UBOS Asset Marketplace: mcp-graphql - Empowering LLMs with GraphQL

In the rapidly evolving landscape of Artificial Intelligence, Large Language Models (LLMs) are becoming increasingly pivotal. However, their true potential is often constrained by their ability to access and interact with real-world data and applications. The UBOS Asset Marketplace addresses this challenge head-on with mcp-graphql, a crucial tool that bridges the gap between LLMs and GraphQL APIs.

What is mcp-graphql?

mcp-graphql is a Model Context Protocol (MCP) server that enables LLMs to seamlessly interact with GraphQL APIs. It provides schema introspection and query execution capabilities, allowing models to dynamically discover and use GraphQL APIs. This unlocks a new realm of possibilities for AI agents, enabling them to access, process, and utilize data from diverse sources exposed through GraphQL.

At its core, MCP standardizes how applications provide context to LLMs. An MCP server acts as an intermediary, translating requests from the LLM into actions that can be performed on external data sources or tools. mcp-graphql specializes in translating those requests into GraphQL queries and mutations.

Key Features and Benefits

• Dynamic Schema Introspection: mcp-graphql can automatically introspect GraphQL schemas, allowing LLMs to understand the structure and capabilities of the API without requiring manual configuration.
• Query Execution: It enables LLMs to execute GraphQL queries against the target endpoint, retrieving the necessary data for their tasks.
• Mutation Support (Optional): With the --enable-mutations flag, mcp-graphql allows LLMs to perform mutations, enabling them to modify data through the GraphQL API (use with caution).
• Customizable Headers: The --headers argument allows you to specify custom headers for requests, enabling authentication and authorization with the GraphQL endpoint.
• Local Schema Support: For environments where introspection is not possible, mcp-graphql can use a local GraphQL schema file.
• Security Focused: Mutations are disabled by default, preventing unintended data modifications by LLMs.
• Easy Installation: Integrate seamlessly with Claude Desktop, either automatically via Smithery or manually through configuration.

Use Cases: Unleashing the Power of LLMs with GraphQL

The integration of mcp-graphql within the UBOS ecosystem unlocks a plethora of use cases, enabling AI agents to perform sophisticated tasks that were previously impossible.

• Data Retrieval and Analysis: LLMs can leverage mcp-graphql to retrieve data from various GraphQL endpoints, such as CRM systems, e-commerce platforms, and internal databases. This data can then be used for analysis, reporting, and decision-making.

  Example: An AI agent can query a CRM system via GraphQL to retrieve customer information, analyze their purchase history, and identify potential upsell opportunities.

• Automated Task Execution: By enabling mutations, mcp-graphql allows LLMs to automate tasks through GraphQL APIs. This can include creating new records, updating existing data, and triggering workflows.

  Example: An AI agent can automatically create a new support ticket in a helpdesk system via GraphQL when a customer reports an issue.

• Real-time Data Integration: mcp-graphql enables LLMs to access real-time data from GraphQL subscriptions, allowing them to react dynamically to changes in the environment.

  Example: An AI agent can monitor social media feeds via GraphQL subscriptions and respond to mentions of a company’s brand in real-time.

• Personalized Experiences: LLMs can use mcp-graphql to retrieve user-specific data from GraphQL APIs and personalize the user experience accordingly.

  Example: An AI agent can retrieve a user’s preferences from a GraphQL endpoint and recommend relevant products or services.

• Knowledge Base Integration: Integrate internal knowledge bases exposed via GraphQL to provide LLMs with access to crucial company information, enhancing their ability to answer complex questions and provide accurate support.

  Example: An AI agent can access product documentation and support articles through a GraphQL API to assist customers with troubleshooting.

• Financial Data Analysis: Access real-time stock prices, market data, and financial reports through GraphQL APIs, enabling LLMs to provide insightful financial analysis and investment recommendations.

  Example: An AI agent can analyze financial data via GraphQL and generate reports on market trends and investment opportunities.

• E-commerce Automation: Automate various e-commerce tasks, such as order processing, inventory management, and product updates, by connecting LLMs to e-commerce platforms via GraphQL.

  Example: An AI agent can automatically update product prices and inventory levels based on data retrieved from a GraphQL endpoint.

• Healthcare Applications: Access patient records, medical research data, and drug information through GraphQL APIs, enabling LLMs to assist healthcare professionals in diagnosis, treatment planning, and drug discovery.

  Example: An AI agent can analyze patient data via GraphQL and provide recommendations for personalized treatment plans.

Integrating mcp-graphql with UBOS

UBOS is a full-stack AI Agent development platform focused on bringing AI Agents to every business department. Our platform helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems. mcp-graphql seamlessly integrates into the UBOS ecosystem, providing a powerful mechanism for connecting your AI agents with external data sources.

Benefits of using mcp-graphql with UBOS:

• Centralized Agent Management: UBOS provides a centralized platform for managing and orchestrating your AI agents, including those that utilize mcp-graphql.
• Simplified Data Integration: UBOS simplifies the process of connecting your AI agents with various data sources, including GraphQL APIs.
• Enhanced Security: UBOS provides robust security features to protect your data and prevent unauthorized access.
• Scalability and Reliability: UBOS is designed to scale to meet the demands of enterprise environments.

Getting Started with mcp-graphql

Installation

You can install mcp-graphql either via Smithery or manually.

Installing via Smithery

bash npx -y @smithery/cli install mcp-graphql --client claude

Installing Manually

{ “mcpServers”: { “mcp-graphql”: { “command”: “npx”, “args”: [“mcp-graphql”, “–endpoint”, “http://localhost:3000/graphql”] } } }

Usage

Run mcp-graphql with the correct endpoint. It will automatically try to introspect your queries.

Command Line Arguments

Examples

bash

Basic usage with a local GraphQL server

npx mcp-graphql --endpoint http://localhost:3000/graphql

Using with custom headers

npx mcp-graphql --endpoint https://api.example.com/graphql --headers ‘{“Authorization”:“Bearer token123”}’

Enable mutation operations

npx mcp-graphql --endpoint http://localhost:3000/graphql --enable-mutations

Using a local schema file instead of introspection

npx mcp-graphql --endpoint http://localhost:3000/graphql --schema ./schema.graphql

Available Tools

The server provides two main tools:

1. introspect-schema: This tool retrieves the GraphQL schema. Use this first if you don’t have access to the schema as a resource. This uses either the local schema file or an introspection query.
2. query-graphql: Execute GraphQL queries against the endpoint. By default, mutations are disabled unless --enable-mutations is specified.

Resources

• graphql-schema: The server exposes the GraphQL schema as a resource that clients can access. This is either the local schema file or based on an introspection query.

Security Considerations

Mutations are disabled by default as a security measure to prevent an LLM from modifying your database or service data. Consider carefully before enabling mutations in production environments.

Customize for Your Own Server

This is a very generic implementation where it allows for complete introspection and for your users to do whatever (including mutations). If you need a more specific implementation, it’s suggested to create your own MCP and lock down tool calling for clients to only input specific query fields and/or variables. You can use this as a reference.

Conclusion

mcp-graphql is a powerful tool that empowers LLMs to interact with GraphQL APIs, unlocking a new realm of possibilities for AI agents. By integrating mcp-graphql with the UBOS platform, you can seamlessly connect your AI agents with external data sources, automate tasks, and personalize user experiences. Start leveraging the power of mcp-graphql today and unlock the full potential of your AI agents within the UBOS ecosystem.