Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_API_KEYYesAPI key for the OpenAI-compatible LLM endpoint (defaults to Groq)
TAVILY_API_KEYYesAPI key for Tavily search

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
verified_searchA

Finds real things matching a query — products, opportunities, tickets, jobs, events, whatever — by running a real web search and having a model restructure ONLY what that search actually returned into the JSON shape you specify. Every item's source field is checked in code against the literal URLs the search returned, so a result can't be invented or hallucinated: if the model can't back a claim with a real fetched page, that item is dropped rather than guessed at. Give it a plain-language query and a JSON Schema for one result item (sourceField, default "sourceUrl", is added automatically if you don't include it).

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/Hemanth-hexo/groundtruth_mcp'

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