Repository files navigation

A modern template for agentic orchestration — built for rapid iteration and scalable deployment using highly customizable, community-supported tools like MCP, LangGraph, and more.

Visit the Github:

• FastAPI MCP LangGraph Template
  • Core Features
    • Technology Stack and Features
    • Planned Features
  • Architecture
    • Inspector
    • Template Setup
    • Reverse Proxy
    • Planned Features Diagrams
      • Monitoring and Observability
      • Authentication and Authorization
  • Quick Start
  • Development
    • VSCode Devcontainer
    • Without VSCode Devcontainer
  • Debugging
  • Refactored Markdown Files
    • MCP
    • LangGraph
    • Supabase
    • Langfuse
    • Grafana Stack

is an open protocol that standardizes how apps provide context to LLMs.

• Seamlessly integrates LLM with growing list of community integrations found here
• No LLM provider lock in

for Customizable Agentic Orchestration

• Native streaming for UX in complex Agentic Workflows
• Native persisted chat history and state management

• for Python backend API
• for Python SQL database interactions (ORM + Validation).
  • Wrapper of
• for LLM Observability and LLM Metrics
• for Data Validation and Settings Management.
• for DB RBAC
  • Relational DB
  • Vector Store
• Reverse Proxy
• for development and production.

• for scraping Metrics
• for visualizing Metrics
• SaaS for Authentication and Authorization with OIDC & JWT via OAuth 2.0
• CI/CD via Github Actions
  • 💵 Deploy live demo to
  • Provision with IaC
  • Push built images to ECR and Dockerhub

This section outlines the architecture of the services, their interactions, and planned features.

Inspector communicates via SSE protocol with each MCP Server, while each server adheres to MCP specification.

graph LR  subgraph localhost    A[Inspector]    B[DBHub Server]    C[Youtube Server]    D[Custom Server]  end  subgraph Supabase Cloud    E[Supabase DB]  end  subgraph Google Cloud    F[Youtube API]  end  A<-->|Protocol|B  A<-->|Protocol|C  A<-->|Protocol|D  B<-->E  C<-->F

The current template does not connect to all MCP servers. Additionally, the API server communicates with the database using a SQL ORM.

graph LR  subgraph localhost    A[API Server]    B[DBHub Server]    C[Youtube Server]    D[Custom Server]  end  subgraph Supabase Cloud    E[Supabase DB]  end  A<-->|Protocol|D  A<-->E

Can be extended for other services like Frontend and/or certain backend services self-hosted instead of on cloud (e.g., Langfuse).

graph LR  A[Web Browser]  subgraph localhost    B[Nginx Reverse Proxy]    C[API Server]  end  A-->B  B-->C

graph LR  subgraph localhost    A[API Server]  end  subgraph Grafana Cloud    B[Grafana]  end  subgraph Langfuse Cloud    C[Langfuse]  end  A -->|Metrics & Logs| B  A -->|Traces & Events| C

Auth0 Source

Setup to run the repository in both production and development environments.

Build community youtube MCP image with:

./community/youtube/build.sh

:::tip

Instead of cloning or submoduling the repository locally, then building the image, this script builds the Docker image inside a temporary Docker-in-Docker container. This approach avoids polluting your local environment with throwaway files by cleaning up everything once the container exits.

:::

Then build the other images with:

docker compose -f compose-dev.yaml build

Copy environment file:

cp .env.sample .env

Add your following API keys and value to the respective file:./envs/backend.env,./envs/youtube.env and.env.

OPENAI_API_KEY=sk-proj-...POSTGRES_DSN=postgresql://postgres...LANGFUSE_PUBLIC_KEY=pk-lf-...LANGFUSE_SECRET_KEY=sk-lf-...LANGFUSE_HOST=https://cloud.langfuse.comENVIRONMENT=productionYOUTUBE_API_KEY=...

Set environment variables in shell: (compatible withbash andzsh)

set -a;forenv_filein ./envs/*;dosource$env_file;done;set +a

Start production containers:

docker compose up -d

First, set environment variables as per above.

:::warning

Only replace the following if you plan to start debugger for FastAPI server in VSCode.

:::

Replace./compose-dev.yaml entrypoint to allow debugging FastAPI server:

api:image:api:prodbuild:dockerfile:./backend/api/Dockerfile# highlight-next-lineentrypoint:bash -c "sleep infinity"env_file:      -./envs/backend.env

Then:

code --no-sandbox.

PressF1 and typeDev Containers: Rebuild and Reopen in Container to open containerized environment with IntelliSense and Debugger for FastAPI.

Run development environment with:

docker compose -f compose-dev.yaml up -d

Sometimes in development, nginx reverse proxy needs to reload its config to route services properly.

docker compose -f compose-dev.yamlexec nginx sh -c"nginx -s reload"

The following markdown files provide additional details on other features:

./docs/mcp.md

./docs/langgraph.md

./docs/supabase.md

./docs/langfuse.md

./docs/grafana-stack.md