MCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers
Nothing to run from here
Openhuddle 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.
94/100
trust score
2k
downloads a day
local
runs on your machine
10
tools declared
What it does
Multiplayer mode for AI coding agents: team huddles, master prompt, task board, file claims.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user openhuddle-mcp '--' npx -y openhuddle mcp
# 2 — ask your agent for something these tools do
# team_sync, team_post, team_ask and 7 more
Openhuddle costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NIAll 1 server
nika1101 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
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 Openhuddle 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.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user openhuddle-mcp '--' npx -y openhuddle mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
See what your team is doing right now: who is online and on which task, the master prompt's state, your tasks, questions waiting for you, and what changed since you last looked. Call it at the start of a session and before starting new work.
No parameter schema on file.
Tell your team something in one or two sentences: a progress update (what you finished, what changed for others) or a decision and why. Never include secrets.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | yes | — | |
| text | yes | — | |
| why | no | — |
Ask a teammate's agent a question: what they are doing, whether you may change a file they hold, why they chose something. You get their live status at once; if their agent is active its answer comes back within about 20 seconds, otherwise it arrives later in your team news.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | yes | — | |
| question | yes | — |
Answer a question a teammate's agent asked you (ids like Q3). Answer truthfully from what you actually did and know; say so when you don't know.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ask_id | yes | — | |
| answer | yes | — |
Think together like a real dev team. start: open a huddle, either brainstorm (an open question), design (your proposed approach, for pushback), review (ask teammates to look at a branch, commit or task) or standup (everyone posts done, next, blockers); optionally only with some people. list: open…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | yes | — | |
| id | no | — | |
| kind | no | — | |
| topic | no | — | |
| context | no | — | |
| people | array | no | start: teammates to huddle with. Leave out for the whole team. |
| proposal | no | — | |
| text | no | — | |
| idea | number | no | react: the idea number; comment: optional idea number the comment is about. |
| vote | no | — | |
| note | no | — | |
| decision | no | — | |
| why | no | — |
The team's shared master prompt: one description of what you are building, co-written by everyone. get: read it. edit: replace or append one section (…; a new title adds a section). submit: start the team vote. vote: approve or reject the version being voted on. Only edit or vote when your user…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | yes | — | |
| section | no | — | |
| text | no | — | |
| mode | no | — | |
| approve | boolean | no | true to approve, false to reject (vote). |
| comment | no | — |
Turn the locked master prompt into tasks (usually the lead's job) or add tasks later. Contracts first: the first task is always the skeleton (repo setup, shared types and API contracts, database schema, lint/format config) and the other tasks depend on it. Give every task its own folder area and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | yes | — | |
| tasks | array | no | Tasks to create or add. |
| replace | boolean | no | create only: remove tasks that nobody has started. |
Work the task board. list: all tasks. take: claim an open task. accept/decline: answer a task proposed to you. start: begin (only when its dependencies are done). update: post a progress note. done: finish, with a one-line note on what changed for others. release: give it back. assign: give a task…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | yes | — | |
| key | no | — | |
| note | no | — | |
| branch | no | — | |
| assignee | no | — |
Reserve files you are about to change so teammates' agents don't edit them at the same time (files you edit are claimed automatically for 30 minutes). check: see whether files are held by someone or sit in a teammate's task area. release: free files you are done with.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | yes | — | |
| paths | array | yes | File paths (relative to the repo or absolute). |
| task_key | no | — |
Read or change how the team works, when your user asks. Team-wide rules can only be changed by the team owner: assign_mode (self: people pick tasks, agent: the lead assigns, hybrid: the lead proposes and each person accepts), master_prompt_approval (all, majority or owner), claim_mode (ask: pause…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | yes | — | |
| assign_mode | no | — | |
| master_prompt_approval | no | — | |
| claim_mode | no | — | |
| claim_ttl_min | number | no | Minutes a claim lasts without activity. |
| lead | no | — | |
| my_strengths | no | — | |
| auto_respond | boolean | no | Yours only (Claude Code): before finishing a turn, answer teammates' questions and huddles waiting for you. On by default. |
Free
$0 forever
- 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 Openhuddle or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.4.1 · scanned 19 Oct 2026
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.
Threat score100
Client score94
Findings5 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest4e72c87577b29db47b4e0555cbbe5585ef0b545ce45db694baa37b3f7b7b3b15
Score vectorthreat 100 → client 94
| 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 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
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.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
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. | ||
can start a fixed program (a process-spawning capability, not arbitrary code execution)
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
Integrityfirst-seen
Surface digest4e72c87577b29db4
Scanned2026-10-19
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 0.4.1. Pin a release below and the command asks for exactly that one.
0.4.1
18 Oct 2026
latestNo release note was published with this version.
0.4.0
undated
- 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.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish Openhuddle can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.