Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | No | Path to the Python source code directory | |
| TAVILY_API_KEY | No | Your Tavily API key (including tvly- prefix) for web search functionality | |
| OLLAMA_BASE_URL | No | URL for connecting to Ollama service (used in Docker configuration) | |
| PYTHONUNBUFFERED | No | Disable Python output buffering for better logging | 1 |
| LANGSMITH_API_KEY | No | Your LangSmith API key for tracing and monitoring | |
| LANGSMITH_PROJECT | No | LangSmith project name | ollama-deep-researcher-mcp-server |
| LANGSMITH_TRACING | No | Enable LangSmith tracing | true |
| LANGSMITH_ENDPOINT | No | LangSmith API endpoint | https://api.smith.langchain.com |
| PERPLEXITY_API_KEY | No | Your Perplexity API key for web search functionality |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| research | Research a topic using web search and LLM synthesis |
| get_status | Get the current status of any ongoing research |
| configure | Configure the research parameters (max loops, LLM model, search API) |