# Prooftask (npm · prooftask-mcp)

Free public n8n, AI support and software acceptance templates; scoped private delivery workflows.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `prooftask-public-mcp-production.up.railway.app`: 69/100, [markdown](https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-public-mcp-production.md), [page](https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-public-mcp-production)
- npm · `prooftask-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-mcp.md), [page](https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-mcp)

## Channel facts

- Registry: `npm`
- Package: `prooftask-mcp`
- Version: `0.1.1`
- 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 2026-10-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 826 tokens (~35/item across 23 items; 23 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 23 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 24 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

Prooftask runs locally as an npm package, launched with npx -y prooftask-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 cognitive-emergence-prooftask -- npx -y prooftask-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "cognitive-emergence-prooftask": {
      "command": "npx",
      "args": [
        "-y",
        "prooftask-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cognitive-emergence-prooftask": {
      "command": "npx",
      "args": [
        "-y",
        "prooftask-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cognitive-emergence-prooftask -- npx -y prooftask-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add cognitive-emergence-prooftask --command npx --arg -y --arg prooftask-mcp
```

### Hermes

```yaml
mcp_servers:
  cognitive-emergence-prooftask:
    command: "npx"
    args: ["-y", "prooftask-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "cognitive-emergence-prooftask": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "prooftask-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cognitive-emergence-prooftask -t stdio -c npx -a -y prooftask-mcp
```

### Other

```json
{
  "mcpServers": {
    "cognitive-emergence-prooftask": {
      "command": "npx",
      "args": [
        "-y",
        "prooftask-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.

### 2026-10-17 (score 61)

First indexed and scored.

## MCP tools (23)

### `exportLegacyRecord` (~25 tokens)

Legacy transport: requires independent trust for verification

Input parameters:

- `path` (object, required)

### `exportResultPackage` (~39 tokens)

Export portable v2 package and fresh signed status bound to the expected agreement and event head

Input parameters:

- `body` (required)
- `path` (object, required)

### `getAgent` (~39 tokens)

Read own workspace, authorizer, scope, expiry and subjectRequirements for new agreements. Preserve these requirements in creation input; required human decisions cannot be automated.

### `getAgentCapabilities` (~21 tokens)

Read supported connection, billing and client capabilities without a credential

### `getAutomationJob` (~25 tokens)

Read current state correlated to the saved submission

Input parameters:

- `path` (object, required)

### `getCreationDocuments` (~23 tokens)

Read current documents before preparing a new agreement; public and read-only

### `getPreparedDraftStatus` (~38 tokens)

Read processing facts for a draft created by this same authorization. No grant to the resulting project is added.

Input parameters:

- `path` (object, required)

### `getProject` (~27 tokens)

Read current state, confirmations, material references and human link

Input parameters:

- `path` (object, required)

### `getProposal` (~27 tokens)

Read scoped proposal, decision readiness and the final project ID

Input parameters:

- `path` (object, required)

### `getRecord` (~23 tokens)

Read historical record plus unsigned compatibility metadata

Input parameters:

- `path` (object, required)

### `getStatus` (~33 tokens)

Read five-minute signed status with caller nonce; not payment authorization

Input parameters:

- `body` (required)
- `path` (object, required)

### `getUsableTemplate` (~41 tokens)

Read an exact available template version; an unavailable version never falls back to the latest.

Input parameters:

- `path` (object, required)
- `query` (object, required)

### `listAutomationJobs` (~24 tokens)

Read jobs for the exact authorized project

Input parameters:

- `query` (object, required)

### `listProjectWebhooks` (~16 tokens)

List this grant’s subscriptions

### `listProposals` (~17 tokens)

Read explicitly scoped supplier and received proposals

### `listUsableTemplates` (~37 tokens)

Read built-in and currently licensed workspace templates. Requires drafting authority and organization-wide parent access. No purchase, adoption, edit or publication.

### `listWebhookDeliveries` (~31 tokens)

Read delivery attempts and version references

Input parameters:

- `path` (object, required)
- `query` (object)

### `prepareTemplate` (~44 tokens)

Bind the exact template version and parameters to the reviewed work, including customizations. Read-only; creation rechecks availability.

Input parameters:

- `body` (required)
- `path` (object, required)

### `previewOperationConfirmation` (~29 tokens)

Preview exact terms and digest; does not record consent or create an agreement

Input parameters:

- `body` (required)

### `useTemplate` (~35 tokens)

Render every template parameter into editable work. Read-only; creates no agreement.

Input parameters:

- `body` (required)
- `path` (object, required)

### `verifyProjectWebhook` (~31 tokens)

Verify exact raw bytes, timestamp and current authorization

Input parameters:

- `body` (required)
- `path` (object, required)

### `searchPublicSpecifications` (~82 tokens)

Find public delivery acceptance templates before asking a user to connect. Search by delivery scenario such as automation, customer support or software. No credential needed. Empty results mean broaden the query; do not invent a matching template. Returned examples are editable starting points, not quality certification or payment proof. Pin the returned version and digest before reuse.

Input parameters:

- `query` (object)

### `getPublicSpecification` (~68 tokens)

Read the exact public template version returned by searchPublicSpecifications. No credential needed. Review scope, completion criteria and required evidence with the user before recommending adoption. This read creates no draft, agreement or acceptance and never grants authority.

Input parameters:

- `path` (object, required)
- `query` (object, required)

## Diagnostics

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

## Score history

- 2026-10-23: 61
- 2026-10-22: 61
- 2026-10-21: 61
- 2026-10-20: 61
- 2026-10-19: 61
- 2026-10-18: 61
- 2026-10-17: 61

## Common questions

### What is the Prooftask MCP server?

Prooftask is an MCP server listed in the public MCP registry as io.github.cognitive-emergence/prooftask. Free public n8n, AI support and software acceptance templates; scoped private delivery workflows. This page covers its npm package (prooftask-mcp).

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

Prooftask scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. It declares no install or post-install scripts. 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 Prooftask MCP server expose?

Prooftask exposes 23 tools: exportLegacyRecord, exportResultPackage, getAgent, getAgentCapabilities, getAutomationJob, and 18 more. Their descriptions and schemas cost roughly 775 tokens of context every time the server is loaded.

### Is the Prooftask MCP server still maintained?

Prooftask is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- npm package: https://www.npmjs.com/package/prooftask-mcp
- Socket report: https://socket.dev/npm/package/prooftask-mcp
- Repository: https://github.com/cognitive-emergence/prooftask-integrations
- Website: https://prooftask.com/developers
- Changelog RSS feed: https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-mcp.json
- HTML version of this page: https://verifymcp.io/servers/cognitive-emergence-prooftask/prooftask-mcp