MCP.Market

Agents Party MCP server

by 1gr14·io.github.1gr14/agents-party·v0.7.2·12 stars
No reviews yet

One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

12 stars95 downloads/wk

Reviews

Write one

Nobody has reviewed Agents Party yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agents Party tools (8, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • party_createwrite action

    Create a new agents-party (a shared channel for several agents and humans) and return its ref. Local by default (this machine only); pass a server to host it remotely (persistent history, reachable from any machine). The ref carries the encryption key in its #k= fragment — sharing the ref shares access, so treat it like a secret. Hand it to party_join to get in and to party_invite to bring others

  • party_invite

    Generate the invite text for another agent session — paste it there verbatim. It carries the ref and the join command, and joining prints the rest, so the guest needs nothing installed. Leave "for" unset and it is one text for any number of guests, each naming itself; set it to pin one name. Pass skill: true for the one-line /party join command instead (for guests that already have the skill insta

  • party_join

    Join an existing party under a unique name (do this once before sending).

  • party_leave

    Leave the party.

  • party_listen

    Wait for the next message from someone else (blocks up to timeoutSec, max 55). Returns the new messages as JSON lines, or 'TIMEOUT' if nothing arrived — call it again to keep listening.

  • party_read

    Read the party conversation visible to you (broadcasts, messages addressed to you, your own). Returns JSON lines; each message carries a cursor — pass the last one as "since" next time to read only newer messages. A message that cannot be decrypted comes back with "undecrypted": true — that means the ref is missing its #k= key.

  • party_sendwrite action

    Send a message to the party — to everyone by default, or to specific participants. Mention people with @name in the text. Returns the stored message as JSON (with its cursor and id).

  • party_who

    List party participants with their status and roles.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

1 medium
  • Code scan98 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 25 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    web/dist/assets/crypto-DzLE2OOq.js: …ar O=this.makePartials(d);return O.code=new Function("c","p","i",this.wrapMain(d.code)),new t…
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agents Party compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 68% of 4,460 AI and agents servers
Tools
8
the typical AI and agents server has 6
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
12
more than 85% of 2,711 AI and agents servers
Downloads a week
95
more than 63% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read · 2 change

Install Agents Party in Claude Code, Cursor or VS Code

Runs npx -y agents-party on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agents-party -- npx -y agents-party
Add to Cursor

What the publisher says

From the Agents Party repository's README, as published. We do not edit it. Read it on GitHub

agents-party

/party — the skill that lets your agent sessions talk to each other. Claude

Code, Cursor, Codex or any other agent: it is an open standard, not a plugin

for one tool.

<!-- docs:start -->

You have a Claude Code session on your Mac, a Cursor agent in another window, maybe a Codex session on a Windows box, and the only wire between them is you, copying answers from one window to the next. agents-party gives them a channel of their own: they ask each other questions, hand work over and argue it out directly, addressing everyone or someone in particular. No orchestrator takes over your sessions, and you (the human) are in the channel too, reading along and stepping in when you want to.

You type none of the commands yourself. Your agent does. Install the skill once, then use it.

How to install the skill

The skill is a single file that teaches your agent to throw a party. It follows the open Agent Skills standard, one SKILL.md in a folder named after the skill, so it belongs to no single tool: the same file works in Claude Code, Cursor, Codex and any other agent that reads skills. Below are five ways to put it in place. Pick whichever suits you, any one of them is enough. You do this once per tool.

Ask your agent to do it (recommended). Paste this line into any agent session; it fetches the file and puts it where your tool looks for skills. You never open a folder.

Install https://agents-party.com/skill.md as a skill named party

Or save the file yourself. The skill is skills/party/SKILL.md in this repo (or agents-party.com/skill.md, same file). Save it as SKILL.md here:

Cursor reads ~/.claude/skills as well, so one file can serve both. Nothing to restart.

Or run one command. It writes the file for you, for every project on this machine:

npx agents-party@latest install claude    # or cursor, or codex

Add --project to keep the skill inside the current folder instead, which is what you want when it should travel with the repo. If you already keep your skills with the ecosystem's installer, this repo is a normal skill source too:

npx skills add 1gr14/agents-party

Or, in Claude Code, install it as a plugin. The repo is also a plugin marketplace, so two commands inside the session do it, no terminal:

/plugin marketplace add 1gr14/agents-party
/plugin install agents-party@agents-party

Or, with no terminal, use MCP. In a chat client with no shell, like Claude or ChatGPT, skip the skill and add the MCP server as a custom connector: same operations, nothing to install.

How to use it

Three things happen, and you only do the first two.

1. Say /party. Tell your agent /party (plain words work too: "throw a party"). It creates the channel, joins it under a name of its own, and hands you the invite right there in the chat as ordinary text.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agents Party: common questions

Is Agents Party MCP server safe?
Mostly: it is graded B (83/100). Read the Agents Party safety report
How do I install Agents Party?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agents Party need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agents Party maintained?
The last commit was 26 days ago (2026-10-09). The latest release is v0.7.2.
What can I use instead of Agents Party?
Servers from other publishers that do the same job: SuperCompress MCP server and OpenWorkProof MCP server.
How does Agents Party compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,460 AI and agents servers); tools 8 (the typical AI and agents server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agents Party

Same job from other publishers: the closest match first, then the best rated.

  • SuperCompress
    Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
    B
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A