Search
The Intercom Search AI tool provides a powerful and unified query system to efficiently find conversations and contacts within your Intercom data. It enables precise, customizable searches using a dedicated query language to help customer support and sales teams locate relevant information quickly.
Features
- Supports searching both conversations and contacts with a single query interface.
- Uses a flexible and detailed query DSL allowing filters by fields such as email, state, date ranges, and custom attributes.
- Returns concise search results including IDs, titles, text snippets, and URLs for quick reference.
- Supports pagination and logical operators to handle large result sets and complex queries.
- Integrates seamlessly with Intercom’s Fetch tool to retrieve full details based on search result IDs.
Benefits
- Speeds up locating key customer interactions and contact information for faster issue resolution.
- Enables targeted filtering to improve accuracy and relevance of search results.
- Improves team productivity by consolidating search capabilities in one tool.
- Facilitates better customer service with rapid access to conversation history and contact details.
- Supports automation and workflow integration through structured query inputs and API compatibility.
Description
Purpose:
- Search for resources in Intercom (conversations and contacts) using a unified query approach.
- Note that only a subset of properties will be returned in search results.
- For complete details, use the Fetch tool with the returned IDs.
Usage:
- MUST specify object_type OR object_type to indicate which API to call.
- Use specific field searches for precise filtering (e.g., email@example.com).
- Use the starting_after parameter for pagination when more results exist.
- Combine multiple search criteria with logical operators for complex queries.
Search Tool Response:
- Returns results with id, title, text, and url for each match.
- IDs are prefixed with 'conversation_' or 'contact_' to indicate type.
- Use these IDs with the Fetch tool to get complete resource details.
Intercom Search Query DSL specification:
• Tokens separated by spaces • Each token: key[
] • op (optional; default "eq") ∈ { eq, neq, gt, lt, in, nin, contains } • value: unquoted (alphanumeric, no spaces) or quoted in single/double quotes (to include spaces)Common Parameters: – object_type (mandatory) → "conversations" or "contacts" (specifies which API to call) – q/query → free-text search across key fields – created_at/updated_at → timestamp filters (YYYY-MM-DD or Unix timestamp) – limit → max results (default 10, max 150) – starting_after → pagination cursor
CONVERSATION SEARCH (object_type
): Supported fields: – id → conversation ID – state → conversation state ("open", "closed", "snoozed") – priority → conversation priority ("priority", "not_priority") – source_type → conversation source type ("conversation", "email", "facebook", "twitter", etc.) – source_author_name → name of the message author – source_author_email → email of the message author – source_subject → subject line of the conversation – source_body → body content of the conversation – contact_ids → contact IDs associated with the conversation – statistics_time_to_assignment → time to assignment in seconds – statistics_time_to_admin_reply → time to admin reply in seconds – statistics_time_to_first_close → time to first close in secondsCONTACT SEARCH (object_type
): Supported fields: – id → contact ID – name → contact name – email → contact email address – email_domain → email domain – phone → contact phone number – role → contact role ("user", "lead") – custom_attributes.* → any custom attribute field (e.g., custom_attributes.company)EXAMPLES:
user: show me recent conversations query: object_type
created_at:gt:1735689600user: find open conversations from email query: object_type
state source_typeuser: search for conversations from support emails
query: object_type
user: find conversations with slow response times query: object_type
statistics_time_to_admin_reply:gt:3600user: find conversations about billing query: object_type
source_subject:contains:"billing"user: find conversations mentioning refund query: object_type
source_body:contains:"refund"user: find contacts named John query: object_type
name:"John"user: find contacts from example.com domain query: object_type
email_domain:"example.com"user: find contacts with specific custom attribute query: object_type
custom_attributes.plan_status:"active"user: recent contact activity query: object_type
updated_at:gt:1735689600 limit:50user: find conversations for a specific contact query: object_type
contact_ids:inUnsupported features:
• Complex boolean logic beyond simple AND/OR
• Fuzzy matching or proximity searches
• Aggregations or analytics queries
• Direct conversation content search (use source fields instead)
• Real-time or streaming results
Parameters
1 parameter
| Name | Type | Description |
|---|---|---|
| queryrequired | string | Intercom Search Query DSL specification. MUST start with object_type or object_type to specify which API to call. Use tokens separated by spaces with key[] format. Examples: 'object_type email:contains:"@example.com"' for domain search, 'object_type state created_at:gte:2024-01-01' for recent open conversations. |