Skip to main content
Glama
monday-graphql-mcp

monday-graphql-mcp

by ataliarf

monday-graphql-mcp

Ein MCP-Server, der Entwicklern hilft, mit der monday.com GraphQL API zu arbeiten – Query-Validierung, Spaltenwertformate, Fehlererklärungen, Live-Schema-Introspektion und Code-Scaffolding, alles direkt von Ihrem KI-Assistenten.

Tools

Tool

API-Schlüssel erforderlich

Beschreibung

column_value_format

Nein

Exaktes JSON-Lese-/Schreibformat für jeden Spaltentyp

explain_error

Nein

API-Fehler entschlüsseln und einen Korrekturvorschlag erhalten

scaffold

Nein

Boilerplate-Code für Integrationen, Webhooks, OAuth und Apps

validate_query

Optional

Syntaxprüfung, Komplexitätsschätzung und Lint-Warnungen

get_schema

Ja

Live-Schema-Introspektion, nach Stichwort filterbar

run_query

Ja

Eine Query oder Mutation gegen die API ausführen

Related MCP server: mcp-graphql-tools

Einrichtung

1. Installieren und erstellen

git clone <repo-url> monday-graphql-mcp
cd monday-graphql-mcp
npm install
npm run build

2. Zu Claude Code hinzufügen

Fügen Sie dies in Ihre ~/.claude/settings.json unter mcpServers ein:

{
  "mcpServers": {
    "monday-graphql-mcp": {
      "command": "node",
      "args": ["/path/to/monday-graphql-mcp/dist/index.js"],
      "env": {
        "MONDAY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Holen Sie sich Ihren API-Schlüssel: monday.com → Avatar → Administration → API.

Starten Sie Claude Code neu, nachdem Sie die Konfiguration aktualisiert haben.

3. Ohne API-Schlüssel verwenden

column_value_format, explain_error und scaffold funktionieren sofort ohne API-Schlüssel.


Anwendungsbeispiele

Das exakte Format für einen Spaltentyp abrufen

How do I write a people column value?
→ uses column_value_format({ column_type: "people" })
{
  "personsAndTeams": [{ "id": 12345678, "kind": "person" }]
}

Einen API-Fehler entschlüsseln

I'm getting "ColumnValueException: invalid value" — what's wrong?
→ uses explain_error({ error: "...", query: "..." })

Eine Query vor der Ausführung validieren

query {
  boards(ids: [123]) {
    items_page(limit: 500) {
      items {
        id
        name
        column_values { id text value }
        subitems { id name }
      }
    }
  }
}
→ validate_query flags:
  - Estimated complexity: ~4200 (HIGH — likely to hit limits)
  - limit: 500 is the hard cap, but combined with subitems + all column_values this is expensive
  - Fetching all column_values without ids filter — add ids: ["col1"] to reduce complexity
  - Fetching subitems + column_values together — consider two separate queries

Boilerplate generieren

Scaffold a TypeScript webhook listener for monday.com
→ uses scaffold({ type: "webhook-listener", language: "typescript" })

Scaffold-Typen: api-client, webhook-listener, oauth-flow, integration, board-view, dashboard-widget
Sprachen: typescript, javascript, python

Das Live-Schema abrufen

Show me the monday.com schema for item-related types
→ uses get_schema({ filter: "item" })

Eine Query ausführen

query {
  me {
    id
    name
    email
  }
}
→ uses run_query({ query: "..." })

Unterstützte Spaltentypen

text · long_text · numbers · status · people · date · timeline · checkbox · dropdown · link · email · phone · rating · country · board_relation · dependency · tags · hour · week · world_clock · color_picker · location · formula · mirror · auto_number · creation_log · last_updated · item_id · vote · files · subtasks


Entwicklung

npm run dev      # run with tsx (no build step)
npm run build    # compile TypeScript to dist/
npm start        # run compiled output

Der Server kommuniziert über stdin/stdout mithilfe des MCP-Protokolls – er ist dafür ausgelegt, von einem MCP-Host (Claude Code, Claude Desktop usw.) gestartet zu werden und nicht direkt in einem Terminal ausgeführt zu werden.

Available Tools

6 tools
column_value_formatA

Returns the exact read and write JSON format for any monday.com column type. No API key required. Use this whenever you need to know how to read or write a column value.

Inputs: column_type (required).

explain_errorA

Explains a monday.com API error response in plain language and suggests a fix. Paste the error JSON or message. No API key required.

Inputs: error (required), query.

get_schemaA

Fetches the live monday.com GraphQL schema and returns type definitions, available queries, and mutations. Requires a monday.com API key.

Inputs: filter, api_key.

run_queryB

Executes a GraphQL query or mutation against the monday.com API and returns the result. Requires a monday.com API key.

Inputs: query (required), api_key, variables.

scaffoldA

Generates ready-to-use boilerplate code for monday.com integrations and apps. No API key required.

Inputs: type (required), language (required), description.

validate_queryA

Validates a monday.com GraphQL query: checks syntax, estimates complexity, and flags common pitfalls. Optionally validates against the live schema when an API key is provided.

Inputs: query (required), api_key.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct use case: schema retrieval, query execution, query validation, column formatting, error explanation, and scaffolding. There is minimal conceptual overlap between them, and the descriptions make the boundaries clear.

    Naming Consistency4/5

    Most tools use a clear verb_noun pattern (get_schema, validate_query, run_query, explain_error, scaffold), but column_value_format deviates by being a noun phrase rather than an action-oriented name. This is a minor inconsistency and does not prevent readability.

    Tool Count5/5

    Six tools is a well-scoped set. Each tool addresses a distinct part of the monday.com GraphQL development workflow, and none feel redundant or unnecessary.

    Completeness5/5

    The set covers the full developer workflow: retrieving schema, validating queries, executing queries, understanding column value formats, troubleshooting errors, and generating boilerplate code. Since run_query handles arbitrary GraphQL operations, there are no obvious dead ends.

    Related MCP Connectors

    Related MCP Servers