Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RETRIESNoNumber of retries per provider call.2
LOG_FILENoPath to the persistent log file.data/research-mcp.log
MCP_HOSTNoHost to bind the MCP server.0.0.0.0
MCP_PORTNoPort to bind the MCP server.8000
LOG_LEVELNoLogging level (e.g., DEBUG, INFO, WARNING).INFO
EXA_API_KEYNoAPI key for the Exa search service.
SEARXNG_URLNoBase URL of the SearXNG instance (e.g., http://localhost:8080).
CRAWL4AI_URLNoBase URL of the Crawl4AI instance.
JINA_API_KEYNoOptional API key for Jina AI reader.
LOG_ROTATIONNoMaximum size for log file rotation.20 MB
LOG_RETENTIONNoRetention period for rotated log files.14 days
CRAWL4AI_TOKENNoToken for Crawl4AI authentication.
SERPER_API_KEYNoAPI key for the Serper.dev search service.
REQUEST_TIMEOUTNoTimeout (seconds) for upstream requests.30
TAVILY_1_API_KEYNoAPI key for the first Tavily instance.
TAVILY_2_API_KEYNoAPI key for the second Tavily instance (fallover).
FIRECRAWL_API_KEYNoAPI key for the Firecrawl service.
FALLBACK_MIN_CHARSNoMinimum characters for a read result to be accepted.500
READ_PAGES_CONCURRENCYNoConcurrent page reads for read_pages tool.5

Capabilities

Server capabilities have not been inspected yet.

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/vvzvlad/research-mcp'

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