Skip to main content
Glama
igagansingh

understanding-mcp

by igagansingh

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_URLNoCanonical URI of the MCP server. Everything else (listen port, endpoint path, resource audience, well-known metadata path) is derived from it.http://localhost:3001/mcp
AUTH_DCRNooff → registration_endpoint is not advertised and /register is disabled (forces the preconfigured-client path).on
MCP_PORTNoOverride for the MCP server's listen port.(from MCP_URL)
AUTH_PORTNoPort of the authorization server.3002
MCP_BASE_URLNoOverride for the origin used to build well-known URLs.(origin of MCP_URL)
MCP_ENDPOINTNoOverride for the MCP endpoint path.(path of MCP_URL)
AUTH_BASE_URLNoIssuer of the authorization server.http://localhost:3002
TOKEN_TTL_SECONDSNoAccess token lifetime.3600
PRECONFIGURED_CLIENT_IDNoStatic client_id available without registration (public client, no secret).preconfigured-client
DCR_ALLOWED_REDIRECT_URISNoComma-separated whitelist. When set, DCR rejects any redirect_uri not on the list.(empty = allow any)
WWW_AUTH_RESOURCE_METADATANooff → 401 challenges omit resource_metadata, forcing the client to construct the well-known URI itself.on
PRECONFIGURED_REDIRECT_URISNoredirect_uris allowed for the preconfigured client.http://localhost:8899/callback

Instructions

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.

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/igagansingh/understanding-mcp'

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