such as impact, why, and ghost_edges. Git history supplies “ghost edges” for files that repeatedly change together without an import relationship. Other analysis tools identify structural holes, recurring bug shapes, risky change velocity, and claims tested against the live graph.

Stored findings can be reinforced when later results confirm them, helping useful paths rank higher. Session presence lets multiple agents register work on the same repository. When overlapping work is detected, the agents receive a warning during orientation; the system does not decide which agent should proceed.

Tools and capabilities

The documented MCP surface includes:

  • north for repository orientation and trust information.
  • seek for structural answers with a re-verification verdict.
  • impact, why, ghost_edges, missing, predict, and tremor for dependency, coupling, absence, change-pattern, and risk analysis.
  • xray_gate and trust_selftest for guardrail and trust checks.
  • antibody_scan for searching the repository for previously identified structural bug patterns.
  • transplant_preview and transplant_commit for guarded Rust symbol moves.

Transplant plans a move from a named symbol and destination, includes relevant documentation and attributes, classifies dependencies, updates referers, and returns a receipt. Commit rechecks planned file hashes and writes atomically. The operation reports unresolved references and state left behind rather than treating an incomplete result as success. A server-side boundary manifest can protect designated repository areas, with blocked operations failing without writing changes.

Limitations and notes

The transplantation feature is limited to Rust, top-level functions, and moves within the same crate. The destination file must already exist, and references created inside macros are not visible to it.

Warnings and trust verdicts do not replace compilation, tests, or runtime validation. A graph-only result cannot close a mission. Multi-agent presence reports collisions but leaves the decision to the developer.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about M1nd

m1nd is an MCP server that builds a local code graph for each repository and exposes tools including north, seek, impact, why, xray_gate, transplant_preview, and transplant_commit. It connects code structure, history, and stored findings so agents can inspect context and trust answers.

Install m1nd through its published npm package, @maxkle1nz/m1nd, or the m1nd-mcp crate on crates.io.

It identifies m1nd as an MCP server but does not name Cursor or provide client-specific setup instructions.

Yes, m1nd can preview and commit guarded moves for top-level Rust functions within the same crate. The destination file must already exist, macro-created references are not handled, and cross-crate moves are outside the documented v1 boundaries.

No, m1nd does not replace tests, compilation, or runtime probes. Its graph findings and trust verdicts are advisory, and a mission cannot be closed using graph evidence alone.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewM1nd AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/m1nd?style=directory)](https://allmcps.com/mcp/m1nd)
HTML Embed
<a href="https://allmcps.com/mcp/m1nd"><img src="https://allmcps.com/api/badge/m1nd?style=directory" alt="M1nd on AllMCPs" /></a>