Ext Ops Panel
Open dashboard
Comparison

fakechat vs Agent Comms

fakechat is a plugin bundle for AI coding tools published by anthropics. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-official). Agent Comms is an MCP server published by ExaDev. Marketplaces we read that list it: 2 (Official MCP Registry, Community GitHub marketplaces). As of our marketplace pass on 2026-10-15. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplacefakechatAgent Comms
Claude Code: claude-plugins-official Listed
Version: 0.0.1
Forks (GitHub): 4 268
Stars (GitHub): 37 981
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 8.13.20
Downloads/month (npm): 46 698
Downloads/week (npm): 3 230
Forks (GitHub): 10
Stars (GitHub): 31
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

fakechat vs Agent Comms
FactfakechatAgent Comms
Marketplaces that list it (differs)1 (worse)2 (better)
Stars (GitHub) (differs)37 981 (better)31 (worse)
Forks (GitHub) (differs)4 268 (better)10 (worse)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (agent-comms)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Hooks it runs (differs)Not published3
Parts of the bundle (differs)115
Licence (differs)Not statedMIT
Repository (differs)github.com/anthropics/claude-plugins-officialgithub.com/exadev/agent-comms
Changes in the last 7 days (differs)02
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

fakechat

In its own words, on Claude Code: claude-plugins-official:

Localhost web chat for testing the channel notification flow. No tokens, no access control, no third-party service.

Agent Comms

In its own words, on Official MCP Registry:

Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP

How to run each

fakechat As a Claude Code plugin

Claude Code
/plugin install fakechat@claude-plugins-official

Agent Comms As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio agent-comms -- npx -y agent-comms

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: fakechat · What it can do: Agent Comms · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-official/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built