Schema | Deep Research MCP Server

Deep Research MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CRAWL_LIMIT`	No	Total number of links the crawler will process starting from a single root URL before stopping.	10
`CRAWL_TIMEOUT`	No	Timeout in seconds for each Tavily Crawl request.	180
`SEARCH_TIMEOUT`	No	Timeout in seconds for Tavily search requests.	60
`TAVILY_API_KEY`	Yes	Your Tavily API key (required).
`CRAWL_MAX_DEPTH`	No	Max depth of the crawl from the base URL. 0 means only the base URL, 1 means the base URL and links found on it.	1
`FILE_WRITE_ENABLED`	No	Enable file writing capability. Disabled by default for security reasons.	false
`MAX_SEARCH_RESULTS`	No	Maximum number of search results to retrieve and consider for crawling (1-20).	7
`ALLOWED_WRITE_PATHS`	No	Comma-separated allowed directories for file writing operations (defaults to user home directory).
`DOCUMENTATION_PROMPT`	No	Your custom, detailed instructions for the LLM on how to generate markdown documents from the research data. Overrides the server's built-in default prompt.
`RESEARCH_OUTPUT_PATH`	No	Path where research documents and images should be saved. If not set, a timestamped folder in the user's Documents directory will be used.
`FILE_WRITE_LINE_LIMIT`	No	Maximum lines per file write operation.	200

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed