# io.github.AINative-Studio/ainative-prd-mcp (npm · ainative-prd-mcp)

PRD Generator MCP — generate, validate, and manage Product Requirement Documents.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `ainative-prd-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/ainative-studio-ainative-prd-mcp/ainative-prd-mcp.md), [page](https://verifymcp.io/servers/ainative-studio-ainative-prd-mcp/ainative-prd-mcp)

## Channel facts

- Registry: `npm`
- Package: `ainative-prd-mcp`
- Version: `1.1.1`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (108 of 109), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (108 of 109), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2045 tokens (~88/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**: 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.
- **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

### Claude

```bash
claude mcp add ainative-studio-ainative-prd-mcp -- npx -y ainative-prd-mcp
```

### Codex

```bash
codex mcp add ainative-studio-ainative-prd-mcp -- npx -y ainative-prd-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ainative-studio-ainative-prd-mcp --command npx --arg -y --arg ainative-prd-mcp
```

### Hermes

```yaml
mcp_servers:
  ainative-studio-ainative-prd-mcp:
    command: "npx"
    args: ["-y", "ainative-prd-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "ainative-studio-ainative-prd-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ainative-prd-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.

### 2026-08-02 (score 64, +43)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 21)

First indexed and scored.

## MCP tools (23)

### `prd_generate` (~230 tokens)

Generate a comprehensive Product Requirements Document (PRD) for an AINative feature, integration, or product. Uses AI with full AINative platform context — knows all services, APIs, SDKs, and architectural constraints. The PRD is automatically saved to ZeroMemory for cross-session recall.

Input parameters:

- `additional_context` (string): Any additional context, links, or requirements
- `ainative_services` (array): AINative services this feature will use (e.g., ["ZeroDB", "ZeroMemory", "Agent Cloud"]). If omitted, the generator will auto-detect relevant services.
- `constraints` (array): Technical or business constraints
- `core_features` (array, required): List of core features to include
- `description` (string, required): Detailed description of what needs to be built
- `issue_number` (integer): Optional GitHub issue number to link to
- `product_name` (string, required): Name of the product or feature
- `target_audience` (string, required): Who will use this product/feature
- `template` (string): PRD template to use (default: standard)

### `prd_generate_section` (~136 tokens)

Generate or regenerate a single section of a PRD. Useful for iterative refinement — update just the Technical Architecture or User Stories without regenerating the entire document.

Input parameters:

- `context` (string): Additional context for generating this section
- `description` (string): Product description (required if no prd_id)
- `prd_id` (string): ID of an existing saved PRD (from prd_save). If provided, the section will be generated in context of the full PRD.
- `product_name` (string): Product name (required if no prd_id)
- `section_name` (string, required): Which section to generate

### `prd_refine` (~109 tokens)

Refine an existing PRD based on feedback. Provide the PRD ID and feedback, and the AI will update the document while preserving version history.

Input parameters:

- `feedback` (string, required): Feedback describing what needs to change (e.g., "Add more detail to user stories", "The API design should use WebSockets instead of polling")
- `prd_id` (string, required): ID of the saved PRD to refine
- `sections_to_update` (array): Optional: limit refinement to specific sections

### `prd_from_issue` (~87 tokens)

Generate a PRD from a GitHub issue. Fetches the issue title, body, labels, and comments, then expands them into a full PRD with AINative platform context.

Input parameters:

- `issue_number` (integer, required): GitHub issue number
- `repo` (string): GitHub repository (owner/repo format)
- `template` (string): PRD template to use

### `prd_list_templates` (~56 tokens)

List all available PRD templates (built-in and custom). Each template has a specific structure optimized for different types of products and features.

Input parameters:

- `include_custom` (boolean): Include custom templates stored in ZeroDB (default: true)

### `prd_get_template` (~52 tokens)

Get a PRD template by name. Returns the full Markdown template with placeholder variables.

Input parameters:

- `name` (string, required): Template name (e.g., "standard", "ainative-feature", "agent-capability")

### `prd_create_template` (~89 tokens)

Create a custom PRD template. Stored persistently in ZeroDB so it survives across sessions.

Input parameters:

- `content` (string, required): Markdown template content with {{PLACEHOLDER}} variables
- `description` (string, required): What this template is for
- `name` (string, required): Template name (lowercase, hyphens allowed)
- `sections` (array): List of section names in this template

### `prd_render_template` (~73 tokens)

Render a template with variable substitution (no AI, pure placeholder replacement). Fast and deterministic.

Input parameters:

- `template_name` (string, required): Template to render
- `variables` (object, required): Key-value pairs for placeholder substitution (e.g., {"PRODUCT_NAME": "My Feature", "TARGET_AUDIENCE": "Developers"})

### `prd_validate` (~99 tokens)

Validate a PRD against quality rules and AINative architectural constraints. Checks for required sections, content completeness, AINative service references, and architecture compliance.

Input parameters:

- `content` (string): PRD content in Markdown (provide directly or use prd_id)
- `prd_id` (string): ID of a saved PRD to validate
- `strict` (boolean): Strict mode: also check AINative-specific rules (default: true)

### `prd_score` (~63 tokens)

Score a PRD completeness from 0-100 based on section coverage, content quality, and AINative integration depth.

Input parameters:

- `content` (string): PRD content in Markdown
- `prd_id` (string): ID of a saved PRD to score

### `prd_check_api_refs` (~69 tokens)

Verify that all API endpoint references in a PRD actually exist in the AINative OpenAPI spec. Catches typos and invalid paths.

Input parameters:

- `content` (string): PRD content to check
- `prd_id` (string): ID of a saved PRD to check

### `prd_save` (~112 tokens)

Save a PRD to ZeroDB as a persistent plan artifact. Returns an ID you can use to load, update, or search for it in future sessions. Version history is tracked automatically on every update.

Input parameters:

- `content` (string, required): Full PRD content in Markdown
- `tags` (array): Tags for categorization (e.g., ["billing", "agent-cloud", "q3-2026"])
- `title` (string, required): PRD title (e.g., "PRD: Agent Cloud Billing")

### `prd_load` (~55 tokens)

Load a saved PRD by its artifact ID. Use at the start of a session to resume work on an existing PRD.

Input parameters:

- `prd_id` (string, required): Artifact ID returned by prd_save or prd_generate

### `prd_search` (~83 tokens)

Semantic search across all saved PRDs. Find PRDs by topic, service name, feature description, or any natural language query.

Input parameters:

- `limit` (integer): Maximum results to return
- `query` (string, required): Natural language search query (e.g., "PRDs about agent billing", "streaming video features")
- `tags` (array): Filter by tags

### `prd_history` (~46 tokens)

Get version history for a PRD, showing how it evolved over time. Returns unified diffs between versions.

Input parameters:

- `prd_id` (string, required): Artifact ID of the PRD

### `prd_list_services` (~98 tokens)

List all AINative products and services with descriptions, categories, API prefixes, SDKs, and pricing tiers. Use this before writing a PRD to understand what platform capabilities are available.

Input parameters:

- `category` (string): Filter by category (e.g., "Data Platform", "AI Inference", "Business", "Infrastructure")
- `verbose` (boolean): Include full details including features, SDKs, and endpoints (default: false)

### `prd_get_api_catalog` (~78 tokens)

Get API endpoint details for a specific AINative service or category. Returns endpoint paths, methods, and descriptions from the OpenAPI catalog.

Input parameters:

- `service` (string, required): Service name (e.g., "ZeroDB", "ZeroMemory", "Agent Cloud") or API prefix (e.g., "/api/v1/zerodb")

### `prd_suggest_stack` (~94 tokens)

Given a set of requirements, suggest which AINative services, APIs, and SDKs to use. Returns a recommended technology stack with justifications.

Input parameters:

- `constraints` (array): Technical constraints (e.g., "must work offline", "real-time updates needed")
- `features` (array): List of required features/capabilities
- `requirements` (string, required): Natural language description of what you need to build

### `skill_list` (~95 tokens)

List all Agent Skills available in the skills repo (the8genc/ai-8gent-skills by default). Each entry includes the skill name, slug, description (with trigger phrases), and its reference files. Skills are pulled live from GitHub. Call this first to discover which skills exist before applying one.

Input parameters:

- `refresh` (boolean): Bypass the in-memory cache and re-fetch from GitHub (default: false)

### `skill_get` (~90 tokens)

Get the full content of a skill by slug or name, including its SKILL.md body and (optionally) all reference files. Use this to load a skill before doing the work it describes.

Input parameters:

- `skill` (string, required): Skill slug or name (e.g., "agentic-platform-builder")
- `with_references` (boolean): Also fetch the full content of every reference file (default: false)

### `skill_get_reference` (~78 tokens)

Get a single reference file for a skill (e.g., "references/testing-patterns.md"). Load reference files on demand when the SKILL.md says to.

Input parameters:

- `reference` (string, required): Reference file path, e.g. "references/agent-patterns.md" or "agent-patterns.md"
- `skill` (string, required): Skill slug

### `skill_search` (~80 tokens)

Semantic search across all skills to find the right one for a task. Queries the ZeroDB mirror when available (run skill_sync first), otherwise falls back to keyword matching over the live GitHub list.

Input parameters:

- `limit` (integer): Max results
- `query` (string, required): Natural language description of the task (e.g., "automate my content workflow")

### `skill_sync` (~73 tokens)

Mirror skills from the GitHub repo into ZeroDB so they can be semantically searched and served offline. GitHub remains the source of truth — this refreshes the cache. Sync all skills, or one by slug.

Input parameters:

- `skill` (string): Optional: sync only this skill slug. Omit to sync all skills.

## Diagnostics

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

## Score history

- 2026-08-03: 64
- 2026-08-02: 64
- 2026-08-01: 21

## Links

- npm package: https://www.npmjs.com/package/ainative-prd-mcp
- Socket report: https://socket.dev/npm/package/ainative-prd-mcp
- Repository: https://github.com/AINative-Studio/ainative-prd-mcp
- Changelog RSS feed: https://verifymcp.io/servers/ainative-studio-ainative-prd-mcp/ainative-prd-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ainative-studio-ainative-prd-mcp/ainative-prd-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ainative-studio-ainative-prd-mcp/ainative-prd-mcp