Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HTTP_PROXYNoOptional HTTP proxy for API requests.
NCBI_EMAILYesRequired by NCBI API policy. Your email address.
S2_API_KEYNoOptional API key for Semantic Scholar. Alias: SEMANTIC_SCHOLAR_API_KEY
HTTPS_PROXYNoOptional HTTPS proxy for API requests.
CORE_API_KEYNoOptional API key for CORE. Get from https://core.ac.uk/services/api
EZPROXY_HOSTNoOptional EZproxy host, e.g., ezproxy.example.edu.
NCBI_API_KEYNoOptional API key for higher rate limits (10 req/s vs 3 req/s). Get from https://www.ncbi.nlm.nih.gov/account/settings/
CROSSREF_EMAILNoOptional email for CrossRef polite pool.
EZPROXY_ENABLEDNoOptional: set to 'true' after configuring EZPROXY_HOST and EZPROXY_COOKIE_FILE.
PUBMED_DATA_DIRNoOptional data directory for notes. Default: ~/.pubmed-search-mcp
UNPAYWALL_EMAILNoOptional email for Unpaywall OA resolver.
OPENALEX_API_KEYNoOptional API key for OpenAlex authenticated requests.
PUBMED_NOTES_DIRNoOptional target folder for save_literature_notes.
EZPROXY_COOKIE_FILENoOptional path to EZproxy cookies JSON file.
BROWSER_FETCH_CONFIGNoOptional JSON string enabling browser-session PDF fallback. Example: '{"enabled":true,"auto_enabled":true,"broker_url":"http://127.0.0.1:8766/fetch","token":"local-dev-token","allowed_hosts":["jamanetwork.com","*.jamanetwork.com"]}'
PUBMED_WORKSPACE_DIRNoOptional fallback workspace directory for notes.
SEMANTIC_SCHOLAR_API_KEYNoOptional alias for S2_API_KEY.
INSTITUTIONAL_DIRECT_FETCHNoOptional: set to 'true' to try DOI publisher pages before CORE fallback.
PUBMED_SEARCH_DISABLED_SOURCESNoOptional comma-separated list of sources to disable, e.g., 'semantic_scholar'.
PUBMED_ARTIFACT_INCLUDE_LOCAL_PATHSNoOptional: set to 'true' to include local_path and manifest_path in artifact responses.

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/u9401066/pubmed-search-mcp'

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