pickfit

BrowseMCP servers

Krusch Context MCP

Local MCP server giving AI coding agents persistent working memory for project decisions across sessions.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js >= 22.0.0
  1. install krusch-context-mcp globally via npm

    npm install -g krusch-context-mcp
Where the README and reality differ
  • README: Zero-GPU default runs 100% offline using deterministic keyword extraction if neither Ollama nor API key is present
    What worked: krusch_context_remember fails with "MCP error -32603: Failed to generate embedding" unless OLLAMA_URL/OPENROUTER_API_KEY or EMBEDDING_URL is reachable; verified via direct MCP call after init and after switching .env to EMBEDDING_PROVIDER=auto
  • README: npx krusch-context-mcp init creates .env with sensible defaults for offline use
    What worked: init writes OLLAMA_BASE_URL=http://localhost:11434 EMBEDDING_PROVIDER=ollama which makes remember fail without a running Ollama instance

Add it to your agent

claude mcp add krusch-context-mcp -- krusch-context-mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "krusch-context-mcp": {
      "command": "krusch-context-mcp",
      "args": []
    }
  }
}

Add the krusch-context-mcp server to your MCP client's configuration, then ask your agent to call krusch_context_health to confirm it is connected.

What it does

  • Store, retrieve, and retire project decisions
    Not tested
  • Record architectural decisions and lessons
    Not tested
  • Check diffs against active project invariants
    Not tested
  • Replace outdated facts and keep their history
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 4 features work
  4. Works offline

Good for

  • capture architectural decisions and invariants
  • retrieve active memories and steering rules
  • audit diffs against project invariants pre-commit
  • supersede stale knowledge with lineage tracking
  • report memory health and TTL decay review

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 1.8.0

An MCP client handshake over stdio listed 5 tools, and a call to krusch_context_health returned a result.

Differences the test machine hit

  • README: krusch-context-mcp --help / --version
    In the test: binary has no --help/--version flag; running without args starts MCP stdio server (ExperimentalWarning: SQLite)

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.