Thread Mind MCP server
io.github.mahmoud-nb/thread-mind·v0.5.0·3 starsGit-friendly memory for AI coding: a tree of thread summaries with inherited context
3 stars16 downloads/wk
Reviews
Write oneNobody has reviewed Thread Mind yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Thread Mind tools (14, 5 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
context_getGet the assembled context of the active thread: its summary plus the decisions and constraints of its ancestors. Call it once at the start of a session.
project_createwrite actionCreate a new ThreadMind project with a main thread
project_listList all ThreadMind projects
project_switchSwitch to a different project
stats_showShow the size of each summary and, with the Claude Code plugin, measured conversation sizes
summary_updatewrite actionUpdate the summary of a thread (markdown). With a section, adds to that section only (or replaces it with replaceSection); without one, replaces the whole summary, so keep what is still true.
thread_createwrite actionCreate a new child thread branching from a parent thread, and make it the active thread. On a feature branch, the thread is linked to that branch.
thread_deletewrite actionDelete a thread and all its descendants
thread_listDisplay the thread tree for the active project, with each thread's status and linked branch
thread_mergeFold a finished thread into its parent: replaces the parent's summary with parentSummary, marks the thread done and switches to the parent. Write parentSummary yourself, including the thread's conclusions.
thread_rebaseMove a thread to a different parent. All descendants move with it. Similar to git rebase.
thread_statusMark a thread as done or abandoned (or active again). The reason is added to the thread's decisions, so the outcome stays on record.
thread_switchSwitch this session to a different thread and return its assembled context (no need to call context_get afterwards)
threadmind_initwrite actionWrite ThreadMind usage instructions into the files AI agents read. Claude Code doesn't need them: it receives these instructions from this server.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan45 source files scanned13/25
- –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
Findings (1)
- highShell command built from a string (injection risk)
exec.shell-concatdist/core/project.js: …tConfig(key) { try { return execSync(`git config ${key}`, { encoding: "utf-8", …
How Thread Mind compares
Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 74/100
- higher than 38% of 1,119 Developer tools servers
- Tools
- 14
- the typical Developer tools server has 7
- Tools that change things
- 36%
- typical: 5%. Fewer write tools means less an agent can break
- GitHub stars
- 3
- more than 75% of 855 Developer tools servers
- Downloads a week
- 16
- more than 4% of 436 Developer tools servers with a package
What its tools let an agent do: 9 read · 5 change
Install Thread Mind in Claude Code, Cursor or VS Code
Runs npx -y thread-mind-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add thread-mind -- npx -y thread-mind-mcp
What the publisher says
From the Thread Mind repository's README, as published. We do not edit it. Read it on GitHub
ThreadMind MCP
Branches for your AI's memory: a git-friendly tree of thread summaries.
ThreadMind is a Model Context Protocol (MCP) server that gives AI coding sessions a memory: a tree of threads, each holding a short summary of what was decided about one topic, stored as Markdown in your repository. Start a fresh session and the active thread's context — its decisions and those of its ancestors — replaces a history that had grown to tens of thousands of tokens.
Documentation | npm | GitHub
Why ThreadMind?
With AI coding assistants, conversations grow long: every request carries the whole history, until the client compacts it or you start over — and starting over loses what was decided. ThreadMind keeps what matters:
- Summaries in sections — Decisions, Constraints, State, Open questions, Next steps
- Inheritance through the tree — a thread's context is its summary plus its ancestors' decisions and constraints; sibling branches stay out
- Branching exploration — try approaches in separate threads, merge the winner's conclusions into the parent, keep the reason an approach was abandoned
- Git-aware — a thread created on a feature branch becomes active whenever that branch is checked out, and summaries warn when the code they describe has changed
- Team collaboration — thread files are committed with the code and reviewed in pull requests
Where the savings come from
ThreadMind can't shrink a conversation in progress: your client decides what it sends. The savings come when you start over:
Before /clear: the conversation carries ~48,000 tokens of history
After /clear: the session starts with the thread's context, ~1,100 tokens
main
├── auth
│ └── auth-ui ← active context = main + auth (decisions, constraints) + auth-ui
└── dashboard dashboard stays outWith the Claude Code plugin, the context reloads automatically after /clear and after compaction, and stats_show measures both sizes on your own sessions.
Quick Start
Claude Code plugin (recommended)
/plugin marketplace add mahmoud-nb/thread-mind-mcp
/plugin install thread-mind@thread-mindThe plugin installs the server and adds:
- a SessionStart hook that loads the active thread's context at startup, after /clear and after compaction (nothing happens in repositories without a ThreadMind project)
- a SessionEnd hook that records how large the conversation grew, read from its transcript, for stats_show
- commands: /thread-mind:context, /thread-mind:tree, /thread-mind:create, /thread-mind:switch, /thread-mind:summary, /thread-mind:merge, /thread-mind:stats
If you configured ThreadMind manually before, remove that configuration so Claude Code doesn't run two servers.
Installation
No installation required — run directly with npx:
npx thread-mind-mcpOr install globally:
npm install -g thread-mind-mcpConfigure with Claude Code
Add to your Claude Code MCP settings (~/.claude/settings.json or project .claude/settings.json):
macOS / Linux:
{
"mcpServers": {
"thread-mind": {
"command": "npx",
"args": ["-y", "thread-mind-mcp"]
}
}
}Windows:
{
"mcpServers": {
"thread-mind": {
"type": "stdio",
"command": "cmd",
"args": ["/c", "npx", "thread-mind-mcp"],
"env": {}
}
}
}Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Thread Mind: common questions
- Is Thread Mind MCP server safe?
- Mostly: it is graded B (74/100). Read the Thread Mind safety report
- How do I install Thread Mind?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Thread Mind need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is Thread Mind maintained?
- The last commit was 37 days ago (2026-09-27). The latest release is v0.5.0.
- What can I use instead of Thread Mind?
- Servers from other publishers that do the same job: Nexusmem MCP server, Agent Memory MCP server and Repowise MCP server. Compare all Thread Mind alternatives.
- How does Thread Mind compare with other Developer tools MCP servers?
- safety score 74/100 (higher than 38% of 1,119 Developer tools servers); tools 14 (the typical Developer tools server has 7); tools that change things 36% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Thread Mind
Same job from other publishers: the closest match first, then the best rated.
- NexusmemLocal-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.not reviewedGrowingA
- Agent MemoryGit-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.not reviewedGrowingA
RepowiseCodebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.not reviewedEstablishedB- PalinodeInspectable, correctable project memory in git-versioned Markdown for AI agents.not reviewedEstablishedC
- ForemergeCoordinate parallel coding agents, above Gitnot reviewedGrowingA