MCP Server

The Model Context Protocol (MCP) server bridges AI assistants like Claude to your indexed codebase, enabling intelligent code search, pattern recognition, and Wikit-aware development.

Overview

The MCP server provides:

Semantic Code Search: Find code by meaning across all projects
WordPress Pattern Recognition: Understand hooks, filters, custom post types
Wikit Block Discovery: Search 60+ Gutenberg blocks
Project Management: Create and manage WordPress projects
Repository Integration: Access git repositories and history

Architecture

%%{init: {'theme':'neutral'}}%%
graph TB
    subgraph "AI Layer"
        Claude[Claude Desktop]
        Cursor[Cursor IDE]
        Other[Other AI Tools]
    end

    subgraph "MCP Server"
        Server[MCP Server<br/>Port 8765]
        Tools[MCP Tools]
    end

    subgraph "Data Layer"
        Qdrant[(Vector DB<br/>Qdrant)]
        Git[Git Repositories]
        Projects[WordPress Projects]
    end

    Claude -->|MCP Protocol| Server
    Cursor -->|MCP Protocol| Server
    Other -->|MCP Protocol| Server

    Server --> Tools
    Tools --> Qdrant
    Tools --> Git
    Tools --> Projects

Available Tools

Code Search Tools

`search_codebase`

Semantic search across all indexed repositories.

python

# Example usage in Claude
search_codebase(
    query="custom post type registration",
    project="my-site",
    file_types=["php"],
    limit=10
)

Parameters:

query (string): Search query
project (string, optional): Project name to scope search
file_types (list, optional): Filter by file extensions
component_type (string, optional): Filter by function, class, hook
limit (int): Maximum results (default: 20)

Returns:

json

[
  {
    "file_path": "wp-content/themes/custom/functions.php",
    "component_type": "function",
    "component_name": "register_portfolio_post_type",
    "content": "function register_portfolio_post_type() {...}",
    "line_start": 45,
    "line_end": 65,
    "score": 0.89
  }
]

`search_functions`

Find specific functions by name.

python

search_functions(
    function_name="get_user",
    project="my-site",
    language="php"
)

`search_classes`

Find PHP or JavaScript classes.

python

search_classes(
    class_name="CustomPostType",
    project="my-site"
)

WordPress-Specific Tools

`search_wordpress_hooks`

Find WordPress actions and filters.

python

search_wordpress_hooks(
    hook_name="init",
    hook_type="action",
    project="my-site"
)

Hook Types:

action - do_action() calls
filter - apply_filters() calls
add_action - Hook registrations
add_filter - Filter registrations

`wordpress_docs`

Search WordPress core documentation.

python

wordpress_docs(
    query="register_post_type",
    type="function",
    get_details=True
)

Wikit-Specific Tools

`search_wikit_blocks`

Search Wikit's 60+ Gutenberg blocks.

python

search_wikit_blocks(
    block_name="hero"  # Optional
)

Returns:

json

[
  {
    "name": "wdg/hero",
    "title": "Hero Section",
    "category": "wdg-layout",
    "description": "Full-width hero with image/video background",
    "attributes": {
      "backgroundType": "image",
      "overlayOpacity": 0.5
    },
    "example_usage": "..."
  }
]

`get_wikit_component`

Get detailed Wikit component information.

python

get_wikit_component(
    component_name="Button"
)

Project Management Tools

`get_project_info`

Get project details and indexing status.

python

get_project_info(
    project_name="my-site"
)

Returns:

json

{
  "name": "my-site",
  "status": "running",
  "php_version": "8.2",
  "url": "https://my-site.localhost:8443",
  "database": "wp_my_site",
  "collection": "project_my_site",
  "vectors": 1450,
  "last_indexed": "2024-10-14T10:30:00Z",
  "repositories": [
    {
      "name": "my-site",
      "branch": "main",
      "last_commit": "abc123"
    }
  ]
}

`list_collections`

List all vector database collections.

python

list_collections()

Recent Changes Tools

`search_recent_changes`

Get recently indexed code.

python

search_recent_changes(
    project="my-site",
    limit=10
)

Configuration

Server Configuration

The MCP server runs on port 8765 by default:

yaml

# docker-compose.yml
mcp-server:
  ports:
    - "8765:8765"
  environment:
    - MCP_HOST=0.0.0.0
    - MCP_PORT=8765
    - VECTOR_DB_HOST=qdrant
    - VECTOR_DB_PORT=6333

Client Configuration

Claude Desktop

Add to Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

json

{
  "mcpServers": {
    "wdg": {
      "url": "http://localhost:8765"
    }
  }
}

Cursor IDE

Add to Cursor settings (.cursor/mcp.json):

json

{
  "servers": {
    "wdg": {
      "url": "http://localhost:8765",
      "name": "WDG AI Dev Environment"
    }
  }
}

Usage Examples

Example 1: Finding Similar Code

User prompt to AI:

"Find all places where we validate email addresses"

AI uses MCP:

python

search_codebase(
    query="email validation",
    file_types=["php", "js"]
)

Result:

is_valid_email() in utils.php
validateEmailAddress() in forms.js
Email regex patterns
WordPress sanitize_email() usage

Example 2: Understanding Wikit Blocks

User prompt:

"What Wikit blocks are available for layout?"

AI uses MCP:

python

search_wikit_blocks()

AI responds with:

Hero block
Grid block
Columns block
Section block
Container block

Example 3: Project Context Search

User prompt:

"In the client-website project, show me how we handle custom post types"

AI uses MCP:

python

search_codebase(
    query="custom post type registration",
    project="client-website",
    component_type="function"
)

Advanced Features

Contextual Awareness

The MCP server understands:

Project context: Scopes searches to active project
File relationships: Knows which files depend on others
Git history: Can reference specific commits
WordPress conventions: Understands hooks, filters, CPTs

Multi-Project Search

Search across multiple projects:

python

# Search in all projects
search_codebase(
    query="user authentication",
    project=None  # Searches all projects
)

# Compare implementations across projects
search_functions(
    function_name="get_user",
    project=None
)

Pattern Recognition

The MCP server identifies:

Wikit patterns: Recognizes WDG's standard implementations
WordPress best practices: Identifies secure coding patterns
Code reusability: Finds similar implementations

Performance

Response Times

Operation	Average Time	Notes
`search_codebase`	50-100ms	Depends on collection size
`search_functions`	20-50ms	Direct lookup
`search_wikit_blocks`	10-20ms	Small collection
`get_project_info`	<10ms	Cached
`list_collections`	<10ms	Direct query

Caching

The MCP server implements caching for:

Project metadata (15 min TTL)
Collection lists (5 min TTL)
Wikit block catalog (1 hour TTL)

Optimization

python

# Limit result count for faster responses
search_codebase(query="...", limit=5)

# Use filters to reduce search space
search_codebase(
    query="...",
    project="my-site",
    file_types=["php"],
    component_type="function"
)

Security

Network Security

yaml

# Bind only to localhost (default)
MCP_HOST=127.0.0.1  # Local only

# Or bind to all interfaces (be careful!)
MCP_HOST=0.0.0.0  # Accessible on network

Authentication

Currently, the MCP server runs locally without authentication. For production deployments:

python

# Add API key authentication
MCP_API_KEY=your-secret-key

# Or use JWT tokens
MCP_JWT_SECRET=your-jwt-secret

Data Privacy

All queries stay local
No external API calls for search
Code never leaves your machine
Project data is isolated

Troubleshooting

Server Not Responding

bash

# Check if server is running
curl http://localhost:8765/health

# View server logs
docker logs wdg-mcp-server

# Restart server
docker-compose restart mcp-server

Connection Refused

bash

# Check port is not in use
lsof -i :8765

# Verify Docker network
docker network inspect wdg-network

# Check firewall settings
sudo ufw status

Slow Responses

bash

# Check Qdrant status
curl http://localhost:6333/collections

# Monitor server resources
docker stats wdg-mcp-server

# Reduce search limits
# Use more specific queries

Empty Results

bash

# Verify collections exist
curl http://localhost:6333/collections

# Check indexing status
wdg status

# Re-index if needed
wdg index my-site

API Reference

Health Check

bash

curl http://localhost:8765/health

Response:

json

{
  "status": "healthy",
  "version": "1.0.0",
  "uptime": 3600,
  "collections": 5,
  "total_vectors": 20450
}

List Tools

bash

curl http://localhost:8765/tools

Response:

json

{
  "tools": [
    {
      "name": "search_codebase",
      "description": "Semantic search across repositories",
      "parameters": {...}
    },
    ...
  ]
}

Best Practices

1. Use Specific Queries

python

# Good: Specific and contextual
search_codebase(
    query="WordPress REST API endpoint registration",
    component_type="function"
)

# Bad: Too vague
search_codebase(query="api")

2. Scope to Project

python

# Good: Scoped search
search_codebase(
    query="user authentication",
    project="client-website"
)

# Bad: Unscoped (slower)
search_codebase(query="user authentication")

3. Use Appropriate Tools

python

# Good: Use specific tool
search_functions(function_name="get_user")

# Bad: Generic search
search_codebase(query="get_user")

4. Limit Results

python

# Good: Limited results
search_codebase(query="...", limit=5)

# Bad: Too many results
search_codebase(query="...", limit=100)

Integration Examples

Claude Desktop

Create a custom slash command:

json

// ~/Library/Application Support/Claude/commands/search-code.json
{
  "command": "/search-code",
  "description": "Search WDG codebase",
  "handler": {
    "tool": "search_codebase",
    "parameters": {
      "query": "$input"
    }
  }
}

Cursor IDE

Use in Cursor's chat:

User: "@wdg Find email validation in my-site project"

Cursor: [Uses MCP search_codebase tool]
Found 3 implementations:
1. is_valid_email() in utils.php
2. validateEmail() in forms.js
3. Email validation in checkout.php

Monitoring

View Real-Time Logs

bash

# Follow MCP server logs
docker logs -f wdg-mcp-server

# Filter for searches
docker logs wdg-mcp-server | grep "search_codebase"

Usage Metrics

bash

# Get server stats
curl http://localhost:8765/metrics

Response:

json

{
  "requests_total": 1250,
  "requests_by_tool": {
    "search_codebase": 800,
    "search_functions": 300,
    "search_wikit_blocks": 150
  },
  "average_response_time": "75ms",
  "cache_hit_rate": "45%"
}

Next Steps:

MCP Server ​

Overview ​

Architecture ​

Available Tools ​

Code Search Tools ​

search_codebase ​

search_functions ​

search_classes ​

WordPress-Specific Tools ​

search_wordpress_hooks ​

wordpress_docs ​

Wikit-Specific Tools ​

search_wikit_blocks ​

get_wikit_component ​

Project Management Tools ​

get_project_info ​

list_collections ​

Recent Changes Tools ​

search_recent_changes ​

Configuration ​

Server Configuration ​

Client Configuration ​

Claude Desktop ​

Cursor IDE ​

Usage Examples ​

Example 1: Finding Similar Code ​

Example 2: Understanding Wikit Blocks ​

Example 3: Project Context Search ​

Advanced Features ​

Contextual Awareness ​

Multi-Project Search ​

Pattern Recognition ​

Performance ​

Response Times ​

Caching ​

Optimization ​

Security ​

Network Security ​

Authentication ​

Data Privacy ​

Troubleshooting ​

Server Not Responding ​

Connection Refused ​

Slow Responses ​

Empty Results ​

API Reference ​

Health Check ​

List Tools ​

Best Practices ​

1. Use Specific Queries ​

2. Scope to Project ​

3. Use Appropriate Tools ​

4. Limit Results ​

Integration Examples ​

Claude Desktop ​

Cursor IDE ​

Monitoring ​

View Real-Time Logs ​

Usage Metrics ​

MCP Server

Overview

Architecture

Available Tools

Code Search Tools

`search_codebase`

`search_functions`

`search_classes`

WordPress-Specific Tools

`search_wordpress_hooks`

`wordpress_docs`

Wikit-Specific Tools

`search_wikit_blocks`

`get_wikit_component`

Project Management Tools

`get_project_info`

`list_collections`

Recent Changes Tools

`search_recent_changes`

Configuration

Server Configuration

Client Configuration

Claude Desktop

Cursor IDE

Usage Examples

Example 1: Finding Similar Code

Example 2: Understanding Wikit Blocks

Example 3: Project Context Search

Advanced Features

Contextual Awareness

Multi-Project Search

Pattern Recognition

Performance

Response Times

Caching

Optimization

Security

Network Security

Authentication

Data Privacy

Troubleshooting

Server Not Responding

Connection Refused

Slow Responses

Empty Results

API Reference

Health Check

List Tools

Best Practices

1. Use Specific Queries

2. Scope to Project

3. Use Appropriate Tools

4. Limit Results

Integration Examples

Claude Desktop

Cursor IDE

Monitoring

View Real-Time Logs

Usage Metrics