# io.github.intenttext/intenttext-mcp (npm · @intenttext/mcp-server)

Parse, validate, query, and render IntentText (.it) documents for AI agents

- Trust score: 64/100 (medium)
- Change this week: +46
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

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

## Channel facts

- Registry: `npm`
- Package: `@intenttext/mcp-server`
- Version: `1.0.1`
- 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 (106 of 110), 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 (106 of 110), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 143 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 724 tokens (~80/item across 9 items; 9 tools + 0 resources), lean.
  - 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add intenttext-intenttext-mcp -- npx -y @intenttext/mcp-server
```

### Codex

```bash
codex mcp add intenttext-intenttext-mcp -- npx -y @intenttext/mcp-server
```

### opencode

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

### OpenClaw

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

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "intenttext-intenttext-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@intenttext/mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 64, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 60, +60)

- [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] Schema quality: unverified → excellent
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 0, −2)

- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 2, −20)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 22, +4)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 18)

First indexed and scored.

## MCP tools (9)

### `parse_intent_text` (~90 tokens)

Parse an IntentText (.it) source string into a structured JSON document. Returns the complete document with metadata and typed blocks array. Use this when you have raw .it text and need to inspect or process its structure.

Input parameters:

- `safe` (boolean): If true, never throw — returns warnings instead of errors. Default: true
- `source` (string, required): The IntentText source string to parse

### `render_html` (~44 tokens)

Render an IntentText source string to styled HTML. Returns a complete HTML string ready to display in a browser.

Input parameters:

- `source` (string, required): IntentText source string (.it format)

### `render_print` (~50 tokens)

Render an IntentText document to print-optimised HTML with @media print CSS. Applies font: and page: block settings. Suitable for PDF generation.

Input parameters:

- `source` (string, required): IntentText source string

### `merge_template` (~99 tokens)

Merge an IntentText template (containing {{variable}} placeholders) with a data object. Returns the merged .it source with all variables resolved. Use this to generate documents from templates.

Input parameters:

- `data` (object, required): JSON object with values to substitute into the template
- `render` (string): Optionally render the merged result. Default: none (returns .it source)
- `template` (string, required): IntentText template source with {{variable}} placeholders

### `validate_document` (~72 tokens)

Validate an IntentText document for semantic correctness beyond syntax. Checks for broken step references, missing required properties, unresolved variables, and workflow logic errors. Returns a list of errors and warnings. Always call this after generating a workflow document to catch issues before execution.

Input parameters:

- `source` (string, required): IntentText source string to validate

### `query_document` (~149 tokens)

Query an IntentText document for specific blocks by type, content, or properties. Returns matching blocks as JSON. Use this to extract tasks, steps, decisions, or any other block type from a document.

Input parameters:

- `content` (string): Substring to search for in block content (case-insensitive)
- `limit` (number): Maximum number of results to return
- `section` (string): Only return blocks within this section (substring match on section title)
- `source` (string, required): IntentText source string
- `type` (string): Block type to filter by (e.g. 'task', 'step', 'gate'). Comma-separated for multiple types: 'step,gate,decision'

### `diff_documents` (~76 tokens)

Compare two versions of an IntentText document and return a semantic diff. Shows which blocks were added, removed, or modified between versions. More meaningful than a line diff — tells you what changed in the document's structure.

Input parameters:

- `after` (string, required): The updated IntentText source
- `before` (string, required): The original IntentText source

### `document_to_source` (~73 tokens)

Convert an IntentText JSON document back to .it source format. Use this when you have a document stored as JSON (e.g. from a database) and need to display or edit it as .it text.

Input parameters:

- `document` (object, required): An IntentText document JSON object (as produced by parse_intent_text)

### `extract_workflow` (~71 tokens)

Extract the execution graph from an IntentText workflow document. Returns steps in topological order, dependency relationships, parallel batches, and gate positions. Use this to understand how to execute a workflow before running it.

Input parameters:

- `source` (string, required): IntentText source containing workflow blocks (step:, decision:, gate:, etc.)

## Diagnostics

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

## Score history

- 2026-08-03: 64
- 2026-08-02: 60
- 2026-08-01: 0
- 2026-07-31: 2
- 2026-07-30: 22
- 2026-07-28: 18
- 2026-07-27: 18

## Links

- npm package: https://www.npmjs.com/package/@intenttext/mcp-server
- Socket report: https://socket.dev/npm/package/@intenttext/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/intenttext-intenttext-mcp/intenttext-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/intenttext-intenttext-mcp/intenttext-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/intenttext-intenttext-mcp/intenttext-mcp-server