Skip to main content
Glama
MCP-Mirror

Deep Research MCP Server

by MCP-Mirror

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CRAWL_LIMITNoTotal number of links the crawler will process starting from a single root URL before stopping.10
CRAWL_TIMEOUTNoTimeout in seconds for each Tavily Crawl request.180
SEARCH_TIMEOUTNoTimeout in seconds for Tavily search requests.60
TAVILY_API_KEYYesYour Tavily API key (required).
CRAWL_MAX_DEPTHNoMax 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_ENABLEDNoEnable file writing capability. Disabled by default for security reasons.false
MAX_SEARCH_RESULTSNoMaximum number of search results to retrieve and consider for crawling (1-20).7
ALLOWED_WRITE_PATHSNoComma-separated allowed directories for file writing operations (defaults to user home directory).
DOCUMENTATION_PROMPTNoYour 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_PATHNoPath 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_LIMITNoMaximum lines per file write operation.200

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MCP-Mirror/pinkpixel-dev_deep-research-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server