Skip to main content
Glama
HubSpot MCP

HubSpot MCP

hubspot_graphql_query

Read-onlyIdempotent

Run GraphQL queries against HubSpot CRM to fetch records, properties, and associations in one request, avoiding multiple REST calls.

Instructions

🟢 READ-ONLY · query · CRM GraphQL · POST /collector/graphql

Run a GraphQL query against HubSpot's CRM data graph and return the JSON result. Fetches records, properties and associations across objects in one round-trip — use it when a REST tool would need several calls or returns too much.

HubSpot's GraphQL endpoint supports queries only (no mutations), so this cannot change account data. Endpoint: https://api.hubapi.com/collector/graphql. Plan: Marketing Hub or Content Hub Professional/Enterprise. Scopes: collector.graphql_query.execute. Not available with a HubSpot service key; it needs a private app or OAuth token. Example: {"query": "query { CRM { contact_collection(limit: 3) { items { email firstname associations { company_collection__primary { items { name } } } } } } }"}

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "hubspot_graphql_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe GraphQL query document (queries only — HubSpot exposes no mutations).
variablesNoOptional variables object referenced by the query.
operationNameNoOptional operation name when the document defines several.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.1

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, yet the description adds real operational context on top: the concrete endpoint, the fact that no mutations exist server-side, the plan gate, and the OAuth/private-app auth requirement. That is exactly the kind of prerequisite information an agent cannot get from the annotation flags or the schema.

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

Conciseness4/5

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

The read-only marker, the verb and the endpoint are front-loaded before any caveats, and each sentence carries either the purpose, the selection rule, or a gating constraint. The status-badge/endpoint header and the scope string are mildly procedural but still operationally relevant, so there is little true waste.

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

Completeness4/5

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

For a pass-through GraphQL tool with no output schema, the description correctly avoids promising a fixed return shape and instead shows a sample document whose result shape is self-evident. Access gating and the no-mutations limit are covered; only pagination/error-surface behavior is left unstated, which is minor here.

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 coverage is 100% and each of query, variables and operationName is already documented in the schema, so the schema carries the semantic burden. The worked example illustrates a realistic query document and reinforces the queries-only constraint, but the description adds no meaning for `variables` or `operationName` beyond what the schema states.

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

Purpose5/5

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

States a specific verb and resource ('Run a GraphQL query against HubSpot's CRM data graph'), plus what comes back ('return the JSON result'). It also carves out its niche versus REST tools ('use it when a REST tool would need several calls or returns too much'), so an agent can pick it apart from hubspot_api_request without opening either schema.

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?

Gives a clear selection rule (multi-object fetches in one round-trip) and an implied exclusion because it is query-only, plus concrete prerequisites: Professional/Enterprise plan, collector.graphql_query.execute scope, and no service-key auth. It stops short of naming a specific sibling tool as the alternative, so the routing is by category rather than by name.

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