# Plures (npm · plures-mcp)

Human in the loop for AI agents: ask ID verified people to check a decision before acting.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `plures-mcp`: 77/100 (this document), [markdown](https://verifymcp.io/servers/plureslabs-plures/plures-mcp.md), [page](https://verifymcp.io/servers/plureslabs-plures/plures-mcp)

## Channel facts

- Registry: `npm`
- Package: `plures-mcp`
- Version: `1.5.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to plureslabs/plures).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1186 tokens (~197/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (50% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Plures MCP server?

Plures runs locally as an npm package, launched with npx -y plures-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add plureslabs-plures -- npx -y plures-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "plureslabs-plures": {
      "command": "npx",
      "args": [
        "-y",
        "plures-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "plureslabs-plures": {
      "command": "npx",
      "args": [
        "-y",
        "plures-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add plureslabs-plures -- npx -y plures-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "plureslabs-plures": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "plures-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add plureslabs-plures --command npx --arg -y --arg plures-mcp
```

### Hermes

```yaml
mcp_servers:
  plureslabs-plures:
    command: "npx"
    args: ["-y", "plures-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "plureslabs-plures": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "plures-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add plureslabs-plures -t stdio -c npx -a -y plures-mcp
```

### Other

```json
{
  "mcpServers": {
    "plureslabs-plures": {
      "command": "npx",
      "args": [
        "-y",
        "plures-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 77, +1)

- [security regression] Stability: 0.20 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 1.5.0 → 1.5.1

### 2026-11-02 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 74, 0)

- [security regression] Stability: 0.00 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Tool coverage: 100% → 50%
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: 216 → 187
- [functional] First check of Schema quality: unverified
- [functional] Schema quality: excellent → good
- [functional] Package version: 1.3.1 → 1.5.0

### 2026-10-28 (score 74)

First indexed and scored.

## MCP tools (6)

### `ask_humans` (~595 tokens)

Ask verified humans

Send a decision to ID verified people before you act on it. Several people answer independently, each confirmed with Face ID, and you get back the consensus answer and how strongly they agreed. Use it for judgment calls where being wrong is costly: evals of AI output, tone and intent, whether two things match, moderation edge cases. Send refunds, payments and other money calls with route team. Write the question so a stranger can answer it from the context alone, and never include secrets or more personal data than the decision needs. Live keys use prepaid credit at $0.20 per answer (clips cost more by length), or $0.05 per internal vote with route team; test keys are free and simulated.

Input parameters:

- `app` (string): Which of the developer's apps this is for, like "support-agent". Default: PLURES_APP, then the default app
- `audio_url` (string): An https recording people listen to in full before answering, such as a call your voice agent handled. Up to 3 minutes; needs media_seconds
- `category` (string): A label the developer's routing rules match on, like "refunds"; the rule may choose the route and team
- `context` (string): The material to judge, as plain text: the AI answer and the policy it should follow, the message, the listing
- `image_url` (string): An https image shown with the question
- `instructions` (string): Short guidance shown under the question
- `media_seconds` (integer): Length of the audio or video in seconds. Required with a clip
- `options` (array, required): 2 to 8 possible answers, e.g. ["Yes", "No"]
- `question` (string, required): What people should decide, e.g. "Is this customer upset?"
- `route` (string): verifiers (default) asks ID verified people first. team sends it straight to the developer's own people, for money and account decisions and confidential or policy calls; $0.05 per internal vote live
- `sensitive` (boolean): Set true for violent, graphic or disturbing content, so only people who opted in see it, behind a warning
- `team` (string): The name of one of the developer's teams, like "Finance", to decide instead of the main team
- `team_votes` (integer): With route team: how many people on the team vote; the majority decides
- `verifiers` (number): How many people answer. Default 3; use 5 for higher stakes
- `video_url` (string): An https video (MP4) people watch in full before answering. Up to 3 minutes; needs media_seconds. Not with audio_url
- `wait_seconds` (integer): How long to wait for the answer before returning a task_id to check later. Default 45, up to 240

Output parameters:

- `agreement` (number|null)
- `answer` (string|null)
- `answers` (number)
- `decided_by` (string|null)
- `label` (string|null)
- `mode` (string)
- `route` (string)
- `status` (string)
- `task_id` (string)
- `votes` (object)
- `with_team` (boolean)

### `get_human_answer` (~66 tokens)

Get the human answer

Check on a task sent with ask_humans and return the verified people's answer once it's ready.

Input parameters:

- `task_id` (string, required): The task_id ask_humans returned
- `wait_seconds` (integer): How long to wait if it's still pending. Default 0

Output parameters:

- `agreement` (number|null)
- `answer` (string|null)
- `answers` (number)
- `decided_by` (string|null)
- `label` (string|null)
- `mode` (string)
- `route` (string)
- `status` (string)
- `task_id` (string)
- `votes` (object)
- `with_team` (boolean)

### `cancel_human_task` (~52 tokens)

Cancel a human task

Cancel a task that is still waiting for answers, for example when the decision no longer matters. Answers already given are still billed.

Input parameters:

- `task_id` (string, required): The task_id ask_humans returned

Output parameters:

- `agreement` (number|null)
- `answer` (string|null)
- `answers` (number)
- `decided_by` (string|null)
- `label` (string|null)
- `mode` (string)
- `route` (string)
- `status` (string)
- `task_id` (string)
- `votes` (object)
- `with_team` (boolean)

### `get_mapping_guide` (~59 tokens)

Get the Plures mapping guide

Returns the steps for mapping the developer's AI agent for Plures: how to find its steps and actions, where to suggest a person checks, and how to draft each check. Call this first when asked to map an app for Plures.

### `submit_agent_map` (~98 tokens)

Send an agent map to Plures

Uploads the map you made with get_mapping_guide: nodes, edges and checkpoints with drafted checks. Never include source code, secrets or customer data. If Plures names a problem, fix it and send again.

Input parameters:

- `app` (string): The app id, like support-agent. Default: the PLURES_APP environment variable, then the account's default app
- `map` (object, required): The agent map, as the guide describes

### `get_agent_map` (~68 tokens)

Get an agent map

Returns an app's agent map from Plures: its checkpoints, which are added, and live numbers for each (checks in 30 days, agreement, how many went to the team).

Input parameters:

- `app` (string): The app id. Default: PLURES_APP, then the default app

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/plureslabs-plures/plures-mcp#diagnostics

## Score history

- 2026-11-05: 77
- 2026-11-04: 77
- 2026-11-03: 76
- 2026-11-02: 76
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 75
- 2026-10-29: 74
- 2026-10-28: 74

## Common questions

### What is the Plures MCP server?

Plures is an MCP server listed in the public MCP registry as io.github.plureslabs/plures. Human in the loop for AI agents: ask ID verified people to check a decision before acting. This page covers its npm package (plures-mcp).

### Is the Plures MCP server safe to use?

Plures scores 77 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Plures MCP server expose?

Plures exposes 6 tools: ask_humans, get_human_answer, cancel_human_task, get_mapping_guide, submit_agent_map, get_agent_map. Their descriptions and schemas cost roughly 938 tokens of context every time the server is loaded.

### Is the Plures MCP server still maintained?

Plures is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Plures MCP server under?

Plures declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/plures-mcp
- Socket report: https://socket.dev/npm/package/plures-mcp
- Repository: https://github.com/plureslabs/plures
- Website: https://plures.si/docs#mcp
- Changelog RSS feed: https://verifymcp.io/servers/plureslabs-plures/plures-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/plureslabs-plures/plures-mcp.json
- HTML version of this page: https://verifymcp.io/servers/plureslabs-plures/plures-mcp