Skip to main content
Glama
groq

groq-compound-mcp-server

Official
by groq
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

groq-compound-mcp-server

Provides a Model Context Protocol (MCP) server for interacting with Groq models, including compound/meta models.

This server exposes the following tools:

  • ask_with_realtime_information

  • ask_with_code_execution

Prerequisites

  • Node.js >= 18.0.0

  • A Groq API key set in the GROQ_API_KEY environment variable.

Related MCP server: MCP-GROQ

Installation

npm install groq-compound-mcp-server

Usage

This server follows the standard MCP server pattern using stdio for transport. It's designed to be run by an MCP client (like Claude Desktop or a custom client).

Refer to the official MCP Quickstart for Server Developers for instructions on setting up and connecting MCP servers.

When configuring your client, use the command npx groq-compound-mcp-server or groq-compound-mcp-server (if installed globally) to run this server.

Here's an example of how you might configure an MCP client (e.g., in a settings.json file) to launch this server:

{
  "mcpServers": {
    "groq-compound": {
      "command": "npx",
      "args": [
        "-y",
        "groq-compound-mcp-server"
      ],
      "env": {
        "GROQ_API_KEY": "YOUR_GROQ_API_KEY_HERE"
      }
    }
  }
}

Hosting on Vercel

This server can also be deployed to Vercel.

  1. Prerequisites:

    • Ensure you have a Vercel account.

    • Connect your Git repository to Vercel.

  2. Environment Variables: Set the following environment variables in your Vercel project settings:

    • GROQ_API_KEY: Your Groq API key.

    • REDIS_URL: (Recommended for SSE transport) The connection URL for a Redis instance (e.g., from Vercel KV or Upstash).

  3. Build Configuration: Vercel should automatically detect it as a Next.js application. The build command npm run build:vercel (or yarn build:vercel/pnpm build:vercel) and the output directory (.next) will be used.

  4. Accessing the MCP Server: Once deployed, your MCP server endpoints will be available at https://your-deployment-url.vercel.app/api/mcp. For example, the SSE endpoint would be https://your-deployment-url.vercel.app/api/mcp/sse.

Development with Vercel CLI

To run the Vercel deployment locally:

  1. Install Vercel CLI: npm install -g vercel

  2. Set up environment variables locally (e.g., in a .env.local file at the project root):

    GROQ_API_KEY=your_groq_api_key
REDIS_URL=your_redis_url

  3. Run the development server: vercel dev or npm run dev:vercel.

License

MIT

Available Tools

2 tools
ask_with_code_executionA

Ask questions that benefit from Python REPL interaction (e.g., for intermediate calculations or code execution).

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYesThe question to ask the model, especially one that benefits from Python REPL interaction (e.g., for intermediate calculations or code execution).
modelNoThe model to use (compound-beta or compound-beta-mini). Defaults to compound-beta. Use compound-beta-mini for quick answers.compound-beta
modeNoResponse mode ('minimal' or 'verbose'). Defaults to 'minimal'. 'verbose' includes executed tools in the response. This is very verbose and should only be used when the user asks for it or when the user query cannot be answered without it (always first try without it).minimal
include_domainsNoList of domains to specifically include in the search.
exclude_domainsNoList of domains to exclude from the search.

TDQS

A3.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must fully disclose behavioral traits. It mentions Python REPL interaction but fails to describe execution details (e.g., sandbox, persistence, side effects, rate limits). The behavior of the code execution remains opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. Every part contributes to explaining the tool's purpose and ideal use case.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 parameters, no output schema, and no annotations, the description is insufficiently complete. It does not explain the purpose of key parameters like 'model' or 'mode', nor does it clarify what the tool returns after execution.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The tool description does not add meaning beyond the schema; it merely reiterates the code execution context without elaborating on how parameters like 'model' or 'mode' affect the tool's behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Ask') and specifies the resource ('questions that benefit from Python REPL interaction'). It clearly distinguishes from the sibling tool 'ask_with_realtime_information' by highlighting code execution capabilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states that the tool is for questions benefiting from Python REPL interaction, which gives clear context on when to use it. However, it does not explicitly explain when not to use it or directly compare with the sibling tool, missing exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ask_with_realtime_informationB

Ask a question requiring real-time information (e.g., news, current events) using a Groq model.

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYesThe question to ask the model, especially if it requires real-time information (e.g., current news, recent events).
modelNoThe model to use (compound-beta or compound-beta-mini). Defaults to compound-beta. Use compound-beta-mini for quick answers.compound-beta
modeNoResponse mode ('minimal' or 'verbose'). Defaults to 'minimal'. 'verbose' includes executed tools in the response. This is very verbose and should only be used when the user asks for it or when the user query cannot be answered without it (always first try without it).minimal
include_domainsNoList of domains to specifically include in the search.
exclude_domainsNoList of domains to exclude from the search.

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral disclosure. It states the tool uses a Groq model but does not explain whether it performs web searches, has latency, or requires network access. The presence of include/exclude domains suggests search functionality, but this is not explicitly stated, leading to potential misuse.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, one sentence long, with the core purpose front-loaded. It avoids unnecessary words and is easy to parse. Minor improvement could be splitting into two sentences for better structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of an output schema and the complexity of 5 parameters (some with enums), the description should provide more context, such as what the tool returns (e.g., an answer, possibly with citations) and when it might fail (e.g., non-real-time questions). It currently omits these details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, providing baseline clarity. The description adds meaningful context beyond the schema, such as recommending compound-beta-mini for quick answers and advising verbose mode only when necessary, which helps the agent choose appropriate parameter values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: asking a question requiring real-time information using a Groq model, with examples like news and current events. It distinguishes itself from the sibling tool 'ask_with_code_execution' by focusing on real-time data needs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide guidance on when to use this tool versus alternatives. It neither mentions when not to use it nor contrasts with the sibling tool. The lack of usage context leaves the agent to infer when real-time information is needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.7
    • First observedask_with_code_execution
    • First observedask_with_realtime_information
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: one for code execution, the other for real-time information. No overlap in functionality.

Naming Consistency5/5

Both tools follow a consistent 'ask_with_' prefix pattern, making it predictable for agents to select the right tool.

Tool Count4/5

Two tools is slightly thin for a 'compound' server, but each tool covers a distinct, specialized need. The count is reasonable but could be expanded.

Completeness3/5

The server covers code execution and real-time info, but lacks a general knowledge query tool. This is a notable gap for a question-answering server.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

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/groq/compound-mcp-server'

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