​
Configuration

Learn how to configure mcp-agent using configuration files to control logging, execution, model providers, and MCP server connections.

​
Configuration Files

mcp-agent uses two configuration files:

mcp_agent.config.yaml

Application settings, logging, and server configurations

mcp_agent.secrets.yaml

API keys and sensitive information (should be gitignored)

​
Basic Configuration

​
Configuration Reference

​
Execution Engine

Controls how mcp-agent executes workflows: 
execution_engine: asyncio
Standard async execution for most use cases.

​
Logging Configuration

​
MCP Server Configuration

Define MCP servers your agents can connect to: 
mcp:
  servers:
    server_name:
      command: "command_to_run"
      args: ["arg1", "arg2"]
      description: "Optional description"

​
Common MCP Servers

Fetch Server

fetch:
  command: "uvx"
  args: ["mcp-server-fetch"]

Filesystem Server

filesystem:
  command: "npx"
  args: ["-y", "@modelcontextprotocol/server-filesystem", "."]

SQLite Server

sqlite:
  command: "npx"
  args: ["-y", "@modelcontextprotocol/server-sqlite", "database.db"]

Git Server

git:
  command: "uvx"
  args: ["mcp-server-git", "--repository", "."]

​
Model Provider Configuration

​
OpenAI

openai:
  default_model: gpt-4o
  max_tokens: 4096
  temperature: 0.7

​
Anthropic

anthropic:
  default_model: claude-3-5-sonnet-20241022
  max_tokens: 4096
  temperature: 0.7

​
Azure OpenAI

Configure Azure OpenAI with different endpoint types: 
azure:
  default_model: gpt-4o-mini
  api_version: "2025-01-01-preview"
Use api_version: "2025-01-01-preview" for structured outputs support.

​
AWS Bedrock

bedrock:
  default_model: anthropic.claude-3-5-sonnet-20241022-v2:0
  region: us-east-1

​
Google Gemini

Configure Google Gemini with different authentication methods: 
google:
  default_model: gemini-2.0-flash
  temperature: 0.7
  vertexai: false
Use the Gemini Developer API with your API key. Set vertexai: false (default).

​
Advanced Configuration

mcp-agent validates configuration against a schema. Check the configuration schema for all available options.

​
Configuration Examples

​
Basic Web Agent

execution_engine: asyncio
logger:
  transports: [console]
  level: info

mcp:
  servers:
    fetch:
      command: "uvx"
      args: ["mcp-server-fetch"]

openai:
  default_model: gpt-4o

​
File Processing Agent

execution_engine: asyncio
logger:
  transports: [file]
  level: info
  path: "logs/file-processor.jsonl"

mcp:
  servers:
    filesystem:
      command: "npx"
      args: ["-y", "@modelcontextprotocol/server-filesystem", "/data"]
    
    sqlite:
      command: "npx"
      args: ["-y", "@modelcontextprotocol/server-sqlite", "results.db"]

anthropic:
  default_model: claude-3-5-sonnet-20241022

​
Multi-Provider Agent

execution_engine: asyncio
logger:
  transports: [console, file]
  level: info
  path: "logs/multi-provider.jsonl"

mcp:
  servers:
    fetch:
      command: "uvx"
      args: ["mcp-server-fetch"]
    
    filesystem:
      command: "npx"
      args: ["-y", "@modelcontextprotocol/server-filesystem", "."]

# Configure multiple providers
openai:
  default_model: gpt-4o

anthropic:
  default_model: claude-3-5-sonnet-20241022

azure:
  default_model: gpt-4o
  api_version: "2024-02-15-preview"

​
Troubleshooting

​
Next Steps

Core Concepts

Learn about agents, MCP servers, and augmented LLMs

MCP Protocol

Understand tools, resources, prompts, and roots

Model Providers

Configure different LLM providers

Examples

See real configuration examples