# @doquflow/cli

Source: https://glimind.com/server/npm%2F-doquflow%2Fcli
Registry id: `npm/-doquflow/cli`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "doquflow-cli": {
      "command": "npx",
      "args": [
        "-y",
        "@doquflow/cli"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add doquflow-cli -- npx -y @doquflow/cli
```

## Tools (19)

- `context`: Context-as-a-Service tool. Persistent local SQLite index using FTS5 (lexical) and sqlite-vec (semantic) search. Use 'index' operation first, then 'query'. Suppo
- `detect_drift`: Compare a documentation page against its source code files to identify discrepancies, stale facts, or contradictions.
- `generate_dependency_graph`: Scan a project and build a dependency graph showing how modules import each other, which DB tables are shared, and which files are most connected. Returns nodes
- `get_schema_guidance`: Analyze what documents should exist based on project schema and current wiki. Removes decision fatigue by suggesting what to create next.
- `ingest_source`: Ingest a markdown source document from .docuflow/sources/ and generate wiki pages (entities, concepts) with cross-references. Returns pages created and entities
- `lint_wiki`: Health check wiki for quality issues: orphan pages, broken references, stale content, metadata gaps, and contradictions. Returns issues found, metrics, health s
- `list_modules`: Walk a project directory and return extracted facts for every non-binary file. Skips node_modules, dist, build, .git, vendor, obj, bin, .docuflow, *.min.js, *.m
- `list_wiki`: List all wiki pages in .docuflow/wiki/, optionally filtered by category. Returns metadata (title, created_at, sources, tags, stale) and page counts by category.
- `preview_generation`: Preview what a tool will generate before running it. Removes black-box feeling by showing predicted actions, outputs, and impact.
- `query_project`: Ask a question against both the wiki and the source code. Synthesizes an answer with specific citations from both docs and code files.
- `query_wiki`: Ask a question against the wiki. Automatically searches for relevant pages, synthesizes an answer, and returns source pages with confidence score. One-stop tool
- `read_module`: Read a single source file, detect its language, and extract classes, functions, dependencies, DB tables, endpoints, and config references. Returns raw content t
- `read_specs`: Read previously written specs from <project_path>/.docuflow/specs/. Optionally filter by module name.
- `regenerate_doc`: Rewrite a stale document so that its facts perfectly match the provided source code, while preserving original structure.
- `save_answer_as_page`: Save a generated answer as a new wiki page. Allows query results to compound back into the knowledge base, growing the wiki with new synthesis pages. Automatica
- `synthesize_answer`: Generate a synthesis answer from multiple wiki pages. Extracts relevant sentences, key concepts, and builds a markdown answer with citations.
- `update_index`: Scan all wiki pages in .docuflow/wiki/ and regenerate .docuflow/index.md organized by category. Appends operation to log.md.
- `wiki_search`: Search the wiki for pages matching a query using relevance scoring. Returns ranked results with preview snippets and matched terms. BM25-inspired ranking weight
- `write_spec`: Write a markdown spec file to <project_path>/.docuflow/specs/<filename>.md and update the index. The agent provides the full markdown content.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
