pickfit

BrowseMCP servers

YAAC — yet another agentic chat

Local radio over MCP letting concurrent AI coding sessions message each other.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • System packages: uv
  1. install yet-another-agentic-chat via uv tool install so launch command is on PATH

    uv tool install yet-another-agentic-chat && yet-another-agentic-chat --help; echo EXIT:$?
    # also check yaac-chat exists
    which yet-another-agentic-chat; which yaac-chat; uv tool list

Check that it works

yet-another-agentic-chat --help

The output should contain “A radio for agentic sessions”.

Add it to your agent

claude mcp add yet-another-agentic-chat -- yet-another-agentic-chat
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "yet-another-agentic-chat": {
      "command": "yet-another-agentic-chat",
      "args": []
    }
  }
}

Add yet-another-agentic-chat as an MCP server in your AI coding client, then call the list_channels tool to see available channels.

Linux x86_64

You need first

  • System packages: uv
  1. install YAAC with Python 3.14 via uv tool

    uv tool install --python 3.14 yet-another-agentic-chat

Check that it works

yet-another-agentic-chat --help

The output should contain “A radio for agentic sessions”.

Add it to your agent

claude mcp add yet-another-agentic-chat -- yet-another-agentic-chat --rendezvous tcp://127.0.0.1:19199
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "yet-another-agentic-chat": {
      "command": "yet-another-agentic-chat",
      "args": [
        "--rendezvous",
        "tcp://127.0.0.1:19199"
      ]
    }
  }
}

Add yet-another-agentic-chat as an MCP server in your AI coding client, then call the list_channels tool to see available channels.

What it does

  • Join a channel under a name you choose
    How to use it
    1. Connect your MCP client to the yet-another-agentic-chat server.
    2. Call the join_channel tool with {"channel":"<channel>","name":"<your name>"}.
    Tested
  • Message other AI coding sessions running at the same time
    Not shown working
  • Send direct messages or broadcast to a channel
    Not shown working

How far pickfit got

macOS arm64

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

Linux x86_64

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

Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • coordinate parallel worktrees on one repo about renames
  • pass a task from a chat conversation to a coding session
  • broadcast announcements to every session on a channel
  • notify a coding session when a long test suite goes green

How pickfit tested it

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

macOS arm64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.6.5

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

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.6.5

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

Differences the test machine hit

  • README: needs uv on PATH, uvx fetches package and suitable Python by itself
    In the test: uv tool install --python 3.14 yet-another-agentic-chat (uv fetched cpython-3.14.10); box python3.12 cannot satisfy Python>=3.14
  • README: launch with uvx yet-another-agentic-chat
    In the test: installed package with uv tool install so launch command yet-another-agentic-chat is on PATH; plain uvx launch would re-fetch on every run and fail with network off
  • README: sessions meet at tcp://127.0.0.1:19116 with no flag
    In the test: isolated test net via --rendezvous tcp://127.0.0.1:19199; default tcp://127.0.0.1:19116 shared by all sessions

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.