MCP Server

🧩 Main modules

1. Main MCP server - the core of the system, performing the following functions:

• Registry of connected servers
• Routing requests between servers
• Monitoring server status
• Aggregation of information about available tools

2. Specialized servers (connect to the main one):

• Embedding server - working with vector representations of text
• PDF extract server - conversion and extraction from PDF to Markdown
• Reranker server - ranking text data
• Qdrant server - managing vector collections
• PostgreSQL server - executing SQL queries and schema inspection
• LLM server - generating and streaming LLM responses, list of models
• MarkUp server - text/file markup using markup service methods
• Transcribe server - audio loading, status and transcription result

⚙️ Available tools

Server	Methods
Embedding server	embedding_generate, embedding_batch_generate, embedding_get_models, health_check
PDF extract server	document_convert_to_markdown, document_get_supported_formats, health_check
Reranker server	rerank_documents, health_check
Qdrant server	vector_create_collection, vector_get_collection_info, vector_upsert_points, vector_search, vector_delete_points, health_check
PostgreSQL server	postgres_execute_query, postgres_get_schema, postgres_create_table, postgres_insert_data, health_check
LLM server	llm_chat_completion, llm_get_models, llm_stream_completion, health_check
MarkUp server	markup_get_methods, markup_process_text, markup_process_file, health_check
Transcribe server	transcribe_audio, transcribe_get_status, transcribe_get_result, health_check

Note:

To add a new FastMCP server, you need to import it in the main_server.py file and place it in the MCP_SERVERS array, after which the main methods of main_server.py will have access to it.

Also a necessary requirement for FastMCP servers is the presence of the health_check method to check the state.

📡 Main server methods

get_server_and_tools() # Get a list of all servers and tools
router(server_name, tool_name, params) # Routing requests
health_check_servers() # Checking the health of all servers

Setting up the environment

Create a .env file in the root of the project and put the following environment variables in it (the list corresponds to the use in the code):

# Main server
MAIN_SERVER_API_KEY=...

# Embedding server
EMBEDDING_API_KEY=...
EMBEDDING_URL=...
EMBEDDING_MODEL_NAME=...
EMBEDDING_URL_MODELS=...
EMBEDDING_HEALTH_URL=...

# PDF extract server
PDF_EXTRACTOR_URL=...
PDF_HEALTH_URL=...

# Reranker server
RERANK_URL=...
RERANK_MODEL=...
RERANK_HEALTH_URL=...

# Qdrant server
QDRANT_URL=...
QDRANT_API_KEY=...
QDRANT_HEALTH_CHECK_URL=...

# PostgreSQL server
POSTGRES_USER=...
POSTGRES_PASSWORD=...
POSTGRES_HOST=...
POSTGRES_DB=...

#LLM server
LLM_SERVICE_API_KEY=...
LLM_SERVICE_MODEL=...
LLM_SERVICE_CHAT_COMPLETIONS_URL=...
LLM_SERVICE_MODELS_URL=...
LLM_SERVICE_COMPLETIONS_URL=...
LLM_SERVICE_HEALTH_URL=...

# MarkUp server
MARKUP_API_KEY=...
MARKUP_GET_METHODS_URL=...
MARKUP_PROCESS_TEXT_URL=...
MARKUP_PROCESS_FILE_URL=...
MARKUP_HEALTH_CHECK_URL=...

# Transcribe server
TRANSCRIBE_API_KEY=...
TRANSCRIBE_UPLOAD_AUDIO=...
TRANSCRIBE_HEALTH_URL=...

Start the main server

Installation dependencies and creating a virtual environment

Before starting the server, it is recommended to create a virtual environment and install all dependencies from requirements.txt. Run the following commands in the terminal:

1. Creating a virtual environment

python -m venv venv

2. Activating the environment

./venv/Scripts/activate

3. Installing dependencies

pip install -r requirements.txt

After setting up the environment, the server is started with the command

fastmcp run ./main_server.py:main_mcp_server --transport http

Running in Docker

1. Build the image:

docker build -t mcp-main-server .

2. Run the container, passing .env as environment variables:

docker run --rm -p 8000:8000 --env-file .env mcp-main-server

Configuring the server connection in Cursor

0. Run the server using the command above

1. Open the settings

2. Add the MCP server configuration:

{
"mcpServers": {
"main-registry": {
   "url": "http://localhost:8000/mcp/"
}}}

Local MCP server: proxy_mcp_server

• What is it: proxy MCP server that connects to the main registry (main_server) and forwards its methods, and provides a high-level pipeline for pre-preparing data for RAG.
• Where is it: proxy_mcp_server/proxy_mcp_server.py
• Available tools:
• get_server_and_tools() — get a list of servers and their tools from the registry
• router(server_name: str, tool_name: str, params: dict) — universal call router
• preprocessing_data_for_rag(file_paths: List[str]) -> str — prepare PDF/texts and create a collection in Qdrant; returns the collection name
• health_check_servers() — check if all services are available

Requirements:

• main_server is running and accessible via URL (e.g. http://localhost:8000/mcp/).
• Valid API key MAIN_SERVER_API_KEY (must match Authorization header in proxy_mcp_server.py).
• Update url and headers.Authorization in config object inside proxy_mcp_server/proxy_mcp_server.py if necessary.

Connection in Cursor (example):

{
"mcpServers": {
"proxy-server": {
"command": "uv",
"args": [
"run",
"fastmcp",
"run",
"YOUR_PATH_TO/proxy_mcp_server/proxy_mcp_server.py:proxy_mcp_server"]
}}}

Launch from terminal:

fastmcp run ./proxy_mcp_server/proxy_mcp_server.py:proxy_mcp_server

RAG inference: interactive launch

• What is this: console assistant for asking questions to a collection of documents in Qdrant with additional ranking and generation of LLM response.
• Location: rag_inference/RAG workflow.py
• Preliminary environment variables: QDRANT_URL, QDRANT_API_KEY, RERANK_URL, RERANK_MODEL, LLM_SERVICE_CHAT_COMPLETIONS_URL, LLM_SERVICE_API_KEY, LLM_SERVICE_MODEL, EMBEDDING_URL, EMBEDDING_MODEL are used (described above in the settings section).

Run (Windows PowerShell):

python ".\rag_inference\RAG workflow.py" <collection_name>

Where <collection_name> is the name of the collection in Qdrant. It is convenient to get it in advance by calling the preprocessing_data_for_rag tool from proxy_mcp_server and passing a list of files to index; the method will return the name of the created collection.

Example:

python ".\rag_inference\RAG workflow.py" collection_for_rag_1