Text-to-GraphQL MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_HOST | No | Server host address | 127.0.0.1 |
| API_PORT | No | Server port | 8000 |
| MODEL_NAME | No | OpenAI model to use | gpt-4o |
| OPENAI_API_KEY | Yes | OpenAI API key for LLM operations | |
| GRAPHQL_API_KEY | Yes | API key for your GraphQL service | |
| GRAPHQL_HEADERS | No | Custom headers as JSON (overrides auto-auth) | {} |
| RECURSION_LIMIT | No | Max recursion for agent workflow | 10 |
| GRAPHQL_ENDPOINT | Yes | GraphQL API endpoint URL | |
| GRAPHQL_AUTH_TYPE | No | Authentication method: bearer, apikey, or direct | bearer |
| MODEL_TEMPERATURE | No | Model temperature for responses | 0 |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_graphql_queryB | Generate a GraphQL query from natural language description |
| validate_graphql_queryC | Validate and update a GraphQL query |
| execute_graphql_queryB | Execute a GraphQL query and optionally visualize the results |
| get_query_historyA | Retrieve the history of all queries Returns: JSON string containing all query history |
| get_query_examplesA | Get example queries to help users understand what they can ask for Returns: JSON string containing example queries |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: execute queries, generate from natural language, retrieve examples, view history, and validate. No overlap or ambiguity.
All tools follow a consistent verb_noun pattern with snake_case, e.g., 'execute_graphql_query', 'generate_graphql_query'. No mixing of conventions.
Five tools cover the core operations for GraphQL query management (generate, validate, execute, retrieve history and examples) without being excessive or insufficient.
The tool surface provides a complete workflow: natural language generation, validation, execution, history tracking, and example discovery. No obvious gaps in the stated domain.