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

ghl-mcp-server-v2

by zackscriven

ghl_conversation_search

Read-onlyIdempotent

Search conversations by query, status, contact, assignee, date, and other filters, then page through matching results with sorting options.

Instructions

Search Conversations Returns a list of all conversations matching the search criteria along with the sort and filter options selected. Endpoint: GET /conversations/search (Version header: v3; source: v3/conversations-v3.json) OAuth scopes: conversations.readonly Pagination params: limit — pass them to page through full result sets.

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": {
      "locationId": "<locationId>"
    },
    "name": "ghl_conversation_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoId of the conversation
sortNoSort paramater - asc or desc
limitNoLimit of conversations - Default is 20
queryNoSearch paramater as a string
sortByNoThe sorting of the conversation to be filtered as - manual messages or all messages
statusNoThe status of the conversation to be filtered - all, read, unread, starred
mentionsNoUser Id of the mention. Multiple values are comma separated.
contactIdNoContact Id
followersNoUser IDs of followers to filter conversations by. Multiple IDs can be provided as comma-separated values.
assignedToNoUser IDs that conversations are assigned to. Multiple IDs can be provided as comma-separated values. Use "unassigned" to fetch conversations not assigned to any user.
locationIdYesLocation Id
scoreProfileNoId of score profile on which conversations should get filtered out, works with scoreProfileMin & scoreProfileMax
startAfterDateNoSearch to begin after the specified date - should contain the sort value of the last document
lastMessageTypeNoType of the last message in the conversation as a string
scoreProfileMaxNoMaximum value for score
scoreProfileMinNoMinimum value for score
sortScoreProfileNoId of score profile on which sortBy.ScoreProfile should sort on
lastMessageActionNoAction of the last outbound message in the conversation as string.
lastMessageDirectionNoDirection of the last message in the conversation as string.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.1.0
    • removedInput schema / properties / endDate
      Removed value: -{
      -  "description": "End date filter for dateAdded field (Unix timestamp in milliseconds)",
      -  "example": 1672531199000,
      -  "type": "number"
      -}
    • changedInput schema / properties / lastMessageType / enum
      Previous value: -[
      -  "TYPE_CALL",
      -  "TYPE_SMS",
      -  "TYPE_RCS",
      -  "TYPE_EMAIL",
      -  "TYPE_SMS_REVIEW_REQUEST",
      -  "TYPE_WEBCHAT",
      -  "TYPE_SMS_NO_SHOW_REQUEST",
      -  "TYPE_CAMPAIGN_SMS",
      -  "TYPE_CAMPAIGN_CALL",
      -  "TYPE_CAMPAIGN_EMAIL",
      -  "TYPE_CAMPAIGN_VOICEMAIL",
      -  "TYPE_FACEBOOK",
      -  "TYPE_CAMPAIGN_FACEBOOK",
      -  "TYPE_CAMPAIGN_MANUAL_CALL",
      -  "TYPE_CAMPAIGN_MANUAL_SMS",
      -  "TYPE_GMB",
      -  "TYPE_CAMPAIGN_GMB",
      -  "TYPE_REVIEW",
      -  "TYPE_INSTAGRAM",
      -  "TYPE_WHATSAPP",
      -  "TYPE_CUSTOM_SMS",
      -  "TYPE_CUSTOM_EMAIL",
      -  "TYPE_CUSTOM_PROVIDER_SMS",
      -  "TYPE_CUSTOM_PROVIDER_EMAIL",
      -  "TYPE_IVR_CALL",
      -  "TYPE_ACTIVITY_CONTACT",
      -  "TYPE_ACTIVITY_INVOICE",
      -  "TYPE_ACTIVITY_PAYMENT",
      -  "TYPE_ACTIVITY_OPPORTUNITY",
      -  "TYPE_LIVE_CHAT",
      -  "TYPE_LIVE_CHAT_INFO_MESSAGE",
      -  "TYPE_ACTIVITY_APPOINTMENT",
      -  "TYPE_FACEBOOK_COMMENT",
      -  "TYPE_INSTAGRAM_COMMENT",
      -  "TYPE_CUSTOM_CALL",
      -  "TYPE_INTERNAL_COMMENT",
      -  "TYPE_ACTIVITY_EMPLOYEE_ACTION_LOG",
      -  "TYPE_TIKTOK",
      -  "TYPE_TIKTOK_COMMENT",
      -  "TYPE_ACTIVITY_WHATSAPP",
      -  "TYPE_FORM_SUBMISSION",
      -  "TYPE_SMS_REACTION"
      -]New value: +[
      +  "TYPE_CALL",
      +  "TYPE_SMS",
      +  "TYPE_EMAIL",
      +  "TYPE_SMS_REVIEW_REQUEST",
      +  "TYPE_WEBCHAT",
      +  "TYPE_SMS_NO_SHOW_REQUEST",
      +  "TYPE_CAMPAIGN_SMS",
      +  "TYPE_CAMPAIGN_CALL",
      +  "TYPE_CAMPAIGN_EMAIL",
      +  "TYPE_CAMPAIGN_VOICEMAIL",
      +  "TYPE_FACEBOOK",
      +  "TYPE_CAMPAIGN_FACEBOOK",
      +  "TYPE_CAMPAIGN_MANUAL_CALL",
      +  "TYPE_CAMPAIGN_MANUAL_SMS",
      +  "TYPE_GMB",
      +  "TYPE_CAMPAIGN_GMB",
      +  "TYPE_REVIEW",
      +  "TYPE_INSTAGRAM",
      +  "TYPE_WHATSAPP",
      +  "TYPE_CUSTOM_SMS",
      +  "TYPE_CUSTOM_EMAIL",
      +  "TYPE_CUSTOM_PROVIDER_SMS",
      +  "TYPE_CUSTOM_PROVIDER_EMAIL",
      +  "TYPE_IVR_CALL",
      +  "TYPE_ACTIVITY_CONTACT",
      +  "TYPE_ACTIVITY_INVOICE",
      +  "TYPE_ACTIVITY_PAYMENT",
      +  "TYPE_ACTIVITY_OPPORTUNITY",
      +  "TYPE_LIVE_CHAT",
      +  "TYPE_LIVE_CHAT_INFO_MESSAGE",
      +  "TYPE_ACTIVITY_APPOINTMENT",
      +  "TYPE_FACEBOOK_COMMENT",
      +  "TYPE_INSTAGRAM_COMMENT",
      +  "TYPE_CUSTOM_CALL",
      +  "TYPE_INTERNAL_COMMENT",
      +  "TYPE_ACTIVITY_EMPLOYEE_ACTION_LOG"
      +]
    • changedInput schema / properties / sortBy / enum
      Previous value: -[
      -  "last_manual_message_date",
      -  "last_message_date",
      -  "score_profile",
      -  "overdue_at",
      -  "due_at"
      -]New value: +[
      +  "last_manual_message_date",
      +  "last_message_date",
      +  "score_profile"
      +]
    • removedInput schema / properties / startDate
      Removed value: -{
      -  "description": "Start date filter for dateAdded field (Unix timestamp in milliseconds)",
      -  "example": 1640995200000,
      -  "type": "number"
      -}
  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 declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that: the HTTP verb/endpoint, the required OAuth scope (conversations.readonly), and the fact that limit is the pagination control for paging through full result sets. It doesn't describe return shape or ordering defaults, which keeps it short of 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.

Conciseness5/5

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

Four short lines, front-loaded with the action and its return, then endpoint, scope, and pagination note. The internals (version header, source spec file) are minor boilerplate but small enough that nothing needs to be cut for comprehension.

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?

With 19 parameters, 6 enums, no output schema and heavy overlapping filters (status, lastMessageType, lastMessageAction, scoreProfile range, mentions/followers/assignedTo), the description leaves the agent guessing about filter combination and the cursor-style startAfterDate. The pagination and auth notes help, but a search tool of this complexity needs more guidance than is given.

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% across 19 params, so the baseline is 3. The description only adds meaning for one of them — that limit is a pagination param to page through results — and says nothing about the confusing cursor-style startAfterDate or how query interacts with the filter params, so it does not exceed the schema's information.

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 gives a specific verb and resource ('Search Conversations', GET /conversations/search) and states it returns conversations matching the search criteria with the selected sort/filter options. It is clear on its own, but never names the distinguishing siblings (e.g. ghl_conversation_get for a single conversation, ghl_conversation_get_messages for messages), so an agent must infer the boundary.

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 implied by the word 'search' and the required locationId plus filter params, and the OAuth scope line tells the agent what access is needed. However there is no explicit statement of when to use this versus the conversation getters/message tools, nor any exclusion such as 'use X to fetch a single conversation by id'.

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