About Fibery MCP GraphQL Server
Fibery MCP GraphQL Server helps LLMs construct valid GraphQL queries and mutations for a Fibery account. It provides schema discovery and validation tools for teams and developers working with Fibery’s GraphQL API.
Key features
- 01List Fibery spaces and types
- 02Retrieve a space’s GraphQL schema SDL
- 03Validate queries and mutations against a schema
Use cases
- 01Inspect available Fibery spaces and types
- 02Retrieve schema details before writing a query
- 03Check generated GraphQL before using it
MCP support
The MCP server exposes Fibery GraphQL introspection and validation tools to MCP clients, using the configured Fibery account and API credentials.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEFibery MCP GraphQL Server
This is a Model Context Protocol (MCP) server that provides tools to introspect the Fibery GraphQL API to help your LLM to write valid graphql queries and mutations.
Features
- List Spaces and Types: Fetches and lists all available GraphQL spaces and types in your Fibery account
- Get Schema SDL: Gets the complete GraphQL schema SDL for a Fibery space
- Validate Fibery GraphQL: Validates a generated GraphQL query or mutation for Fibery against the known schema
Prerequisites
- Node.js (v20 or higher)
- Fibery account with API access
Using with MCP Clients
This server implements the Model Context Protocol and can be used with any MCP-compatible client. The MCP endpoint is available at:
{
"mcpServers": {
"fibery-mcp-graphql": {
"command": "node", // note: if using nvm, use the full path to the version of node you want to use
"args": ["/full-path-to/index.js"],
"env": {
"FIBERY_TOKEN": "your_fibery_token",
"FIBERY_URL": "your_fibery_domain.fibery.io"
}
}
}
}
Installation
- Clone the repository
- Install dependencies:
bun install
MCP Tools
list_spaces_and_types
Lists all available GraphQL spaces and types in your Fibery account.
Parameters: None
Response:
{
"spaces": [
{
"name": "Space Name",
"url": "https://your-domain.fibery.io/api/graphql/space/Space_Name",
"id": "Space_Name"
},
...
],
"count": 5
}
get_schema_sdl
Gets the complete GraphQL schema SDL for a Fibery space. This includes all type definitions, queries, mutations, etc.
Parameters:
space_id: The ID of the space to get the schema for (required)
Response:
{
"space_id": "Space_Name",
"sdl": "type Query { ... } type Mutation { ... } ..."
}
validate_fibery_graphql
Validates a generated GraphQL query or mutation for Fibery against the known schema. Returns any validation errors.
Parameters:
space_id: The ID of the space to validate against (required)query_to_validate: The GraphQL query or mutation to validate (required)
Response:
{
"valid": true,
"errors": []
}
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.