pickfit

BrowseDeveloper CLIs

Context Guardian

MCP server and proxy that indexes local context so agents can search it with tools.

Tested on LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 2 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • npm:hono 4.12.12 hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard (GHSA-88fw-hqm2-52qc, high, fixed in 4.12.25)
  • npm:zod 3.25.76 Zod can exhaust memory while validating oversized constrained collections (GHSA-mrhx-c7xc-m3w5, high, fixed in 4.6.6)

Linux x86_64

You need first

  • Runtimes: Node.js 20+
  • Needs the network
  1. install context-guardian via npm

    npm install -g context-guardian-mcp
Where the README and reality differ
  • README: Create `.context-guardian.json` with `context-guardian init`
    What worked: init creates guardian.config.json in cwd and prints to stderr

Check that it works

curl -s http://localhost:9120/mcp -H 'Content-Type: application/json' -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"index_content","arguments":{"content":"function login(user, pass) { return auth(user, pass); }\nERROR 2024-01-01 login failed for user alice\nconfig: {\"port\": 9120}","source":"auth.ts"}}}'

The output should contain “Indexed 1 chunks from”.

First thing to try

curl -s http://localhost:9120/mcp -H 'Content-Type: application/json' -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"index_content","arguments":{"content":"function login(user, pass) { return auth(user, pass); }\nERROR 2024-01-01 login failed for user alice\nconfig: {\"port\": 9

Start the server with context-guardian mcp --port 9120, then send MCP requests to http://localhost:9120/mcp.

What it does

  • Index code, logs and config locally
    How to use it
    1. Start the server with context-guardian mcp --port 9120.
    2. Call the index_content tool with your text and a source name: `curl -s http://localhost:9120/mcp -H 'Content-Type: application/json' -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name
    Tested
  • Give coding agents search tools over the index
    How to use it
    1. Start the server with context-guardian mcp --port 9120 and index some content.
    2. Search it with the grep tool: `curl -s http://localhost:9120/mcp -H 'Content-Type: application/json' -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"grep","arguments":{"pattern":
    Tested
  • Proxy OpenAI and Anthropic agent requests locally
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 2 of 3 features work
  4. Works offline

Good for

  • index code, logs and configs into local store
  • regex search indexed content with context lines
  • search logs and errors by query
  • find functions, classes and interfaces across code
  • inspect git changes

How pickfit tested it

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

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.3.0

Differences the test machine hit

  • README: Requirements: Ollama running locally with qwen3.5:4b and nomic-embed-text
    In the test: index_content and grep work without Ollama via heuristic classification and zero-vector embedding fallback; proxy warns Ollama not detected and uses fallback behavior

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.