Documentation MCP Server

Overview Schema Source Related Servers Discussions Admin

docs_generate_api

Generate API documentation from code comments like JSDoc and docstrings by providing project path, output path, and language. Supports TypeScript, JavaScript, Python, Go, Rust, Java, and C#.

Instructions

Generate API documentation from code (JSDoc, Docstrings, etc.)

Input Schema

TableJSON Schema

Name	Required	Description
`projectPath`	Yes	Path to the project source code
`outputPath`	Yes	Output path for API documentation
`language`	Yes	Programming language

Implementation Reference

src/index.ts:13-13 (registration)
Imports the generateApi handler function from the tools module
```
import { generateApi } from "./tools/generateApi.js";
```

src/index.ts:111-132 (schema)

Tool registration with name 'docs_generate_api' and inputSchema (projectPath, outputPath, language)

  name: "docs_generate_api",
  description: "Generate API documentation from code (JSDoc, Docstrings, etc.)",
  inputSchema: {
    type: "object",
    properties: {
      projectPath: {
        type: "string",
        description: "Path to the project source code",
      },
      outputPath: {
        type: "string",
        description: "Output path for API documentation",
      },
      language: {
        type: "string",
        description: "Programming language",
        enum: ["typescript", "javascript", "python", "go", "rust", "java", "csharp"],
      },
    },
    required: ["projectPath", "outputPath", "language"],
  },
},

src/tools/generateApi.ts:7-81 (handler)

Main handler function that generates API documentation instructions based on language

export async function generateApi(args: any) {
  const { projectPath, outputPath, language } = args as GenerateApiArgs;

  const instructions: Record<string, string> = {
    typescript: `📖 TypeScript API Documentation:

1. Install TypeDoc:
   npm install --save-dev typedoc

2. Generate API docs:
   npx typedoc --out ${outputPath} ${projectPath}

3. For integration with Docusaurus:
   npm install --save-dev docusaurus-plugin-typedoc`,
    javascript: `📖 JavaScript API Documentation:

1. Install JSDoc:
   npm install --save-dev jsdoc

2. Generate API docs:
   npx jsdoc -c jsdoc.json -d ${outputPath} ${projectPath}

3. Use JSDoc comments:
   /**
    * Description
    * @param {string} param - Parameter description
    * @returns {Promise<void>}
    */`,
    python: `📖 Python API Documentation:

1. For Sphinx:
   pip install sphinx sphinx-autodoc

2. Generate API docs:
   sphinx-apidoc -o ${outputPath} ${projectPath}

3. For MkDocs:
   pip install mkdocstrings mkdocstrings-python
   
   Add to mkdocs.yml:
   plugins:
     - mkdocstrings:
         handlers:
           python:
             options:
               docstring_style: google`,
    go: `📖 Go API Documentation:

1. Use godoc:
   godoc -http=:6060

2. Or generate static docs:
   go doc -all > ${outputPath}/api.md`,
    rust: `📖 Rust API Documentation:

1. Generate docs:
   cargo doc --no-deps

2. Open in browser:
   cargo doc --no-deps --open

3. Output is in target/doc`,
  };

  const instruction = instructions[language] || "Language not supported for API generation";

  return {
    content: [
      {
        type: "text",
        text: instruction,
      },
    ],
  };
}

src/tools/generateApi.ts:1-5 (schema)
TypeScript interface defining the arguments (projectPath, outputPath, language)
```
interface GenerateApiArgs {
  projectPath: string;
  outputPath: string;
  language: string;
}
```
src/index.ts:306-307 (registration)
Routes the 'docs_generate_api' tool name to the generateApi handler
```
case "docs_generate_api":
  return await generateApi(args);
```

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Dec 12, 2025

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not clarify behavioral traits like whether the tool modifies project files, requires specific permissions, or produces a specific output format. The mention of 'from code' implies a read-only analysis but the outputPath parameter suggests writing, which is not explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the core purpose. It avoids unnecessary words, but could include a bit more detail without harming conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With three required parameters, no output schema, and no annotations, the description is insufficiently complete. It does not explain what format the documentation is generated in (e.g., HTML, Markdown), where it is written, or how to interpret the output. The agent would lack enough information to use the tool correctly without external knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all three required parameters, each with a clear purpose. The description adds no additional meaning beyond what the schema already provides, achieving the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates API documentation from code comments like JSDoc or Docstrings, using a specific verb 'generate' and resource 'API documentation'. However, it does not differentiate from the sibling tool docs_generate_openapi, which also generates API documentation but specifically for OpenAPI.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as docs_generate_openapi or docs_analyze_project. It lacks context about prerequisites, when not to use, or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server