pickfit

BrowseMCP servers

PermitAI NEPA MCP Toolkit

MCP server toolkit giving AI agents structured access to federal environmental and regulatory data for NEPA screening.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Python 3.12 or newer
  • Needs the network
  • Keys or accounts: CENSUS_API_KEY, EPA_AQS_EMAIL, EPA_AQS_API_KEY
  1. install nepa-mcp via pipx (candidate 1)

    pipx install nepa-mcp

Check that it works

nepa-mcp --help

The output should contain “usage: nepa-mcp”.

First thing to try

nepa-mcp doctor

Add it to your agent

claude mcp add nepa-mcp -e CENSUS_API_KEY='<CENSUS_API_KEY>' -e EPA_AQS_EMAIL='<EPA_AQS_EMAIL>' -e EPA_AQS_API_KEY='<EPA_AQS_API_KEY>' -- nepa-mcp server cfr
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "nepa-mcp": {
      "command": "nepa-mcp",
      "args": [
        "server",
        "cfr"
      ],
      "env": {
        "CENSUS_API_KEY": "<CENSUS_API_KEY>",
        "EPA_AQS_EMAIL": "<EPA_AQS_EMAIL>",
        "EPA_AQS_API_KEY": "<EPA_AQS_API_KEY>"
      }
    }
  }
}

You fill in

  • CENSUS_API_KEY: Census API credentials (required)
  • EPA_AQS_EMAIL: EPA AQS account email (required)
  • EPA_AQS_API_KEY: EPA AQS API key (required)

Ask the user for CENSUS_API_KEY, EPA_AQS_EMAIL, EPA_AQS_API_KEY; pickfit never had a value, so these are placeholders.

Run nepa-mcp doctor to check the setup, then connect the server to your MCP client.

What it does

  • Get federal environmental data for NEPA screening
    Not shown working
  • Build interactive maps and GeoJSON exports
    Not shown working
  • Search permitting projects and review timetables
    Not shown working

How far pickfit got

Linux x86_64

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

Good for

  • compose project-area data into interactive HTML map or GeoJSON export
  • search permitting projects by title, state, sector and agency
  • retrieve tracked agency reviews and milestones timetable for a project
  • find upcoming, completed or past-target permitting milestones

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 0.1.6

An MCP client handshake over stdio listed 7 tools, and a call to cfr_browse_structure returned a result.

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.