What does QuerySculptor do differently from raw GraphQL query generation?
QuerySculptor provides structured MCP tools that let agents build, validate, and execute queries step-by-step rather than generating complete query strings at once.
@flinstonedev
基本情報
QuerySculptor is a GraphQL query builder designed for AI agents that provides 26 structured tools via the Model Context Protocol (MCP). Instead of generating complex GraphQL queries from scratch, AI agents can build queries step-by-step with real-time validation, schema introspec
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"querysculptor": {
"command": "npx",
"args": [
"mcp-remote",
"https://agent-query-builder-toolbox.vercel.app/mcp",
"--allow-http"
]
}
}
}Retrieve the complete GraphQL schema definition for API understanding and exploration
Discover the available root operation types (Query, Mutation, Subscription) and their entry points
Get detailed information about a specific GraphQL type including fields, descriptions, and relationships
Get detailed information about a specific field within a GraphQL type including arguments and return type
Get guidance and field information for GraphQL input object types to help with argument construction
Initialize a new GraphQL query building session with persistent state management
Clean up and close a GraphQL query building session to free resources
Visualize the current GraphQL query structure and generated query string for debugging and review
Get suggestions for available fields that can be selected at a specific path in the query structure
Add a field to the GraphQL query structure with optional aliasing and validation
Add multiple fields to the GraphQL query structure in a single operation for efficiency
Define a GraphQL variable with its type and optional default value for use in the query
Assign a runtime value to a previously defined GraphQL variable for query execution
Remove a previously defined GraphQL variable from the query structure
Set string or enum arguments on GraphQL fields with automatic type detection and validation
Sets a typed argument (number, boolean, null) on a field in the GraphQL query structure.
Set nested properties within GraphQL input object arguments for complex data structures
Set a field argument to reference a GraphQL variable instead of a literal value
Create reusable named fragments for common field selections across queries
Apply a previously defined named fragment to a specific location in the query
Apply type-conditional field selections using inline fragments for union/interface types
Add GraphQL directives like @include or @skip to fields for conditional selection
Add directives to the root operation for query-level behavior control
Validate the built GraphQL query against the schema for syntax and semantic correctness
Execute the built GraphQL query against the configured endpoint and return results
Analyze the complexity, depth, and performance characteristics of the current query structure
Get current rate limit status for the client
QuerySculptor is a server application that helps AI agents interact with GraphQL APIs through structured tools instead of raw query generation. It provides 26 tools via the Model Context Protocol (MCP) for building, validating, and executing GraphQL queries step-by-step. It is designed for developers using AI agents like Cursor.
Add the public demo endpoint to your Cursor mcp.json configuration. For local setup, clone the repository, run pnpm install, copy example.env to .env and customize, then launch with vercel dev. The server becomes available at http://localhost:3000/mcp.
QuerySculptor provides structured MCP tools that let agents build, validate, and execute queries step-by-step rather than generating complete query strings at once.
The server uses Node.js with pnpm and is deployed on Vercel. Clone the repo and install dependencies with `pnpm install`.
The demo is pre-configured to use the public Pokemon API (graphql-pokeapi.vercel.app). No local database is required.
Yes, the MCP endpoint is `https://agent-query-builder-toolbox.vercel.app/mcp` and works with the Pokemon API out of the box.
It uses HTTP via MCP, exposed as a URL endpoint (e.g., `/mcp`). No other transports or authentication are mentioned in the README.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
MCP Toolbox for Databases is an open source MCP server for databases.
A curated list of references for MLOps
A search tool helps dev to solve the naming things problem.
Open-source MCP to use Blender with any LLM
コメント