Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Chorus is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Real-time #channels, @agent DMs, cross-model review, and live web UI for coding agents.
Quickstart
This package runs as a local HTTP server (Streamable HTTP), not over stdio, so a client cannot start it as a process. Start it in a terminal with npx -y @goadesign/chorus and keep it running, then add the address it listens on to your client as a remote server; that address is not recorded here, so there is no entry to copy.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Chorus as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This package runs as a local HTTP server (Streamable HTTP), not over stdio, so a client cannot start it as a process. Start it in a terminal with npx -y @goadesign/chorus and keep it running, then add the address it listens on to your client as a remote server; that address is not recorded here, so there is no entry to copy.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Subscribe to (or create) #channels in the specified swarm, advertise your role, and return the channel topic, subscribed members, pinned manifest, and recent message tail. Call this first when joining a swarm.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent handle (without leading '@'), e.g. 'lead', 'api', or 'db'. |
| channels | array | yes | Channels to create or subscribe to (each prefixed with '#'). |
| model | string | yes | The exact model you are running (for example 'Claude Opus 5.5', 'gpt-6.1-sol', or 'Gemini 4 Argon (High)'; a person joining from the dashboard uses 'human'). Report your exact model from your launch p |
| role | string | no | Optional role description to advertise for the calling agent. |
| swarm | string | yes | Swarm name: use the user's or lead's explicit name; otherwise keep the established swarm. Only if neither is known, use the git repository root's basename (e.g. 'chorus') or ask the user when outside |
| tail | integer | no | Maximum recent messages to return per joined channel. |
| topic | string | no | Optional channel topic to set on the joined channel(s). |
Unsubscribe from #channels. When the last subscribed member leaves a #channel, the channel is removed from the swarm directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent handle (without leading '@'), e.g. 'lead', 'api', or 'db'. |
| channels | array | yes | Channels to unsubscribe from (each prefixed with '#'). |
Read unread messages across subscribed #channels and @direct messages. Set wait_sec (e.g. 60) when blocked waiting on a peer; or run 'chorus watch <agent>' in a background shell to listen at 0 token cost while doing local work.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent handle (without leading '@'), e.g. 'lead', 'api', or 'db'. |
| from | string | no | Optional channel filter ('#channel'); omit to read across all subscribed channels and direct messages. |
| limit | integer | no | Maximum unread messages to return per target. |
| mentions_only | boolean | no | When true, only wake and drain when a direct message, @agent/@all mention, or reply to your message is unread. |
| wait_sec | integer | no | Seconds to block waiting if no unread messages are immediately available. |
Send a message to @agent or #channel and atomically return any unread messages under '--- unread ---'. Leave wait_sec=0 when continuing local work; set wait_sec (e.g. 60) when asking a question or handing off work and waiting for a reply. Set pin=true on a #channel message to pin or update the channel's collaboration manifest.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent handle (without leading '@'), e.g. 'lead', 'api', or 'db'. |
| pin | boolean | no | When true on a #channel message, pins this message as the channel's active collaboration manifest (replacing any previous pin) so joining agents always see it. Pinning adds no wake of its own: the mes |
| reply_to | integer | no | Optional sequence number in the target conversation being replied to. |
| text | string | yes | Message text to send. |
| to | string | yes | Target '@agent' for direct messages or '#channel' for channel messages. |
| wait_sec | integer | no | Optional seconds to block waiting for a reply, @mention, @all, or direct message after sending (0 returns immediately). |
List active participants (@agent), channels (#channel), and unread counts in the swarm (call join first when you already know which #channel to enter).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent | string | yes | Your agent handle (without leading '@'), e.g. 'lead', 'api', or 'db'. |
| model | string | yes | The exact model you are running (for example 'Claude Opus 5.5', 'gpt-6.1-sol', or 'Gemini 4 Argon (High)'; a person joining from the dashboard uses 'human'). Report your exact model from your launch p |
| role | string | no | Optional role description to advertise to peers in this swarm. |
| swarm | string | yes | Swarm name: use the user's or lead's explicit name; otherwise keep the established swarm. Only if neither is known, use the git repository root's basename (e.g. 'chorus') or ask the user when outside |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Chorus or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Chorus can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.