mcp-server-langgraph
Verified Safeby vishnu2kmohan
Overview
A production-ready Model Context Protocol (MCP) server for building and deploying multi-LLM LangGraph agents, complete with fine-grained authorization, comprehensive observability, and a unique visual workflow builder that generates production-ready Python code.
Installation
docker compose -f docker-compose.dev.yml up -dEnvironment Variables
- ENVIRONMENT
- ENABLE_CODE_EXECUTION
- CODE_EXECUTION_BACKEND
- CODE_EXECUTION_TIMEOUT
- CODE_EXECUTION_MEMORY_LIMIT_MB
- CODE_EXECUTION_CPU_QUOTA
- CODE_EXECUTION_NETWORK_MODE
- CODE_EXECUTION_DOCKER_SOCKET
- CHECKPOINT_BACKEND
- CHECKPOINT_REDIS_URL
- REDIS_URL
- GDPR_STORAGE_BACKEND
- GDPR_POSTGRES_URL
- OPENFGA_API_URL
- OPENFGA_STORE_ID
- OPENFGA_MODEL_ID
- QDRANT_URL
- QDRANT_PORT
- AUTH_PROVIDER
- JWT_SECRET_KEY
- ENABLE_MOCK_AUTHORIZATION
- LLM_PROVIDER
- ANTHROPIC_API_KEY
- OPENAI_API_KEY
- GOOGLE_API_KEY
- VERTEX_AI_PROJECT
- AWS_REGION
- AWS_ACCESS_KEY_ID
- AWS_SECRET_ACCESS_KEY
- OTEL_EXPORTER_OTLP_ENDPOINT
- OTEL_EXPORTER_OTLP_PROTOCOL
- OTEL_SERVICE_NAME
- OTEL_SERVICE_VERSION
- INFISICAL_PROJECT_ID
- INFISICAL_CLIENT_ID
- INFISICAL_CLIENT_SECRET
- INFISICAL_SITE_URL
- RATE_LIMIT_<PROVIDER>_RPM
- RETRY_MAX_ATTEMPTS
- RETRY_EXPONENTIAL_BASE
- RETRY_EXPONENTIAL_MAX
- RETRY_JITTER_STRATEGY
- RETRY_OVERLOAD_MAX_ATTEMPTS
- RETRY_OVERLOAD_EXPONENTIAL_BASE
- RETRY_OVERLOAD_EXPONENTIAL_MAX
- RETRY_OVERLOAD_INITIAL_DELAY
- RETRY_OVERLOAD_JITTER_STRATEGY
- RETRY_OVERLOAD_HONOR_RETRY_AFTER
- RETRY_OVERLOAD_RETRY_AFTER_MAX
- TIMEOUT_DEFAULT
- TIMEOUT_LLM
- TIMEOUT_AUTH
- TIMEOUT_DB
- TIMEOUT_HTTP
- BULKHEAD_LLM_LIMIT
- BULKHEAD_OPENFGA_LIMIT
- BULKHEAD_REDIS_LIMIT
- BULKHEAD_DB_LIMIT
- PAGERDUTY_INTEGRATION_KEY
- SLACK_WEBHOOK_URL
- OPSGENIE_API_KEY
- EMAIL_SMTP_HOST
- EMAIL_FROM_ADDRESS
- EMAIL_TO_ADDRESSES
- BUILDER_AUTH_TOKEN
- BUILDER_OUTPUT_DIR
- BUILDER_POSTGRES_URL
- BUILDER_REDIS_URL
Security Notes
The server implements extensive security measures, especially around code execution and secret handling. Key controls include: a `CodeValidator` to prevent dangerous imports (`os`, `subprocess`), builtins (`eval`, `exec`), and patterns; Docker/Kubernetes sandboxing for isolated code execution (running as non-root, restricted networks by default); `SecretString` for obfuscating secrets in logs/exceptions; and explicit sanitization for logging and HTTP headers. Authentication for builder endpoints is enforced, and path traversal in file operations is rigorously validated. These practices are backed by dedicated unit and integration tests.
Similar Servers
mcp-python-starter
A feature-complete Model Context Protocol (MCP) server template in Python for developing AI applications and agents.
atlantis-mcp-server
An MCP (Model Context Protocol) server for hosting and managing dynamic Python functions and third-party MCP tools, enabling AI agents to discover and utilize shared capabilities across a network.
fastmcp-example
Integrate Model Context Protocol (MCP) with LangChain and LangGraph to build AI agent workflows by exposing a variety of custom and pre-defined tools.
mcp-forge-python
A production-ready MCP (Model Context Protocol) server template for building AI-powered applications with OAuth 2.0 authentication and JWT validation.