Skip to main content
Glama
nubiia-dev

@iamsamuelfraga/mcp-hubspot

by nubiia-dev

hubspot_crm_search

Search HubSpot CRM records across all object types using filters, sorts, and full-text queries. Retrieve specific properties with up to 5 filter groups.

Instructions

Search HubSpot CRM records using filters, sorts, and full-text query. Applies to all object types. Supports up to 5 filter groups (OR-ed) with up to 6 filters per group (AND-ed). IMPORTANT NOTES: (1) Search has stricter rate limits (~5 req/s per token) than regular reads — avoid polling. (2) Search has an indexing latency of several seconds — do NOT use immediately after create/update. Use hubspot_crm_get instead for read-after-write. (3) Max total results via paging: 10 000. (4) Specify properties explicitly — HubSpot returns only defaults otherwise. Returns matching records with their requested properties.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
afterNoPagination cursor. Use 0 (or omit) for first page.
limitNoRecords per response (1–200). Default: 10.
queryNoFull-text search query across all searchable string properties.
sortsNoSort specifications applied in order.
objectTypeYesCRM object type. Sales objects: deals, line_items, products, quotes. Engagement objects: calls, meetings, tasks, notes, emails.
propertiesNoProperty names to return. Always specify — HubSpot omits non-default properties.
filterGroupsNoOR-ed filter groups (max 5). Each group contains AND-ed filters (max 6). Leave empty with a `query` for full-text-only search.
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses rate limits, indexing latency, max results, and property requirements. However, it does not mention error behavior or response format, which would be helpful for a complete behavioral picture.

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 concise and well-structured: a clear lead sentence followed by bullet-pointed important notes. Every sentence adds value, and the most critical information is front-loaded.

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?

Given the tool's complexity (search with filtering, sorting, paging) and no output schema, the description covers essential behaviors like rate limits, latency, max results, and property specification. It could be improved by explicitly stating the response format (list of records), but overall it is complete enough for an AI agent to use correctly.

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?

All 7 parameters have schema descriptions (100% coverage), so baseline is 3. The tool description adds context about filter group structure and usage (e.g., OR-ed groups, AND-ed filters, max counts) but does not add significant new semantics per parameter beyond what the schema already provides.

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?

The description clearly states it searches HubSpot CRM records with filters, sorts, and full-text query, and applies to all object types. It distinguishes itself from sibling tools like hubspot_crm_get by explicitly recommending that tool for read-after-write.

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

Usage Guidelines5/5

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

The description provides explicit usage guidelines including rate limits (~5 req/s), indexing latency (do not use after create/update), max results (10,000), and the need to specify properties. It also recommends an alternative tool (hubspot_crm_get) for read-after-write scenarios.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nubiia-dev/mcp-hubspot'

If you have feedback or need assistance with the MCP directory API, please join our Discord server