MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Quorum 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
Attested multi-agent consensus: proposals, votes, and outcomes stamped and traced.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http terradev-cloud-quorum-mcp https://quorum-mcp.terradev.cloud/mcp
# 2 — ask your agent for something these tools do
# register, propose, write and 4 more
Quorum costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http terradev-cloud-quorum-mcp https://quorum-mcp.terradev.cloud/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
7 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.
OPTIONAL one-time setup -- only needed if you want proposal telemetry (OTLP spans) pushed to your Telinea account. Call once before propose: it binds an api_key you choose to your Telinea API key. Afterwards, pass the same api_key on propose and every span for that proposal is pushed to your Telinea with standard OTLP bearer auth. Storage: the Telinea key is sealed with AES-256-GCM under a key der
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | Your Quorum API key -- chosen by you, presented on propose, never stored. |
| telinea_key | string | yes | Your Telinea API key -- stored encrypted, used to authenticate span pushes. |
Open a new proposal: a question, named options, expected voter identities, an aggregation algorithm, a deadline, and a quorum threshold. Returns the proposal id, the creation attestation, and the deadline. All later operations key off the proposal id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | no | Optional. Your Quorum API key (from register). Binds the proposal to your account so its spans push to your Telinea. Omit for anonymous use -- everything works, no spans. |
| name | string | yes | Human-readable proposal id, e.g. pr-review-2026-09-18. Letters, digits, . _ - only; becomes the key for all subsequent calls. |
| namespace | string | no | Optional tenant namespace. The proposal id becomes '<namespace>:<name>' -- different teams can reuse names without colliding. Same charset as name. |
| question | string | yes | The thing being decided. |
| voters | array | yes | Expected voter identities. Only these may vote; missing voters at resolution are recorded abstained. |
| deadline_minutes | number | yes | Minutes until voting closes. |
| options | array | no | Named options. Default ["yes","no"]. |
| algorithm | string | no | Aggregation algorithm. Default approval -- robust general-purpose choice with no strategic incentive. |
| quorum | number | no | Min percent of expected voters that must vote before resolution. Default 100. |
| threshold | number | no | Supermajority only: required share of votes cast, percent. Default 66.67. |
| description | string | no | Optional context for the audit trail. |
Append a key-value entry to a proposal's blackboard. Any agent may write; writes are appended, never replaced -- the full ordered history is preserved and attested.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proposal_id | string | yes | — |
| key | string | yes | Key other agents use to filter this entry on read. |
| value | yes | Any JSON value. | |
| author | string | no | Optional author identity, recorded and attested. |
Read a proposal's blackboard: every write in order with timestamp, author, and attestation id -- the complete deliberation record, or filtered to one key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proposal_id | string | yes | — |
| key | string | no | Optional: only entries with this key. |
Submit a vote from an expected voter identity, with optional reasoning stored in the attested record. Vote shape depends on the algorithm: plurality/supermajority take an option string; approval takes an option or list of options; borda takes a ranking of all options; condorcet takes a ranking or a single option; opinion_pool takes a probability distribution over options. Duplicates and post-deadl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proposal_id | string | yes | — |
| voter | string | yes | — |
| value | yes | Ballot in the algorithm's format. | |
| reasoning | string | no | Free-text rationale, kept in the audit trail. |
Compute and attest the outcome once quorum is met (or the deadline has passed). Idempotent: resolving twice returns the recorded outcome. Condorcet cycles and missed supermajority thresholds return co_winners with status unresolved rather than an arbitrary tiebreak.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proposal_id | string | yes | — |
The complete attested record of a proposal in chronological order: creation, every blackboard write, every vote with reasoning, the outcome. Optional filter: all | writes | votes | outcome.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proposal_id | string | yes | — |
| filter | string | no | Default all. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Quorum 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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.1.
No release note was published with this version.
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 Quorum 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.