Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_contact_search_advanced

Read-onlyIdempotent

Search GoHighLevel contacts by combining filters, sorting, and pagination criteria through a JSON request body, enabling targeted contact lookups via the v3 contacts search endpoint.

Instructions

SPEC GAP: the official OpenAPI's SearchBodyV2DTO is an empty object schema — GoHighLevel's spec only points to an external ClickUp doc (linked in the op's externalDocs) for the real filter/sort/pageLimit/searchAfter/query body shape, which is not available in this docs corpus. Verified this is a genuine spec gap (not an extraction bug) against both the legacy (contacts.json) and v3 (v3/contacts-v3.json) copies of this endpoint, and via ghl_docs_context — both show the identical empty schema. The generated tool's body property will still accept arbitrary JSON (no additionalProperties:false is applied inside body sub-schemas), so callers who know the real field names from GHL's docs can pass them; there's just no schema-level validation or autocomplete for this one operation. Search Contacts Search contacts based on combinations of advanced filters. Documentation Link - https://doc.clickup.com/8631005/d/h/87cpx-158396/6e629989abe7fad Endpoint: POST /contacts/search (Version header: v3; source: v3/contacts-v3.json) OAuth scopes: contacts.readonly

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": {
      "body": "<body>"
    },
    "name": "ghl_contact_search_advanced"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.0
    • addedInput schema / properties / body / title
      Added value: +"SearchBodyV2DTO"
  2. First observedv2.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/non-destructive, so the description focuses on what they cannot say: the body is unvalidated arbitrary JSON with no autocomplete, the OAuth scope is contacts.readonly, and the version header is v3. That is meaningful context beyond the structured fields, though return shape and pagination behavior are unaddressed.

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

Conciseness3/5

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

The purpose sentence is buried behind a long internal 'SPEC GAP' engineering note, so the description is not front-loaded. The verification detail about comparing legacy and v3 spec copies is provenance noise for an agent, even if the underlying warning is valuable.

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 tool whose request body is an empty schema and which has no output schema, the description does the heavy lifting: it names expected fields, links the external docs, and discloses auth scope and versioning. What remains missing is any indication of result shape or result-set limits, which matters for a search endpoint.

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

Parameters4/5

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

Schema coverage is nominally 100%, but the body schema is literally empty, so the schema carries no information. The description compensates substantially by naming the expected field families (filter, sort, pageLimit, searchAfter, query) and explaining that no additionalProperties:false constraint applies, letting callers pass unvalidated fields.

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?

States a specific verb and resource ('Search Contacts ... based on combinations of advanced filters') plus the exact endpoint, so the operation is unambiguous. It does not, however, distinguish itself from nearby siblings such as ghl_contact_list or ghl_contact_lookup, which is the one thing an agent still has to infer.

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

Usage Guidelines3/5

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

Usage is only implied by 'advanced filters'; the description never says when to prefer this over ghl_contact_list or ghl_contact_lookup. It does give a genuinely useful operational caveat (callers must supply real field names from GHL's docs because the schema is empty), which counts as partial guidance.

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

Deploy Server

Other Tools