Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RESEARCH_MCP_CONTACTNoEmail for scholarly-API polite pools and to enable the Unpaywall OA resolver
RESEARCH_MCP_BRAVE_KEYNoBrave Search API key → reliable backend for web-search (free tier)
RESEARCH_MCP_CACHE_DIRNoWhere retrieved files and API responses are cached
RESEARCH_MCP_USER_AGENTNoOverride the browser User-Agent used by fetch-url
RESEARCH_MCP_ZOTERO_URLNoOverride the Zotero local API base (default http://localhost:23119/api)
RESEARCH_MCP_SEARXNG_URLNoA SearXNG instance URL → self-hosted backend for web-search
RESEARCH_MCP_OBSIDIAN_VAULTNoPath to an Obsidian vault → activates the vault-* tools
RESEARCH_MCP_SEARCH_BACKENDNoForce web-search backend: duckduckgo (default, keyless best-effort), brave, or searxng

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/simonives/research_mcp'

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