klapaudius/symfony-mcp-server
Symfony MCP Server is a powerful package designed to streamline the implementation of Model Context Protocol (MCP) servers in Symfony applications.
Symfony MCP Server
A powerful Symfony package to build a Model Context Protocol Server seamlessly and
build Intelligent AI Agents.
Transform your Symfony applications into powerful AI-driven systems
๐ค Unleash the Power of AI Agents in Your Symfony Apps
Symfony MCP Server enables you to build intelligent, context-aware AI agents that can reason, make decisions, and interact with your application's business logic. By implementing the Model Context Protocol (MCP), your Symfony application becomes a platform for sophisticated AI-driven automation and intelligence.
๐ฏ Why Build Agents with Symfony MCP Server?
Transform Static Tools into Intelligent Agents:
- ๐ง AI-Powered Reasoning: Tools can consult LLMs mid-execution to make smart decisions
- ๐ Dynamic Adaptation: Agents adapt their behavior based on context and real-time analysis
- ๐ก Complex Problem Solving: Break down complex tasks and solve them iteratively with AI assistance
- ๐จ Creative Generation: Generate content and solutions that evolve with user needs
Enterprise-Grade Security:
- ๐ Secure Transports: StreamableHTTP and SSE instead of STDIO for production environments
- ๐ก๏ธ Protected APIs: Keep your internal systems safe while exposing AI capabilities
- ๐๏ธ Fine-Grained Control: Manage authentication, authorization, and access at every level
Key Features:
- ๐ ๏ธ Tools: Create powerful, executable functions that LLM can invoke to interact with your application
- ๐ฌ Prompts: Define conversation starters and templates to guide AI behavior and interactions
- ๐ Resources: Expose structured data and documents that AI can read and reason about
- ๐ง Sampling: Enable tools to consult AI models mid-execution for intelligent decision-making
- ๐ Progress Streaming: Real-time progress notifications for long-running operations
- ๐จ Multi-Modal Results: Support for Text, Image, Audio, and Resource outputs from tools
- ๐ Flexible Architecture: Adapter-based design with Pub/Sub messaging for scalable deployments
๐ Agent-First Features
๐งช Sampling: The Core of Agentic Behavior (v1.4.0+)
Transform your tools into autonomous agents that can think and reason:
class IntelligentAnalyzer implements SamplingAwareToolInterface
{
private SamplingClient $samplingClient;
public function execute(array $arguments): ToolResultInterface
{
// Check if sampling is available
if ($this->samplingClient !== null && $this->samplingClient->isEnabled()) {
try {
// Let AI analyze and reason about complex data
$response = $this->samplingClient->createTextRequest(
"Analyze this data and suggest optimizations: {$arguments['data']}",
new ModelPreferences(
[['name' => 'claude-3-sonnet']],
0.3, // costPriority
0.8, // intelligencePriority
0.2 // speedPriority
),
'You are a data analysis expert.',
2000
);
// Execute actions based on AI reasoning
return new TextToolResult($response->getContent()->getText());
} catch (\Exception $e) {
// Fallback to basic analysis
return new TextToolResult('Basic analysis: Data structure appears valid.');
}
}
return new TextToolResult('Advanced analysis requires AI capabilities.');
}
public function setSamplingClient(SamplingClient $samplingClient): void
{
$this->samplingClient = $samplingClient;
}
}
๐ ๏ธ Tool System: Building Blocks for Agents
Create powerful tools that AI agents can orchestrate:
- StreamableToolInterface: Real-time progress updates for long-running operations
- Multi-Result Support: Return text, images, audio, or resources
- Progress Notifications: Keep users informed during complex agent operations
- Dynamic Tool Discovery: Agents can discover and use tools based on capabilities
๐ญ Prompt Engineering for Agent Behavior
Define agent personalities and behaviors through sophisticated prompt systems:
- Context-Aware Prompts: Guide agent behavior based on application state
- Multi-Modal Support: Text, image, audio, and resource-based prompts
- Dynamic Prompt Generation: Prompts that adapt based on user interaction
๐ Resource Management for Agent Memory
Give your agents access to structured knowledge:
- Dynamic Resource Loading: Agents can access and reason about your data
- Template-Based Resources: Generate resources on-the-fly based on context
- Multi-Provider Support: File system, database, API, or custom providers
๐ฏ Real-World Agent Examples
๐ Intelligent Code Review Agent
class CodeReviewAgent implements SamplingAwareToolInterface
{
private SamplingClient $samplingClient;
public function execute(array $arguments): ToolResultInterface
{
// Check if sampling is available
if ($this->samplingClient !== null && $this->samplingClient->isEnabled()) {
try {
// AI analyzes code for patterns, security, and best practices
$review = $this->samplingClient->createTextRequest(
"Review this code for security vulnerabilities, performance issues, and suggest improvements: {$arguments['code']}",
new ModelPreferences(
[['name' => 'claude-3-sonnet']],
0.2, // costPriority
0.8, // intelligencePriority
0.2 // speedPriority
),
'You are a senior code reviewer with expertise in security and performance.',
2000
);
// Generate actionable recommendations
return new TextToolResult($this->formatReview($review->getContent()->getText()));
} catch (\Exception $e) {
// Fallback to basic analysis
return new TextToolResult('Basic code review: Structure appears valid.');
}
}
return new TextToolResult('Advanced code review requires AI capabilities.');
}
public function setSamplingClient(SamplingClient $samplingClient): void
{
$this->samplingClient = $samplingClient;
}
}
๐ Data Analysis Agent
class DataInsightAgent implements SamplingAwareToolInterface, StreamableToolInterface
{
private SamplingClient $samplingClient;
private ?ProgressNotifierInterface $progressNotifier = null;
public function execute(array $arguments): ToolResultInterface
{
// Check if sampling is available
if ($this->samplingClient !== null && $this->samplingClient->isEnabled()) {
try {
// Multi-step reasoning process
$steps = [
'Identify patterns and anomalies',
'Generate statistical insights',
'Create visualizations',
'Recommend actions'
];
$this->progressNotifier?->sendProgress(
progress: 0,
total: count($steps)+1,
message: "Analyzing dataset..."
);
$insights = [];
foreach ($steps as $i => $step) {
$response = $this->samplingClient->createTextRequest(
"$step for this data: {$arguments['data']}",
new ModelPreferences(
[['name' => 'claude-3-sonnet']],
0.2, // costPriority
0.8, // intelligencePriority
0.2 // speedPriority
),
'You are a data analysis expert.',
2000
);
$insights[] = $response->getContent()->getText();
$this->progressNotifier?->sendProgress(
progress: $i+1,
total: count($steps)+1,
message: $step
);
}
return new TextToolResult($this->compileReport($insights));
} catch (\Exception $e) {
return new TextToolResult('Basic data analysis: Dataset appears well-formed.');
}
}
return new TextToolResult('Advanced data analysis requires AI capabilities.');
}
public function setSamplingClient(SamplingClient $samplingClient): void
{
$this->samplingClient = $samplingClient;
}
public function setProgressNotifier(ProgressNotifierInterface $progressNotifier): void
{
$this->progressNotifier = $progressNotifier;
}
}
๐ค Customer Support Agent
class SupportAgent implements SamplingAwareToolInterface
{
private SamplingClient $samplingClient;
public function execute(array $arguments): ToolResultInterface
{
// Check if sampling is available
if ($this->samplingClient !== null && $this->samplingClient->isEnabled()) {
try {
// Load customer context
$context = $this->loadCustomerHistory($arguments['customer_id']);
// AI determines best response strategy
$response = $this->samplingClient->createTextRequest(
"Customer issue: {$arguments['issue']}\nHistory: $context\nDetermine the best resolution approach.",
new ModelPreferences(
[['name' => 'claude-3-sonnet']],
0.2, // costPriority
0.8, // intelligencePriority
0.2 // speedPriority
),
'You are an expert customer support agent.',
2000
);
// Send back the strategy for user approval
return new TextToolResult($response->getContent()->getText());
} catch (\Exception $e) {
return new TextToolResult('Standard support response: We will review your issue and respond within 24 hours.');
}
}
return new TextToolResult('Personalized support requires AI capabilities.');
}
public function setSamplingClient(SamplingClient $samplingClient): void
{
$this->samplingClient = $samplingClient;
}
}
๐ Quick Start: Build Your First Agent
1. Requirements
- PHP >=8.2
- Symfony >=6.4
2. Install Symfony MCP Server
Create the configuration file config/packages/klp_mcp_server.yaml and paste into it:
```yaml
klp_mcp_server:
enabled: true
server:
name: 'My MCP Server'
version: '1.0.0'
default_path: 'mcp'
ping:
enabled: true # Read the warning section in the default configuration file before disable it
interval: 30
server_providers: ['streamable_http','sse']
sse_adapter: 'cache'
adapters:
cache:
prefix: 'mcp_sse_'
ttl: 100
tools:
- KLP\KlpMcpServer\Services\ToolService\Examples\CodeAnalyzerTool # Agentic tool sample
- KLP\KlpMcpServer\Services\ToolService\Examples\HelloWorldTool
- KLP\KlpMcpServer\Services\ToolService\Examples\ProfileGeneratorTool
- KLP\KlpMcpServer\Services\ToolService\Examples\StreamingDataTool
- KLP\KlpMcpServer\Services\ToolService\Examples\VersionCheckTool
prompts:
- KLP\KlpMcpServer\Services\PromptService\Examples\CodeReviewPrompt # Agentic prompt sample
- KLP\KlpMcpServer\Services\PromptService\Examples\HelloWorldPrompt
resources:
- KLP\KlpMcpServer\Services\ResourceService\Examples\HelloWorldResource
- KLP\KlpMcpServer\Services\ResourceService\Examples\ProjectSummaryResource # Agentic resource sample
resources_templates:
- KLP\KlpMcpServer\Services\ResourceService\Examples\DynamicAnalysisResource # Agentic resource template sample
- KLP\KlpMcpServer\Services\ResourceService\Examples\McpDocumentationResource
```
For more detailed explanations, you can open the default configuration file
Install the package via Composer:
composer require klapaudius/symfony-mcp-server
Add routes in your config/routes.yaml
klp_mcp_server:
resource: '@KlpMcpServerBundle/Resources/config/routes.php'
type: php
You're all done! Upon completing this setup, your project will include 3 new API endpoints:
- Streaming Endpoint for MCP Clients:
GET /{default_path}/sse
- Request Submission Endpoint:
POST /{default_path}/messages
- Streamable HTTP Endpoint:
GET|POST /{default_path}
Docker Setup (Optional)
The project includes a Docker setup that can be used for development. The Docker setup includes Nginx, PHP-FPM with Redis extension, and Redis server.
For detailed instructions on how to set up and use the Docker containers, please refer to the .
3. Create Your First Tool
# Generate a new tool
php bin/console make:mcp-tool MyCustomTool
# Test your tool locally
php bin/console mcp:test-tool MyCustomTool --input='{"task":"analyze this code"}'
4. Visualizing with Inspector
You can use the Model Context Protocol Inspector to visualize and test your MCP tools:
# Run the MCP Inspector without installation
npx @modelcontextprotocol/inspector node build/index.js
This will typically open a web interface at localhost:6274
. To test your MCP server:
5. Connect AI Clients
Your agents are now accessible to:
- ๐ค Claude Desktop / Claude.ai
- ๐ง Custom AI applications
- ๐ Any MCP-compatible client
๐๏ธ Architecture for Agent Builders
Secure Agent Communication
- StreamableHTTP: Direct, secure agent-to-client communication
- SSE (Server-Sent Events): Real-time updates for long-running agent tasks
- No STDIO: Enterprise-safe, no system exposure
Scalable Agent Infrastructure
- Pub/Sub Messaging: Handle multiple agent sessions concurrently
- Redis/Cache Adapters: Scale your agent platform horizontally
- Progress Streaming: Real-time feedback for complex agent operations
Agent Development Tools
- MCP Inspector: Visualize and debug agent behavior
- Test Commands: Rapid agent development and testing
Current Available MCP Features
Ressources | Prompts | Tools | Discovery | Sampling | Roots | Elicitation |
---|---|---|---|---|---|---|
โ | โ | โ | โ | โ | โ | โ |
๐ Agent Development Resources
- ๐ Building Intelligent Tools: Complete guide to creating AI-powered tools
- ๐ง Sampling Documentation: Master agent reasoning capabilities
- ๐ญ Prompt Engineering: Design agent behaviors and personalities
- ๐ Resource Management: Give agents access to knowledge
๐ Join the Agent Revolution
Build the next generation of AI-powered applications with Symfony MCP Server. Your tools aren't just functions anymore โ they're intelligent agents capable of reasoning, learning, and evolving.
Community
- ๐ฌ GitHub Discussions: Share your agent creations
- ๐ Issue Tracker: Report bugs and request features
- ๐ Examples: Learn from working agents
๐ License
MIT License - Build freely!
๐ฐ MCP Registries referencing
- https://mcpreview.com/mcp-servers/klapaudius/symfony-mcp-server
- https://mcp.so/server/symfony-mcp-server/klapaudius
Built with โค๏ธ by Boris AUBE and the contributors - Inspired by OP.GG/laravel-mcp-server