# ProvenTools (npm · @proventools/mcp)

Read-only ProvenTools business ideas, evidence, build prompts, and validation reports.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-16

## Components

- npm · `@proventools/mcp`: 73/100 (this document), [markdown](https://verifymcp.io/servers/proventools-proventools/proventools-mcp.md), [page](https://verifymcp.io/servers/proventools-proventools/proventools-mcp)

## Channel facts

- Registry: `npm`
- Package: `@proventools/mcp`
- Version: `0.1.0-beta.3`
- 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 2026-08-16.

- **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**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to proventools/agent-clients).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1019 tokens (~84/item across 12 items; 12 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**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 27% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; 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

### Claude

```bash
claude mcp add proventools-proventools -- npx -y @proventools/mcp
```

### Codex

```bash
codex mcp add proventools-proventools -- npx -y @proventools/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add proventools-proventools --command npx --arg -y --arg @proventools/mcp
```

### Hermes

```yaml
mcp_servers:
  proventools-proventools:
    command: "npx"
    args: ["-y", "@proventools/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "proventools-proventools": {
      "command": "npx",
      "args": [
        "-y",
        "@proventools/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.

### 2026-08-12 (score 73, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-11 (score 58)

First indexed and scored.

## MCP tools (12)

### `search_ideas` (~75 tokens)

Search and filter the ProvenTools curated idea library. Credit cost: 0. Reads stored ProvenTools data only.

Input parameters:

- `category` (string): Exact category name.
- `difficulty` (string): Easy, Medium, or Hard.
- `page` (integer): Results page.
- `query` (string): Words to search for.

### `get_idea` (~48 tokens)

Get the full read-only breakdown for one curated idea. Credit cost: 0. Reads stored ProvenTools data only.

Input parameters:

- `id` (string, required): The idea id returned by search_ideas.

### `get_build_prompt` (~48 tokens)

Get the agent-ready build prompt for one curated idea. Credit cost: 0. Reads stored ProvenTools data only.

Input parameters:

- `id` (string, required): The idea id returned by search_ideas.

### `whats_new` (~30 tokens)

See the latest ProvenTools monthly idea drop. Credit cost: 0. Reads stored ProvenTools data only.

### `get_idea_evidence` (~75 tokens)

Get the latest stored evidence and ProvenScore history for one idea. This never starts live research. Credit cost: 0. Reads stored ProvenTools data only.

Input parameters:

- `historyLimit` (integer): Maximum score snapshots to return (default 12).
- `id` (string, required): The idea id returned by search_ideas.

### `get_validation_report` (~51 tokens)

Get the current status or stored result for one of your validation jobs. Credit cost: 0. Reads stored ProvenTools data only.

Input parameters:

- `id` (string, required): A validation id from your ProvenTools account.

### `get_credit_balance` (~34 tokens)

Get Live credit balances, expiry, usage, and activity. Credit cost: 0. Reads stored ProvenTools data only.

### `recommend_ideas` (~156 tokens)

Recommend stored ideas using structured filters plus semantic retrieval. Credit cost: 0. Depending on server configuration, ProvenTools may send any natural-language input and selected stored idea fields to OpenAI for semantic retrieval and bounded answer synthesis; otherwise it uses PostgreSQL retrieval and deterministic text.

Input parameters:

- `confidence` (array)
- `difficulties` (array)
- `limit` (integer)
- `maximumBudgetUsd` (number)
- `maximumBuildWeeks` (number)
- `maximumScore` (number)
- `minimumScore` (number)
- `opportunityTypes` (array)
- `platforms` (array)
- `query` (string, required): What you want to build or compare.
- `validationStates` (array)

### `shortlist_ideas` (~154 tokens)

Create a ranked shortlist from stored ideas. Credit cost: 0. Depending on server configuration, ProvenTools may send any natural-language input and selected stored idea fields to OpenAI for semantic retrieval and bounded answer synthesis; otherwise it uses PostgreSQL retrieval and deterministic text.

Input parameters:

- `confidence` (array)
- `difficulties` (array)
- `limit` (integer)
- `maximumBudgetUsd` (number)
- `maximumBuildWeeks` (number)
- `maximumScore` (number)
- `minimumScore` (number)
- `opportunityTypes` (array)
- `platforms` (array)
- `query` (string, required): What you want to build or compare.
- `validationStates` (array)

### `discover_ideas` (~155 tokens)

Discover stored ideas from a natural-language brief. Credit cost: 0. Depending on server configuration, ProvenTools may send any natural-language input and selected stored idea fields to OpenAI for semantic retrieval and bounded answer synthesis; otherwise it uses PostgreSQL retrieval and deterministic text.

Input parameters:

- `confidence` (array)
- `difficulties` (array)
- `limit` (integer)
- `maximumBudgetUsd` (number)
- `maximumBuildWeeks` (number)
- `maximumScore` (number)
- `minimumScore` (number)
- `opportunityTypes` (array)
- `platforms` (array)
- `query` (string, required): What you want to build or compare.
- `validationStates` (array)

### `compare_ideas` (~80 tokens)

Compare two to ten stored ideas and their ProvenScores. Credit cost: 0. Depending on server configuration, ProvenTools may send any natural-language input and selected stored idea fields to OpenAI for semantic retrieval and bounded answer synthesis; otherwise it uses PostgreSQL retrieval and deterministic text.

Input parameters:

- `ideaIds` (array, required)
- `query` (string)

### `explain_idea_score` (~72 tokens)

Explain one stored ProvenScore and its subscores. Credit cost: 0. Depending on server configuration, ProvenTools may send any natural-language input and selected stored idea fields to OpenAI for semantic retrieval and bounded answer synthesis; otherwise it uses PostgreSQL retrieval and deterministic text.

Input parameters:

- `id` (string, required)

## Diagnostics

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

## Score history

- 2026-08-16: 73
- 2026-08-15: 73
- 2026-08-14: 73
- 2026-08-13: 73
- 2026-08-12: 73
- 2026-08-11: 58

## Links

- npm package: https://www.npmjs.com/package/@proventools/mcp
- Socket report: https://socket.dev/npm/package/@proventools/mcp
- Repository: https://github.com/proventools/agent-clients
- Changelog RSS feed: https://verifymcp.io/servers/proventools-proventools/proventools-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/proventools-proventools/proventools-mcp.json
- HTML version of this page: https://verifymcp.io/servers/proventools-proventools/proventools-mcp