graphql-introspection-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALLOW_MUTATIONS | No | Enable mutation execution (set to 'true' to enable) | false |
| CACHE_DURATION_MS | No | Cache duration in milliseconds (default: 300000) | 300000 |
| GRAPHQL_DEFAULT_ENDPOINT | No | Default GraphQL endpoint URL | http://localhost:5555/graphql |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_graphql_schemaB | Get complete GraphQL schema introspection |
| filter_queriesA | Filter and list available GraphQL queries |
| filter_mutationsB | Filter and list available GraphQL mutations |
| filter_typesB | Filter and list available GraphQL types |
| get_type_detailsB | Get detailed information about a specific GraphQL type |
| get_field_detailsB | Get detailed information about a specific query or mutation field |
| execute_queryA | Execute a read-only GraphQL query against the endpoint. Only query operations are allowed. |
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 7 tools
Each tool has a clearly distinct purpose: schema retrieval, filtering queries, mutations, types, and fetching details for types and fields, plus query execution. No overlap or ambiguity exists.
Tool names consistently follow a verb_noun pattern with snake_case: get_graphql_schema, filter_queries, filter_mutations, filter_types, get_type_details, get_field_details, execute_query. Naming is predictable and unified.
With 7 tools, the set is well-scoped for a GraphQL introspection server. Each tool covers a necessary aspect without redundancy, making the count appropriate.
The surface covers schema introspection, listing queries/mutations/types, and detailed field/type info, plus query execution. The only notable gap is the absence of a filter for subscriptions, but core workflows are fully covered.