pickfit

BrowseMCP servers

scoped-mcp

Per-agent scoped MCP tool proxy with credential isolation, resource scoping, and audit logging.

Tested on Linux

Use it

Linux x86_64

  1. install scoped-mcp via uv tool install

    uv tool install scoped-mcp
Where the README and reality differ
  • README: pip install scoped-mcp and run scoped-mcp --manifest
    What worked: requires AGENT_ID and AGENT_TYPE env vars or server exits with ConfigError; also needs manifest file and base_path/db_dir to exist
  • README: filesystem_list_dir path="/" example
    What worked: root path "/" rejected; use "." to list agent-scoped directory

Add it to your agent

claude mcp add scoped-mcp -e AGENT_ID='<AGENT_ID>' -e AGENT_TYPE='<AGENT_TYPE>' -e SCOPED_MCP_BEARER_TOKEN='<SCOPED_MCP_BEARER_TOKEN>' -- scoped-mcp --manifest '<manifest>'
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "scoped-mcp": {
      "command": "scoped-mcp",
      "args": [
        "--manifest",
        "<manifest>"
      ],
      "env": {
        "AGENT_ID": "<AGENT_ID>",
        "AGENT_TYPE": "<AGENT_TYPE>",
        "SCOPED_MCP_BEARER_TOKEN": "<SCOPED_MCP_BEARER_TOKEN>"
      }
    }
  }
}

You fill in

  • AGENT_ID: unique agent instance identity (required)
  • AGENT_TYPE: agent role for manifest mapping (required)
  • SCOPED_MCP_BEARER_TOKEN: bearer token for http transport (required)

Replace <manifest> with your own path. Ask the user for AGENT_ID, AGENT_TYPE, SCOPED_MCP_BEARER_TOKEN; pickfit never had a value, so these are placeholders.

Add scoped-mcp as an MCP server in your MCP client, then call the scoped_mcp_status tool to see which tools your agent can use.

What it does

  • Give each agent only the tools it is allowed to use
    Not tested
  • Keep each agent within its own resources
    Not shown working
  • Hold backend credentials so agents never see them
    Not tested
  • Log every tool call to an audit trail
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • load only the tools an agent is allowed to use
  • enforce resource boundaries between agents
  • hold backend credentials so agents never see them
  • log every tool call to a structured audit trail

An alternative to Aggregation gateways, Access control proxies, Credential proxies and Enterprise gateways.

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 1.19.3

An MCP client handshake over stdio listed 3 tools, and a call to filesystem_read_file 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.