Spec MCP Server

Overview Schema Related Servers Score Discussions

Generate Codebase Analysis Documents

generate-codebase-analysis

Analyze codebases to generate foundational documentation including product features, technology stack, and project structure analysis in .spec/steering/ directory, with optional regeneration control.

Instructions

Analyzes codebase and generates three foundational analysis documents: product.md, tech.md, and structure.md in .spec/steering/ directory. These documents provide comprehensive analysis of the product features, technology stack, and project structure. Checks if files already exist and skips generation unless force_regenerate is true.

Input Schema

TableJSON Schema

Name	Required	Description
`additional_context`	No	Additional context about the project
`force_regenerate`	No	Force regeneration even if files exist (default: false)
`project_path`	No	Path to the project directory (defaults to current directory)

Implementation Reference

src/server.ts:30-228 (handler)

The handler function constructs a comprehensive prompt that instructs an AI agent to analyze the codebase and generate three markdown documents (product.md, tech.md, structure.md) in the .spec/steering/ directory. It includes checks for existing files unless force_regenerate is true, and provides detailed templates and execution steps for file creation using filesystem tools.

  async ({ project_path = '.', additional_context, force_regenerate = false }) => {
    const prompt = `# ⚠️ IMPORTANT: YOU MUST EXECUTE THE FOLLOWING ACTIONS

This MCP tool provides instructions that YOU (the AI assistant) must execute using your available file system tools.
**DO NOT** just report success - you MUST actually create the files using Write or MultiEdit tools.

# Generate Steering Documents for ${project_path}

## PREREQUISITE: CHECK IF FILES ALREADY EXIST
${!force_regenerate ? `
IMPORTANT: Before generating new files, FIRST check if steering documents already exist:
1. **USE Read tool** to check if file exists: ${project_path}/.spec/steering/product.md
2. **USE Read tool** to check if file exists: ${project_path}/.spec/steering/tech.md
3. **USE Read tool** to check if file exists: ${project_path}/.spec/steering/structure.md

If ALL THREE files already exist:
- STOP HERE and return: "✅ Steering documents already exist at ${project_path}/.spec/steering/. No regeneration needed. Use force_regenerate=true to regenerate."
- Do NOT proceed with generation

If ANY files are missing, proceed with generation below.
` : 'FORCE REGENERATE MODE: Regenerating all steering documents even if they exist.'}

You MUST create THREE separate steering documents that match exact structure and content approach.

## 🔴 CRITICAL: YOU MUST CREATE THE FILES - NOT JUST REPORT SUCCESS
### File Creation Instructions:
1. **USE Bash tool** to create directory: mkdir -p ${project_path}/.spec/steering/
2. **USE Write tool** to create THREE separate files with exact filenames:
   - ${project_path}/.spec/steering/product.md
   - ${project_path}/.spec/steering/tech.md
   - ${project_path}/.spec/steering/structure.md
3. **USE Read tool** to verify each file exists after creation

⚠️ The files MUST be physically created on the filesystem. Do NOT proceed without using the Write tool.

## DOCUMENT SPECIFICATIONS:

### 1. PRODUCT.MD - Product Overview
Create ${project_path}/.spec/steering/product.md with:

# Product Overview

## Purpose
[Analyze the codebase and describe what this product/application does]

## Target Users
- [Primary user type]: [Their needs and use cases]
- [Secondary user type]: [Their needs and use cases]

## Key Features
- [Feature 1]: [Description based on codebase analysis]
- [Feature 2]: [Description based on codebase analysis]
- [Feature 3]: [Description based on codebase analysis]

## Business Objectives
- [Objective 1 derived from codebase context]
- [Objective 2 derived from codebase context]

## Product Context
[Additional context about the product's market, competition, or unique value proposition]

---

### 2. TECH.MD - Technology Stack
Create ${project_path}/.spec/steering/tech.md with:

# Technology Stack

## Core Technologies
- **Primary Language**: [Language and version from package.json/requirements/etc]
- **Framework**: [Main framework detected]
- **Runtime**: [Node.js, Python, .NET, etc. with version]
- **Database**: [Database system if detected]

## Development Tools
- **Package Manager**: [npm, yarn, pip, maven, cargo, dotnet, etc.]
- **Build System**: [webpack, vite, gradle, maven, cargo, msbuild, etc.]
- **Testing Framework**: [jest, pytest, junit, nunit, go test, etc.]
- **Linter/Formatter**: [eslint, prettier, black, checkstyle, clippy, etc.]

## Build and Test Commands
[Auto-detect from project configuration files and scripts]

### Essential Commands
- **Install Dependencies**: [e.g., npm install, pip install -r requirements.txt, dotnet restore]
- **Build Project**: [e.g., npm run build, mvn compile, cargo build, dotnet build]
- **Run Tests**: [e.g., npm test, pytest, mvn test, dotnet test, go test ./...]
- **Lint/Format Check**: [e.g., npm run lint, ruff check, gradle checkstyle, cargo clippy]
- **Type Check**: [e.g., tsc --noEmit, mypy, if applicable]
- **Start Development**: [e.g., npm run dev, python app.py, dotnet run]
- **Production Build**: [e.g., npm run build:prod, mvn package, cargo build --release]

### Project-Specific Commands
[Any custom commands specific to this project from package.json, Makefile, etc.]

## Libraries and Dependencies
### Required Libraries
[List key dependencies from package.json/requirements with purpose]
- [Library]: [Version] - [Purpose]

### Preferred Libraries
[Document preferred libraries for common tasks]
- UI Components: [Library preference]
- State Management: [Library preference]
- HTTP Client: [Library preference]

## Development Guidelines
- Variable naming: [Convention detected from codebase]
- Function naming: [Convention detected from codebase]
- File naming: [Convention detected from codebase]
- Code style: [Style detected from config files]

## Performance Requirements
[Any performance considerations detected or inferred]

## Security Requirements
[Any security patterns or requirements detected]

## Technical Constraints
[Any constraints detected from the codebase]

---

### 3. STRUCTURE.MD - Project Structure
Create ${project_path}/.spec/steering/structure.md with:

# Project Structure

## Directory Organization
\`\`\`
[Generate actual directory tree from the project]
\`\`\`

## File Naming Conventions
- Components: [Pattern detected from codebase]
- Services: [Pattern detected from codebase]
- Types: [Pattern detected from codebase]
- Tests: [Pattern detected from codebase]

## Import Patterns
- Relative imports: [Rules detected from codebase]
- Absolute imports: [Rules detected from codebase]
- External dependencies: [Patterns detected]

## Code Organization
- [Organizational principle 1 detected]
- [Organizational principle 2 detected]
- [Index file strategy if detected]

## Architectural Patterns
- [Pattern 1]: [Description of how it's implemented]
- [Pattern 2]: [Description of how it's implemented]

## Testing Structure
- Unit tests: [Location pattern]
- Integration tests: [Location pattern if exists]
- Test naming: [Convention detected]

## Configuration Files
[List and explain key config files: .env, config/, etc.]

${additional_context ? `\n## Additional Context\n${additional_context}` : ''}

---

## 🔴 EXECUTION STEPS - YOU MUST FOLLOW EXACTLY:
1. Analyze the codebase at: ${project_path} using Read, Grep, and Glob tools
   - **IMPORTANT**: Check package.json, pom.xml, build.gradle, Cargo.toml, go.mod, requirements.txt, *.csproj, Makefile, etc.
   - Extract actual build/test/lint commands from these files
   - Look for CI configuration files (.github/workflows, .gitlab-ci.yml, Jenkinsfile, etc.)
2. **USE Bash tool** to create directory: mkdir -p ${project_path}/.spec/steering/
3. **USE Write tool** to create product.md with product overview and business context
4. **USE Write tool** to create tech.md with comprehensive technology stack analysis
   - **CRITICAL**: In the "Build and Test Commands" section, document ACTUAL commands found in the project
   - Do not use placeholder text like "[e.g., npm test]" - use the real commands from package.json scripts or build files
5. **USE Write tool** to create structure.md with detailed project organization
6. **USE Read tool** to verify all three files exist and contain expected content:
   - ${project_path}/.spec/steering/product.md
   - ${project_path}/.spec/steering/tech.md
   - ${project_path}/.spec/steering/structure.md

## SUCCESS CRITERIA:
✅ Three separate markdown files PHYSICALLY CREATED on filesystem (not just reported)
✅ Files verified to exist using Read tool
✅ Each file follows content structure exactly
✅ All content derived from actual codebase analysis
✅ Files ready for use with generate-tasks tool

⚠️ FINAL REMINDER: You MUST use Write tool to create the files. Do not just say they were created.

These files should be automatically included in every AI interaction.`;

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

src/server.ts:21-28 (schema)

Tool metadata including title, description, and Zod input schema defining optional parameters: project_path, additional_context, force_regenerate.

{
  title: 'Generate Codebase Analysis Documents',
  description: 'Analyzes codebase and generates three foundational analysis documents: product.md, tech.md, and structure.md in .spec/steering/ directory. These documents provide comprehensive analysis of the product features, technology stack, and project structure. Checks if files already exist and skips generation unless force_regenerate is true.',
  inputSchema: {
    project_path: z.string().optional().describe("Path to the project directory (defaults to current directory)"),
    additional_context: z.string().optional().describe("Additional context about the project"),
    force_regenerate: z.boolean().optional().describe("Force regeneration even if files exist (default: false)")
  }

src/server.ts:19-229 (registration)

Registers the 'generate-codebase-analysis' tool with the MCP server using server.registerTool, providing the tool name, schema/metadata, and inline handler function.

server.registerTool(
  'generate-codebase-analysis',
  {
    title: 'Generate Codebase Analysis Documents',
    description: 'Analyzes codebase and generates three foundational analysis documents: product.md, tech.md, and structure.md in .spec/steering/ directory. These documents provide comprehensive analysis of the product features, technology stack, and project structure. Checks if files already exist and skips generation unless force_regenerate is true.',
    inputSchema: {
      project_path: z.string().optional().describe("Path to the project directory (defaults to current directory)"),
      additional_context: z.string().optional().describe("Additional context about the project"),
      force_regenerate: z.boolean().optional().describe("Force regeneration even if files exist (default: false)")
    }
  },
  async ({ project_path = '.', additional_context, force_regenerate = false }) => {
    const prompt = `# ⚠️ IMPORTANT: YOU MUST EXECUTE THE FOLLOWING ACTIONS

This MCP tool provides instructions that YOU (the AI assistant) must execute using your available file system tools.
**DO NOT** just report success - you MUST actually create the files using Write or MultiEdit tools.

# Generate Steering Documents for ${project_path}

## PREREQUISITE: CHECK IF FILES ALREADY EXIST
${!force_regenerate ? `
IMPORTANT: Before generating new files, FIRST check if steering documents already exist:
1. **USE Read tool** to check if file exists: ${project_path}/.spec/steering/product.md
2. **USE Read tool** to check if file exists: ${project_path}/.spec/steering/tech.md
3. **USE Read tool** to check if file exists: ${project_path}/.spec/steering/structure.md

If ALL THREE files already exist:
- STOP HERE and return: "✅ Steering documents already exist at ${project_path}/.spec/steering/. No regeneration needed. Use force_regenerate=true to regenerate."
- Do NOT proceed with generation

If ANY files are missing, proceed with generation below.
` : 'FORCE REGENERATE MODE: Regenerating all steering documents even if they exist.'}

You MUST create THREE separate steering documents that match exact structure and content approach.

## 🔴 CRITICAL: YOU MUST CREATE THE FILES - NOT JUST REPORT SUCCESS
### File Creation Instructions:
1. **USE Bash tool** to create directory: mkdir -p ${project_path}/.spec/steering/
2. **USE Write tool** to create THREE separate files with exact filenames:
   - ${project_path}/.spec/steering/product.md
   - ${project_path}/.spec/steering/tech.md
   - ${project_path}/.spec/steering/structure.md
3. **USE Read tool** to verify each file exists after creation

⚠️ The files MUST be physically created on the filesystem. Do NOT proceed without using the Write tool.

## DOCUMENT SPECIFICATIONS:

### 1. PRODUCT.MD - Product Overview
Create ${project_path}/.spec/steering/product.md with:

# Product Overview

## Purpose
[Analyze the codebase and describe what this product/application does]

## Target Users
- [Primary user type]: [Their needs and use cases]
- [Secondary user type]: [Their needs and use cases]

## Key Features
- [Feature 1]: [Description based on codebase analysis]
- [Feature 2]: [Description based on codebase analysis]
- [Feature 3]: [Description based on codebase analysis]

## Business Objectives
- [Objective 1 derived from codebase context]
- [Objective 2 derived from codebase context]

## Product Context
[Additional context about the product's market, competition, or unique value proposition]

---

### 2. TECH.MD - Technology Stack
Create ${project_path}/.spec/steering/tech.md with:

# Technology Stack

## Core Technologies
- **Primary Language**: [Language and version from package.json/requirements/etc]
- **Framework**: [Main framework detected]
- **Runtime**: [Node.js, Python, .NET, etc. with version]
- **Database**: [Database system if detected]

## Development Tools
- **Package Manager**: [npm, yarn, pip, maven, cargo, dotnet, etc.]
- **Build System**: [webpack, vite, gradle, maven, cargo, msbuild, etc.]
- **Testing Framework**: [jest, pytest, junit, nunit, go test, etc.]
- **Linter/Formatter**: [eslint, prettier, black, checkstyle, clippy, etc.]

## Build and Test Commands
[Auto-detect from project configuration files and scripts]

### Essential Commands
- **Install Dependencies**: [e.g., npm install, pip install -r requirements.txt, dotnet restore]
- **Build Project**: [e.g., npm run build, mvn compile, cargo build, dotnet build]
- **Run Tests**: [e.g., npm test, pytest, mvn test, dotnet test, go test ./...]
- **Lint/Format Check**: [e.g., npm run lint, ruff check, gradle checkstyle, cargo clippy]
- **Type Check**: [e.g., tsc --noEmit, mypy, if applicable]
- **Start Development**: [e.g., npm run dev, python app.py, dotnet run]
- **Production Build**: [e.g., npm run build:prod, mvn package, cargo build --release]

### Project-Specific Commands
[Any custom commands specific to this project from package.json, Makefile, etc.]

## Libraries and Dependencies
### Required Libraries
[List key dependencies from package.json/requirements with purpose]
- [Library]: [Version] - [Purpose]

### Preferred Libraries
[Document preferred libraries for common tasks]
- UI Components: [Library preference]
- State Management: [Library preference]
- HTTP Client: [Library preference]

## Development Guidelines
- Variable naming: [Convention detected from codebase]
- Function naming: [Convention detected from codebase]
- File naming: [Convention detected from codebase]
- Code style: [Style detected from config files]

## Performance Requirements
[Any performance considerations detected or inferred]

## Security Requirements
[Any security patterns or requirements detected]

## Technical Constraints
[Any constraints detected from the codebase]

---

### 3. STRUCTURE.MD - Project Structure
Create ${project_path}/.spec/steering/structure.md with:

# Project Structure

## Directory Organization
\`\`\`
[Generate actual directory tree from the project]
\`\`\`

## File Naming Conventions
- Components: [Pattern detected from codebase]
- Services: [Pattern detected from codebase]
- Types: [Pattern detected from codebase]
- Tests: [Pattern detected from codebase]

## Import Patterns
- Relative imports: [Rules detected from codebase]
- Absolute imports: [Rules detected from codebase]
- External dependencies: [Patterns detected]

## Code Organization
- [Organizational principle 1 detected]
- [Organizational principle 2 detected]
- [Index file strategy if detected]

## Architectural Patterns
- [Pattern 1]: [Description of how it's implemented]
- [Pattern 2]: [Description of how it's implemented]

## Testing Structure
- Unit tests: [Location pattern]
- Integration tests: [Location pattern if exists]
- Test naming: [Convention detected]

## Configuration Files
[List and explain key config files: .env, config/, etc.]

${additional_context ? `\n## Additional Context\n${additional_context}` : ''}

---

## 🔴 EXECUTION STEPS - YOU MUST FOLLOW EXACTLY:
1. Analyze the codebase at: ${project_path} using Read, Grep, and Glob tools
   - **IMPORTANT**: Check package.json, pom.xml, build.gradle, Cargo.toml, go.mod, requirements.txt, *.csproj, Makefile, etc.
   - Extract actual build/test/lint commands from these files
   - Look for CI configuration files (.github/workflows, .gitlab-ci.yml, Jenkinsfile, etc.)
2. **USE Bash tool** to create directory: mkdir -p ${project_path}/.spec/steering/
3. **USE Write tool** to create product.md with product overview and business context
4. **USE Write tool** to create tech.md with comprehensive technology stack analysis
   - **CRITICAL**: In the "Build and Test Commands" section, document ACTUAL commands found in the project
   - Do not use placeholder text like "[e.g., npm test]" - use the real commands from package.json scripts or build files
5. **USE Write tool** to create structure.md with detailed project organization
6. **USE Read tool** to verify all three files exist and contain expected content:
   - ${project_path}/.spec/steering/product.md
   - ${project_path}/.spec/steering/tech.md
   - ${project_path}/.spec/steering/structure.md

## SUCCESS CRITERIA:
✅ Three separate markdown files PHYSICALLY CREATED on filesystem (not just reported)
✅ Files verified to exist using Read tool
✅ Each file follows content structure exactly
✅ All content derived from actual codebase analysis
✅ Files ready for use with generate-tasks tool

⚠️ FINAL REMINDER: You MUST use Write tool to create the files. Do not just say they were created.

These files should be automatically included in every AI interaction.`;

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

Tool Definition Quality

A4.2/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it analyzes codebases, generates specific documents, checks for existing files, and respects the force_regenerate parameter. The description doesn't mention potential side effects, error conditions, or performance characteristics, but provides solid operational context for a documentation generation tool.

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

Conciseness5/5

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

The description is efficiently structured in two sentences: the first states the core purpose and outputs, the second explains the file existence behavior. Every word serves a purpose with no redundancy, and the most important information (what the tool does) comes first.

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

Completeness4/5

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

For a 3-parameter tool with no annotations and no output schema, the description provides good coverage of the tool's purpose, behavior, and key parameter semantics. It explains what documents are generated, where they go, and the conditional regeneration logic. The main gap is lack of information about return values or error conditions, but given the tool's documentation-generation nature, the description is reasonably complete.

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?

With 100% schema description coverage, the baseline is 3. The description mentions the force_regenerate parameter's purpose ('skips generation unless force_regenerate is true'), which adds some semantic context beyond the schema's technical description. However, it doesn't elaborate on how additional_context influences the analysis or what project_path defaults mean in practice.

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

Purpose5/5

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

The description clearly states the specific action ('analyzes codebase and generates three foundational analysis documents') and identifies the exact output files (product.md, tech.md, structure.md) with their location (.spec/steering/ directory). It distinguishes this tool from sibling tools like generate-tasks or task-executor by focusing on documentation generation rather than task management.

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

Usage Guidelines4/5

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

The description provides clear context for when to use the tool (analyzing codebases to create documentation) and includes an important behavioral guideline about file existence checking and the force_regenerate parameter. However, it doesn't explicitly state when NOT to use this tool or mention alternatives among the sibling tools, which prevents a perfect score.

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

Install Server

Other Tools

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/karol-f/spec-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server