MCP.Market

Mindtrail MCP server

by RohitDeshmukh-1·io.github.RohitDeshmukh-1/mindtrail·v0.1.1·1 stars
No reviews yet

Persistent, local-first memory for AI coding agents. Remember, recall and forget across sessions.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed Mindtrail yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mindtrail tools (7, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • forget

    Permanently delete a memory.

  • get_context

    Relevant memories as a compact, prompt-ready block within a token budget.

  • get_memory

    Fetch one memory by id, with its edit history.

  • recall

    Find memories relevant to a query, from this project and the user's personal space.

  • remember

    Store a memory that persists across sessions and tools.

  • search_memory

    Search memories with explicit space, type and validity filters.

  • update_memorywrite action

    Correct a memory in place; the previous version is kept in its history.

Public scan report

scanner v0.1.10 · 2026-10-09 · same rubric, same numbers if you re-run it

no findings
  • Code scan35 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mindtrail compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
7
the typical server has 7
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers

What its tools let an agent do: 6 read · 1 change

Install Mindtrail in Claude Code, Cursor or VS Code

claude mcp add mindtrail -- uvx mindtrail
Add to Cursor

What the publisher says

From the Mindtrail repository's README, as published. We do not edit it. Read it on GitHub

🧭 Mindtrail

Leave a trail your AI agents can follow.

Persistent, local-first memory for coding agents over MCP. Tell your agent something once, and every future session remembers it.

Install · Day to day · How it works · Benchmarks · Docs

Every new agent session starts from zero. You explain your conventions again, re-state your preferences, and re-describe decisions you made last week. Mindtrail gives your agents a shared, long-term memory through the Model Context Protocol, so what one session learns, every later session (in any tool) can recall.

VS Code, Codex and your own agents.

  • 🔌 Works with any MCP client. One memory shared by Claude Code, Claude Desktop, Cursor,

telemetry.

  • 🏠 Local-first and private. One SQLite file on your machine. No account, no API key, no

the official MCP Registry; with uv there is nothing to install first.

  • ⚡ One command to install. Published on PyPI and

personal preferences follow you everywhere.

  • 🗂️ Scoped automatically. Repo facts stay with the repo (detected from the git remote) and

signals shown for every result.

  • 🔎 Hybrid retrieval. Keyword (BM25) and vector search, fused and ranked, with the ranking

and deletes for real.

  • 🛡️ Safe by default. Refuses to store credentials, marks recalled memory as untrusted data,

Does it actually help?

We tested it with real Claude Code sessions. In one session the user mentions a project fact in passing ("FYI, this project uses pnpm"). A fresh session later gets a task that depends on it ("how do I add lodash?"). The agent is never told to use Mindtrail.

Without memory, the agent answers from habit every time: npm install lodash, a commit message in the wrong format, port 5432 instead of your 5433. With Mindtrail it checks first and gets your project's answer. This is a small test (12 facts run three times, one model, an empty repository), not a measure of task success on large codebases. Method, raw results and how to reproduce.

Install

Mindtrail needs Python 3.11+. The fastest route is uv: uvx downloads and runs Mindtrail on demand, so you only add it to your client. The first time the server starts, it downloads the embedding model (~210 MB) in the background.

Claude Code

claude mcp add mindtrail --scope user -- uvx --from "mindtrail[semantic]" mindtrail serve

--scope user makes Mindtrail available in every project. Check it with claude mcp list.

Cursor and VS Code

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Mindtrail: common questions

Is Mindtrail MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Mindtrail safety report
How do I install Mindtrail?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Mindtrail need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Mindtrail maintained?
The last commit was 26 days ago (2026-10-09). The latest release is v0.1.1.
What can I use instead of Mindtrail?
Servers from other publishers that do the same job: Deja Vu MCP server, Memorix MCP server and Claudexor MCP server.
How does Mindtrail compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 7 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Mindtrail

Same job from other publishers: the closest match first, then the best rated.

  • Deja Vu
    deja-vu: local memory over the session histories of forty-three coding agents.
    A
  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B
  • Claudexor
    Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
    A
  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B
  • State Memory MCP
    Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.
    A