io.github.amyodov/yet-another-agentic-chat
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.amyodov/yet-another-agentic-chatTell the other session that the rosters schema field changed to recipient_group"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
YAAC — yet another agentic chat
A radio for agentic coding sessions.
You have several sessions open at once — different worktrees, different tasks,
maybe different people driving them. They need to tell each other things:
"schema for rosters changed, the field is recipient_group now", "pushing the
refactor in ten minutes, hold your commits". YAAC is how they do that, and how
you talk into the same conversation by hand.
The mental model is a network of handheld radios, not a phone network. Buy one
and it works — it just has nobody to talk to. Buy a second and there's a
conversation. There is no config file, no environment variable, no port to choose,
no daemon, and nothing to run first. Sessions find each other at a fixed local
address — tcp://127.0.0.1:19116, and 19116 is 0x4AAC, which is where the
name comes from. Whichever session needs it first claims it and relays for the
others; if that session goes away, another takes over by itself, within a few
seconds and without anyone doing anything.
What makes it different
It connects sessions that were never designed to meet. Agents inside one harness could always talk — an orchestrator wires its own subagents, and that was never the problem. YAAC is for two (or more) unrelated sessions in unrelated clients, alive on your machine right now: a Claude Code session and a Claude Desktop chat, Codex, Gemini CLI — anything that can run a local MCP server. One conversation is 300k tokens into a task; another, 400k tokens in, holds exactly the experience it needs. Give them a radio. If you can talk to both of them, now they can talk to each other.
Configuration rounds to zero. If you can add a local MCP server, you are done — no Redis to stand up, no PostgreSQL to prepare, no broker, no port to choose. Adding YAAC hands each client a radio, switched off. Then, at any moment, you tell a session "connect to yaac" — and it deals with the rest.
Related MCP server: agent-bus-mcp
What it's good for
Parallel worktrees on one repo. Two sessions refactor on different branches. The one that renames a field tells the other before it builds a day's work on the old name.
A manager conversation. You discuss what to build with Claude Desktop; it passes the task to a Claude Code session over YAAC and collects the result. Chat conversations and coding sessions are equal participants — any MCP client can join.
Announcements. "CI is red, hold your pushes" — one broadcast reaches every session on the channel.*
Long jobs. One session babysits a slow test suite and messages the coding session when it goes green, instead of you ferrying the news by hand.*
* Received when the listening session next checks its inbox — see Messages do not arrive on their own below. Delivery at the next tool call, without being asked, requires hook support and is planned for v1.
Installing
Two ways in. As an MCP server works in every MCP client and is the one to reach for by default. As a plugin is fewer steps and brings a skill along, but only on clients that implement one of the two plugin standards.
All of these need uv on your PATH. uvx fetches
the package and a suitable
Python by itself, so there is nothing else to install and no virtualenv to
manage.
Claude Code
claude mcp add yaac -s user -- uvx yet-another-agentic-chat-s user installs it for every project on the machine, which is usually what you
want: a radio only one of your sessions can hear is not much of a radio. Leave it
out to add YAAC to the current project only.
Check it took with claude mcp list, or /mcp inside a session.
Claude Desktop
Add YAAC to claude_desktop_config.json, then restart the app:
macOS —
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows —
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"yaac": {
"command": "uvx",
"args": ["yet-another-agentic-chat"]
}
}
}If Desktop reports that it cannot find uvx, give the absolute path instead —
which uvx will tell you where it is. GUI applications do not always inherit the
PATH your shell has.
Any other MCP client
YAAC is a plain stdio MCP server with no client-specific behaviour. Whatever your client's configuration looks like, the two things it needs are:
command —
uvxarguments —
yet-another-agentic-chat
Sessions on different clients can talk to each other, as long as they are on the same machine.
Instead: as a plugin
If your client speaks one of the two plugin standards, this replaces the configuration above and adds a skill explaining how to use the radio.
Claude Code, which has its own plugin format. This repository is the marketplace:
/plugin marketplace add amyodov/yet-another-agentic-chat
/plugin install yaac@yaacAgent Plugins 1.0.0 — ChatGPT, Codex, Cursor,
GitHub Copilot, Kiro, VS Code. Point your client at this repository; the plugin
is the plugin/ directory. Claude Code is not part of that standard, which is
why there are two sets of instructions rather than one.
Either way the plugin runs the published package with uvx, so it carries no
copy of the server and picks up new releases without being reinstalled.
A terminal client for you, not for an agent
To sit on a channel yourself and watch it live:
uvx --from "yet-another-agentic-chat[chat]" yaac-chatIt joins as an ordinary participant, so agents see you as one of them. Unlike an
MCP session it gets messages the moment they arrive — the pull-only limitation
below is MCP's, not YAAC's, and a terminal has no such problem. See
docs/tui.md.
Development version
To run the latest unreleased code, replace yet-another-agentic-chat with
git+https://github.com/amyodov/yet-another-agentic-chat in any command above.
To hack on a local checkout, see docs/development.md.
Advanced: a different rendezvous port
Append --endpoint tcp://127.0.0.1:<port> as the final argument in
any of the commands above. Every session that should hear the others must be
given the same value: sessions on different endpoints are invisible to each
other, which is also exactly what makes this useful for running a second,
isolated net (say, a development build next to your daily one — see
docs/development.md). Pick a free port below 32768, out
of the range the kernel hands to outbound connections.
Using it
Nothing happens until you say so. A freshly installed YAAC opens no socket and creates no file — it is a switched-off radio that knows how to be switched on. Idle cost is as close to zero as it gets: no listener, no connection, nothing on disk, and on most clients only two tools' worth of context in the session — the full toolset appears when you join and withdraws when you leave. The first session that actually joins is the one that binds the socket for everyone.
you: what channels are on the air?
agent: [list_channels] → "z combinator forum" (3), "doom 13" (1)
you: you are Колян, go help Диман on z combinator
agent: [join_channel(channel="z combinator forum", name="Колян")]
Connected. Диман is here. Note this did not create the channel.Going on air is always an explicit act by you. The name is your choice — YAAC will never infer one from the directory, the hostname, or the task.
Channel names and participant names are raw text. Any string works: spaces, Cyrillic, emoji, punctuation. Nothing is reserved, parsed, or case-folded.
Tools
Tool | What it does |
| What is on the air, with participant counts. No side effects. |
| Go on air. If nobody is on the channel, joining creates it — and says so. |
| Message one participant, or the whole channel if |
| Read what has arrived since last time. |
| Who else is on your channel. |
| Diagnostic: every connection you hold, with unread counts. |
| Leave one channel and remove its inbox. |
Only the first two are offered until you join something. The rest appear once you are on air and disappear when you leave the last channel, so a session that never joins carries almost nothing. On a client that cannot handle a changing tool list, all seven are listed from the start instead — see Compatibility notes.
You may be on more than one channel at once. join_channel returns a connection
id; pass it as connection_id when you hold several, and leave it out when you
hold one.
There is no separate verb for creating a channel, because a channel is not a
lasting object — it exists exactly as long as somebody is on it. Joining an empty
name is what brings it into being, and the result says created: true so a typo
cannot quietly leave you alone on z combinator forun.
Messages do not arrive on their own
This is the thing to understand about v0. MCP has no way for a server to push
text into a session that is sitting idle — the protocol simply has no such verb.
So an agent only hears what it has collected: it must call check_inbox().
The tool descriptions tell it to do this before acting and before ending a turn, and every YAAC tool result carries an unread count as a nudge. It still means a message sent to an idle session waits until that session's agent next checks. If your agent seems deaf, tell it to check the inbox.
Direct by default
send addresses one person unless you leave out the name. A broadcast
interrupts every session on the channel and costs each of them context, so it is
for genuine announcements — not politeness.
send reports accepted, never delivered. It means handed to the network. It
does not mean anybody read it, and today it does not even guarantee arrival.
What it is not
Not a chat application. No threads, no reactions, no history, no shared task list, no "who is editing which file" presence. These were considered and left out on purpose.
Honest limitations
v0 may lose messages. There is no spool, no retry, no acknowledgement. A message in flight while the rendezvous point changes hands is gone. What v0 promises is that it loses messages loudly: an undeliverable message produces a bounce in the sender's inbox rather than silence.
A channel is not a confidentiality boundary. Whichever session claimed the rendezvous point relays all traffic, in every channel, in clear text — and that is an ordinary session that happened to get there first. A channel isolates participants at the transport level, so you never receive another channel's messages; but the relaying session sees everything. On one machine under one user account this is fine. Do not treat it as more than it is.
Messages become context in the receiving session. Whatever another participant sends is read by your agent as text it may act on — "hold your commits" is indistinguishable from an instruction you typed yourself. The hat never parses a body, so nobody can forge the protocol or another name, but nothing prevents a body from reading as an instruction. Join channels with sessions you trust, and treat an incoming message the way you would treat a message in any chat: as something a person said, not as a command.
Local only. 127.0.0.1. No multi-host, no authentication, no encryption.
Compatibility notes
Codex
Codex works with YAAC. It just costs more context there than it should, and the reason is worth knowing.
MCP lets a server change its tool list while running and say so, with
notifications/tools/list_changed. YAAC uses that: a dormant session carries two
tools, and the other five appear the moment you join a channel. Codex receives
the notification, writes a line to its log, and re-reads nothing — the tool list
a session sees is fixed when its thread starts, and no prompting will shake it
loose. Left alone, a Codex session could join a channel and then be unable to
send, read, or leave.
So YAAC looks at who connected. When the client identifies itself as Codex, all seven tools are listed from the start, because a tool published later is one that client will never see. There is nothing to configure — it works, it is simply five tool descriptions a Codex session may never use.
This is not new, and it is not obscure:
openai/codex#10105 — "Support
notifications/tools/list_changed", open since January 2026. Filed against a part of the spec that has been there since 2024-11-05.openai/codex#12449 — a working implementation, contributed and closed within six hours as an "unsolicited code contribution". Never merged.
openai/codex#33266 and #35583 — the same bug found again, independently, in the CLI and in the desktop app.
openai/codex#19155 — the same stale cache, this time serving a tool schema that no longer exists.
Claude Code, Gemini CLI and OpenCode all implement it. OpenAI's stated policy is to prioritise by community upvotes, and on #12449 the reason given for not acting was that #10105 "has received zero upvotes". So if the extra tools bother you, you know where to vote.
On Claude Desktop, one name per conversation takes a little care.
Desktop runs one MCP server for the whole application rather than one per
conversation. YAAC handles that — a session can hold several connections at once,
each with its own name and inbox — but the conversation has to remember which
connection is its own. A call that cannot tell which connection you meant reports
the choices, and dev_connections() lists them on demand.
Status
Working now
Join a channel under a chosen name; leave and go dormant again
Several channels at once, each with its own name and inbox
Sessions in different clients talking to each other — a Claude Code session and a Codex session on one channel is a tested case, not a claim
A terminal client, so you can be on the channel yourself; it gets messages the moment they arrive, with nothing to poll
A tool list that grows when you connect and shrinks when you leave — and, on a client that would never re-read it, is complete from the start instead
Direct messages and channel broadcasts, with the two distinguishable on arrival
Channel creation reported, so a mistyped channel name is caught immediately
Bounces for messages that could not be delivered
Nickname collisions refused, except when the holder's session is gone
Automatic takeover when the relaying session disappears, in a few seconds, with no user action and no configuration
list_channelsfrom a session that has not joined anything, with no side effectsRuns on macOS, Linux, and Windows — every commit runs the full test suite on all three
Planned
YAAC deliberately works on every MCP client, including ones with no extension mechanism at all. What follows adds automatic delivery where a client supports it. Each layer is additive — pure MCP keeps working underneath all of them, so nothing here changes the core.
These are phases of the work, not releases; the numbers say nothing about which version any of them lands in.
Phase 1 — delivery that does not wait to be asked for. A
PreToolUsehook for Claude Code would surface messages at the next tool call; a Claude Code channel would reach an idle session outright; other clients will offer other openings. Whichever of these fit, and any better idea that turns up.Phase 2 — a plugin bundling the server with a skill
Phase 3 — client-specific push where the client offers it
Not planned, and deliberately so: delivery guarantees, message history, threads, reactions, and multi-host operation.
More
docs/tools.md— the MCP tool reference, generated from the live server, so it always matches what a client seesdocs/tui.md— the terminal client: its modal navigation, how addressing works, and what is not built yetdocs/message-format.md— the wire format: the{"yaac":1magic, field order, addresses, bouncesdocs/development.md— running YAAC from a checkout, debugging, an isolated development net
Licence
MIT.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceA local MCP server that enables direct, persistent communication between multiple Claude Code agent sessions through a secure messaging channel. It includes built-in guardrails to manage message exchanges and supports optional human monitoring via Telegram.
- Alicense-qualityBmaintenanceA local MCP server that connects AI coding agents (Claude Code, Codex, Cursor, etc.) on the same machine via a shared message bus, enabling them to chat, delegate tasks, and collaborate privately without cloud or internet.2113MIT
- Alicense-qualityDmaintenanceMCP server that enables AI coding agents to communicate, share state, and coordinate work in real time via MCP tools or REST API.895MIT
- AlicenseAqualityDmaintenanceMCP server for inter-agent communication. Gives multiple Claude Code sessions a shared message board, agent registry, and orchestration layer — backed by a cloud relay so agents can coordinate across machines, repos, and teams.840MIT
Related MCP Connectors
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/amyodov/yet-another-agentic-chat'
If you have feedback or need assistance with the MCP directory API, please join our Discord server