MCP Inspector

Supported AI Tools

MCP Inspector works with any tool that supports the Model Context Protocol (MCP):

• Claude Code – Full support with dedicated Nette plugin
• Cursor – Configure via .cursor/mcp.json
• VS Code + Continue – Configure via Continue settings
• Any MCP-compatible tool – See manual configuration

Why MCP Matters

Imagine you ask your AI: “Generate an entity for the product table.”

Without MCP Inspector, the AI has to guess what columns your table has. It might assume common patterns like id, name, price – but what if your table has different columns? What if price is called unit_price? What if you have a currency_id foreign key?

With MCP Inspector, the AI doesn't guess. It calls db_get_columns("product") and sees your actual schema:

The result is code that actually works with your database, not code you have to fix.

Installation

If you're using the Nette plugin for Claude Code, installation is simple:

/install-mcp-inspector

This command adds nette/mcp-inspector to your project and configures everything automatically.

For other AI tools or manual installation:

composer require nette/mcp-inspector

Then configure your AI tool to use the MCP server – see manual configuration below.

Important: After installation, restart your AI tool. The MCP server only connects when the tool starts.

How It Works

MCP Inspector runs as a background process that your AI tool can communicate with. When AI needs information about your application, it sends a request to MCP Inspector, which:

1. Loads your application's DI container (using App\Bootstrap)
2. Executes the requested query (get services, read database schema, etc.)
3. Returns the result to the AI

All operations are read-only. MCP Inspector can't modify your database, change configuration, or execute commands.

DI Container Tools

These tools let AI explore your service definitions.

di_get_services

Lists all registered services. You can filter by name or type.

When AI asks “What mail services do I have?”, it calls:

di_get_services("mail")

And gets a list like:

- mail.mailer (Nette\Mail\Mailer)
- App\Model\QueueMailer
- App\Core\SmtpTransport

di_get_service

Gets detailed information about a specific service – how it's created, what setup methods are called, what tags it has.

di_get_parameters

Reads configuration parameters. Want to know what your database settings are?

di_get_parameters("database")

Note: Sensitive values (passwords, tokens, API keys) are automatically masked.

di_find_by_tag

Finds services with a specific tag. Useful for discovering CLI commands:

di_find_by_tag("console.command")

di_find_by_type

Finds services implementing a specific interface:

di_find_by_type("Nette\\Security\\Authenticator")

di_get_extensions

Lists all registered DI extensions with their configuration.

Database Tools

These tools give AI visibility into your database structure.

db_get_tables

Lists all tables in your database.

db_get_columns

Gets detailed column information for a table – types, whether they're nullable, default values, and foreign key relationships.

db_get_columns("order")

Returns something like:

- id: int (PRIMARY KEY)
- customer_id: int (FK → customer.id)
- status: varchar(20)
- total: decimal(10,2)
- created_at: datetime

db_get_relationships

Shows all foreign key relationships in your database – which tables reference which other tables.

db_get_indexes

Lists indexes for a specific table.

db_explain_query

Runs EXPLAIN on a SELECT query to analyze its performance. AI can use this to suggest query optimizations.

db_generate_entity

The most useful tool for quick development. Given a table name, it generates a complete PHP entity class with proper type hints:

db_generate_entity("product")

Generates:

/**
 * @property-read int $id
 * @property-read string $name
 * @property-read float $unit_price
 * @property-read ?CategoryRow $category
 * @property-read DateTimeImmutable $created_at
 */
final class ProductRow extends Table\ActiveRow
{
}

Router Tools

These tools help AI understand your URL structure.

router_get_routes

Lists all registered routes with their masks and default values.

router_match_url

Given a URL, finds which presenter and action handles it:

router_match_url("/admin/products/edit/5")

Returns:

Presenter: Admin:Product
Action: edit
Parameters: id=5

router_generate_url

Generates a URL for a given presenter and action:

router_generate_url("Admin:Product:edit", {"id": 5})

Tracy Tools

These tools let AI see error logs and help with debugging. They're incredibly useful when something goes wrong – instead of you describing the error, AI can read it directly.

tracy_get_last_exception

Gets the most recent exception from Tracy's log, including the full stack trace. When something breaks, this is the first thing AI checks.

tracy_get_last_exception()

Returns the exception class, message, file, line number, and complete stack trace. AI can analyze this to identify the root cause and suggest a fix.

Example response:

Exception: Nette\Database\UniqueConstraintViolationException
Message: Duplicate entry 'john@example.com' for key 'email'
File: /app/Model/UserService.php:45
Stack trace:
  #0 /app/Presentation/Admin/UserPresenter.php:32
  #1 /vendor/nette/application/src/...

tracy_get_exceptions

Lists recent exception files from Tracy's log directory. Useful for finding patterns or recurring issues.

tracy_get_exceptions(5)

Returns the 5 most recent exception files with timestamps. You can then use tracy_get_exception_detail to examine any of them.

tracy_get_exception_detail

Gets the complete details of a specific exception file. Use this when you want to examine an older exception, not just the latest one.

tracy_get_exception_detail("exception-2024-01-15-143022-abc123.html")

tracy_get_warnings

Shows recent PHP warnings and notices from Tracy's log. These often indicate problems that don't crash the application but should be fixed.

tracy_get_warnings(10)

Common warnings AI can help fix:

• Undefined array key
• Deprecated function calls
• Type mismatch warnings

tracy_get_log

Reads entries from any Tracy log level. Tracy supports multiple log files: error.log, warning.log, info.log, and custom levels.

tracy_get_log("error", 20)

This reads the last 20 entries from the error log. Useful for seeing a history of issues, not just the most recent one.

Creating Custom Tools

You can extend MCP Inspector with your own tools. This is useful if you have application-specific data that AI should be able to query.

Create a class implementing the Toolkit interface:

use Mcp\Capability\Attribute\McpTool;
use Nette\McpInspector\Toolkit;
use Nette\McpInspector\Bridge\BootstrapBridge;

class OrderToolkit implements Toolkit
{
    public function __construct(
        private BootstrapBridge $bridge,
    ) {}

    /**
     * Get pending orders count and total value.
     */
    #[McpTool(name: 'orders_get_pending_summary')]
    public function getPendingSummary(): array
    {
        $db = $this->bridge->getContainer()
            ->getByType(Nette\Database\Explorer::class);

        $result = $db->table('order')
            ->where('status', 'pending')
            ->select('COUNT(*) AS count, SUM(total) AS total')
            ->fetch();

        return [
            'count' => $result->count,
            'total' => $result->total,
        ];
    }
}

Register it in mcp-config.neon:

toolkits:
    - App\Mcp\OrderToolkit

Now AI can call orders_get_pending_summary() to get real-time order statistics.

Configuration

MCP Inspector works out of the box with the default Nette project structure. If your setup is different, create mcp-config.neon in your project root:

# Path to Bootstrap file (if not in default location)
bootstrap: src/Bootstrap.php

# Bootstrap class name (if different from default)
bootstrapClass: MyApp\Bootstrap

# Additional custom toolkits
toolkits:
    - App\Mcp\OrderToolkit
    - App\Mcp\CustomerToolkit

Manual MCP Configuration

For AI tools other than Claude Code (which configures automatically via the plugin), add MCP Inspector to your tool's configuration:

For most MCP-compatible tools, create .mcp.json in your project root:

{
    "mcpServers": {
        "nette-inspector": {
            "command": "php",
            "args": ["vendor/bin/mcp-inspector"]
        }
    }
}

For Cursor, add to .cursor/mcp.json:

{
    "mcpServers": {
        "nette-inspector": {
            "command": "php",
            "args": ["vendor/bin/mcp-inspector"]
        }
    }
}

Consult your AI tool's documentation for the exact configuration location.

Security Considerations

MCP Inspector is designed for development environments. Here's what you should know:

Read-only by design – All tools only read data, never modify it.

Database protection – The db_explain_query tool only accepts SELECT, SHOW, DESCRIBE, and EXPLAIN queries. INSERT, UPDATE, DELETE, and other modifying queries are rejected.

Sensitive data masking – Configuration values containing words like “password”, “secret”, “token”, or “apikey” are automatically masked with ***MASKED***.

Do not expose in production – MCP Inspector should only run on development machines. It provides detailed information about your application internals that you don't want exposed publicly.