Skip to main content
Glama
deenesjakoruzh
blurrah

mcp-graphql

by blurrah
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

mcp-graphql

значок кузнеца

Сервер Model Context Protocol, который позволяет LLM взаимодействовать с API GraphQL. Эта реализация обеспечивает возможности интроспекции схемы и выполнения запросов, позволяя моделям динамически обнаруживать и использовать API GraphQL.

Использование

Запустите mcp-graphql с правильной конечной точкой, он автоматически попытается проанализировать ваши запросы.

Переменные среды (критическое изменение в версии 1.0.0)

Примечание: Начиная с версии 1.0.0 аргументы командной строки заменены переменными среды.

Переменная среды

Описание

По умолчанию

ENDPOINT

URL-адрес конечной точки GraphQL

http://localhost:4000/graphql

HEADERS

Строка JSON, содержащая заголовки для запросов

{}

ALLOW_MUTATIONS

Включить операции мутации (по умолчанию отключено)

false

NAME

Имя MCP-сервера

mcp-graphql

SCHEMA

Путь к локальному файлу схемы GraphQL (необязательно)

-

Примеры

# Basic usage with a local GraphQL server
ENDPOINT=http://localhost:3000/graphql npx mcp-graphql

# Using with custom headers
ENDPOINT=https://api.example.com/graphql HEADERS='{"Authorization":"Bearer token123"}' npx mcp-graphql

# Enable mutation operations
ENDPOINT=http://localhost:3000/graphql ALLOW_MUTATIONS=true npx mcp-graphql

# Using a local schema file instead of introspection
ENDPOINT=http://localhost:3000/graphql SCHEMA=./schema.graphql npx mcp-graphql

Related MCP server: mcp4gql

Ресурсы

  • graphql-schema : Сервер выставляет схему GraphQL как ресурс, к которому клиенты могут получить доступ. Это либо локальный файл схемы, либо основанный на запросе интроспекции.

Доступные инструменты

Сервер предоставляет два основных инструмента:

  1. introspect-schema : Этот инструмент извлекает схему GraphQL. Используйте его в первую очередь, если у вас нет доступа к схеме как к ресурсу. Он использует либо локальный файл схемы, либо запрос интроспекции.

  2. query-graphql : Выполнение запросов GraphQL к конечной точке. По умолчанию мутации отключены, если ALLOW_MUTATIONS не установлен в true .

Установка

Установка через Smithery

Чтобы автоматически установить GraphQL MCP Server для Claude Desktop через Smithery :

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

Установка вручную

Его можно вручную установить на Клода:

{
    "mcpServers": {
        "mcp-graphql": {
            "command": "npx",
            "args": ["mcp-graphql"],
            "env": {
                "ENDPOINT": "http://localhost:3000/graphql"
            }
        }
    }
}

Соображения безопасности

Мутации отключены по умолчанию в качестве меры безопасности, чтобы не дать LLM изменить вашу базу данных или данные сервиса. Тщательно подумайте, прежде чем включать мутации в производственных средах.

Настройте под свой сервер

Это очень общая реализация, которая позволяет проводить полную интроспекцию и делать что угодно для ваших пользователей (включая мутации). Если вам нужна более конкретная реализация, я бы предложил просто создать свой собственный MCP и заблокировать вызов инструмента для клиентов, чтобы они вводили только определенные поля запроса и/или переменные. Вы можете использовать это в качестве справочного материала.

Available Tools

2 tools
introspect-schemaA

Introspect the GraphQL schema, use this tool before doing a query to get the schema information if you do not have it available as a resource already.

ParametersJSON Schema
NameRequiredDescriptionDefault
endpointNoOptional: Override the default endpoint, the already used endpoint is: http://localhost:3000/graphql
headersNoOptional: Add additional headers, the already used headers are: {}

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. The description mentions timing ('before doing a query') but doesn't explain what the introspection actually returns, whether it's a one-time operation or cached, what format the schema information comes in, or any authentication/rate limit considerations. For a tool with zero annotation coverage, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose ('Introspect the GraphQL schema') followed by usage guidance. Every word earns its place with no redundancy or unnecessary elaboration. The structure is clear and appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no output schema and no annotations, the description should do more to explain what the introspection returns and any behavioral considerations. While it adequately covers purpose and basic usage, it lacks details about the return format, error conditions, or operational characteristics that would help an agent use it effectively. The description is minimally viable but has clear gaps in completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters thoroughly with descriptions of their optional nature and default values. The description adds no parameter-specific information beyond what's in the schema. With high schema coverage, the baseline score of 3 is appropriate since the description doesn't need to compensate for schema gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('introspect') and resource ('GraphQL schema'), and specifies the purpose is to 'get the schema information'. It distinguishes from the sibling tool 'query-graphql' by indicating this is for schema discovery rather than query execution. However, it doesn't explicitly contrast with the sibling beyond implied timing ('before doing a query').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use this tool: 'before doing a query to get the schema information if you do not have it available as a resource already'. It implies an alternative (having the schema as a pre-existing resource) and gives timing guidance. However, it doesn't explicitly state when NOT to use it or provide detailed comparison with the sibling tool beyond the basic distinction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

query-graphqlC

Query a GraphQL endpoint with the given query and variables

ParametersJSON Schema
NameRequiredDescriptionDefault
endpointNoOptional: Override the default endpoint, the already used endpoint is: http://localhost:3000/graphql
headersNoOptional: Add additional headers, the already used headers are: {}
queryYes
variablesNo

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the action but lacks details on permissions, rate limits, error handling, or response format. This is inadequate for a tool that interacts with an external endpoint, leaving significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It is appropriately sized and front-loaded, directly stating the tool's purpose without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of querying a GraphQL endpoint, no annotations, no output schema, and incomplete parameter documentation, the description is insufficient. It fails to address critical aspects like authentication, response structure, or error scenarios, making it incomplete for effective tool use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (2 out of 4 parameters have descriptions). The description adds minimal value beyond the schema, as it only mentions 'query and variables' without explaining their formats or relationships. It doesn't compensate for the undocumented parameters (query and variables lack schema descriptions), resulting in a baseline score due to partial coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Query') and resource ('a GraphQL endpoint'), specifying what the tool does. It distinguishes from the sibling 'introspect-schema' by focusing on general query execution rather than schema introspection, though it doesn't explicitly mention this distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention the sibling tool 'introspect-schema' or any other context for selection. It simply states the action without usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedintrospect-schema
    • First observedquery-graphql
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: introspect-schema retrieves schema information, while query-graphql executes queries. There is no overlap or ambiguity between them, making it easy for an agent to select the correct tool.

Naming Consistency3/5

The tools use a verb-noun pattern (introspect-schema, query-graphql), which is consistent. However, the hyphenated naming style is less common than snake_case or camelCase, and with only two tools, it's hard to assess full consistency, but they follow the same convention.

Tool Count2/5

With only two tools, the server feels thin for a GraphQL domain, which typically involves operations like mutations, subscriptions, or schema updates. While core querying is covered, the scope is limited, potentially requiring agents to work around missing functionality.

Completeness2/5

The server covers basic introspection and querying but lacks essential GraphQL operations like mutations (for data modification) or subscriptions (for real-time updates). This creates significant gaps that could lead to agent failures when full lifecycle management is needed.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • gqai

    fotoetienne
    A
    license
    Not graded
    quality
    D
    maintenance
    Turn any GraphQL endpoint into a set of MCP tools
    23
    MIT

  • mcp4gql

    jorgeraad
    A
    license
    A
    quality
    D
    maintenance
    GraphQL MCP Server that acts as a bridge allowing MCP clients (like Cursor or Claude Desktop) to interact with target GraphQL APIs through standard tools for schema introspection and operation execution.
    2
    13 npm
    3
    MIT

  • mcp-graphql-forge

    toolprint
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP that can proxy any GraphQL API and expose graphql operations as mcp tools.
    13 npm
    18
    Apache 2.0

  • mcp-graphql-enhanced

    letoribo
    A
    license
    A
    quality
    A
    maintenance
    Enhanced MCP server for GraphQL with filtered introspection and full variable support.
    85
    2
    27,915 npm
    6
    MIT

Appeared in Searches