Skip to main content
Glama
HubSpot MCP

HubSpot MCP

hubspot_invoke_endpoint

Destructive

Invoke any HubSpot API endpoint from the registry by name with schema-matched arguments. Fetch endpoint details first, then call it to perform reads or writes, confirming destructive actions.

Instructions

๐ŸŸก WRITE-CAPABLE ยท invoke a catalog endpoint

Call any endpoint in the registry by name with arguments matching its input schema (fetch it first via hubspot_get_endpoint).

The registry includes ๐ŸŸก write and ๐Ÿ”ด destructive endpoints. Check the endpoint's banner first and confirm with the user before any destructive call (delete / merge / GDPR purge / send).

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": {
      "name": "<name>"
    },
    "name": "hubspot_invoke_endpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesEndpoint tool name from the catalog.
argumentsNoArguments matching the endpoint's input schema.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.1

TDQS

A3.8/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is known. The description adds real value on top: it warns that the registry mixes write and destructive endpoints, enumerates the dangerous categories (delete / merge / GDPR purge / send), and mandates user confirmation first. It does not state rate-limit, idempotency, or auth behavior, keeping it below a 5.

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 banner is front-loaded and the body is two short paragraphs with no filler. Slight redundancy exists in repeating the safety tier ('write-capable') alongside the per-endpoint banner guidance, but the structure serves scanning well.

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?

For a generic passthrough with an unconstrained nested 'arguments' object and no output schema, the description covers selection and safety but says nothing about what comes back โ€” whether the raw endpoint response, an error envelope, or a wrapped payload. Given the open-world passthrough nature and the absence of an output schema, one line on the return shape would materially help the agent interpret results.

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 both parameters are already documented, and the description largely restates that arguments must match the endpoint's input schema. With only two parameters and full schema coverage, the required baseline of 3 applies โ€” no additional syntax, format, or nesting guidance is provided for the free-form 'arguments' object.

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 uses a specific verb+resource ('invoke a catalog endpoint') and immediately clarifies the mechanism: call any registry endpoint by name with schema-matching arguments. It also names the sibling hubspot_get_endpoint as the way to discover schemas, which distinguishes it from the fetch-schema tool, though it does not differentiate it from hubspot_api_request.

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?

It gives a clear prerequisite ('fetch it first via hubspot_get_endpoint'), a pre-call safety check ('check the endpoint's banner first'), and a user-confirmation rule for destructive operations. What's missing is an explicit statement of when to prefer this over hubspot_api_request, the other direct-call sibling.

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