pickfit

BrowseMCP servers

HIEF (Hybrid Intent-Evaluation Framework)

Local MCP server giving coding agents persistent searchable context, task coordination, and quality checks.

Tested on LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 1 known high or critical vulnerability (2 findings, one per affected package version) in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:rustls-webpki 0.102.8 rustls-webpki: Denial of service via panic on malformed CRL BIT STRING (GHSA-82j2-j2ch-gfr8, high, fixed in 0.103.13)
See 1 more

Linux x86_64

You need first

  • Runtimes: Rust stable toolchain 1.85+
  • System packages: Git
  1. download linux x86_64 release tarball and extract

    curl -fsL https://github.com/hiranp/hief/releases/download/v0.5.0/hief-linux-x86_64.tar.gz -o /tmp/hief.tar.gz && tar xzf /tmp/hief.tar.gz -C /tmp
    mkdir -p ~/.local/bin
  2. install binary to ~/.local/bin and verify on PATH

    cp /tmp/hief ~/.local/bin/hief && hief --help

Check that it works

cp /tmp/hief ~/.local/bin/hief && hief --version && hief --help

The output should contain “hief 0.5.0”.

Add it to your agent

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

In your project folder, run hief init, then hief index build, then point your MCP client at hief serve.

What it does

  • Search your codebase with AST-aware search
    How to use it
    1. In your project folder, run hief init and then hief index build.
    2. Start the server with hief serve and connect your MCP client.
    3. Call the search_code tool with a query, such as {"query":"<your text>"}.
    Tested
  • Coordinate tasks with an intent graph
    How to use it
    1. In your project folder, run hief init, then start the server with hief serve.
    2. From your MCP client, call create_intent with a title, kind and description, such as {"title":"<your title>","kind":"feature","description":"<your text>"}.
    Tested
  • Evaluate quality with golden sets
    Not shown working
  • Scaffold documentation and sync workflows
    Not shown working

How far pickfit got

Linux x86_64

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

Good for

  • index and search codebase with keyword, structural, and semantic search
  • coordinate tasks via dependency-tracked intent graph
  • run golden-set quality evaluations against codebase
  • scaffold feature specs from templates
  • expose markdown recipes as dynamic agent tools

An alternative to Augment Code, Sourcegraph and Cursor.

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 1 Nov 2026
  • Version 0.5.0

An MCP client handshake over stdio listed 38 tools, and a call to search_code returned a result.

Differences the test machine hit

  • README: Install from source via cargo build --release (requires Rust 1.85+/1.88+)
    In the test: Used prebuilt binary hief-linux-x86_64.tar.gz from GitHub releases v0.5.0; cargo build needs Rust toolchain not present in box
  • README: hief serve starts MCP server (stdio) with no prior setup
    In the test: Server expects project initialized via hief init and indexed via hief index build in the working directory before serve
  • README: An MCP server over stdio writes only JSON-RPC messages to stdout
    In the test: This server wrote 2 other line(s) to stdout during the handshake; strict MCP clients may reject them.

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.