Intercom Automation logo

Intercom Automation

CommunityPopular
davepoon
intercom-automation

Automate Intercom tasks via Rube MCP (Composio): conversations, contacts, companies, segments, admins. Always search tools first for current schemas.

Overview

Publisherdavepoon
Repositorybuildwithclaude
Skill nameintercom-automation
Stars
3.6K
Forks
586
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by davepoon on GitHub. Read the source before you install it.

Installation

Install the Intercom Automation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/intercom-automation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davepoon/buildwithclaude.git /tmp/buildwithclaude
mkdir -p .claude/skills
cp -r /tmp/buildwithclaude/plugins/all-skills/skills/intercom-automation .claude/skills/intercom-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Intercom Automation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Intercom Automation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Intercom Automation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Intercom Automation via Rube MCP

Automate Intercom operations through Composio's Intercom toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/intercom

Prerequisites

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Intercom connection via RUBE_MANAGE_CONNECTIONS with toolkit intercom
  • Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

  1. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  2. Call RUBE_MANAGE_CONNECTIONS with toolkit intercom
  3. If connection is not ACTIVE, follow the returned auth link to complete Intercom OAuth
  4. Confirm connection status shows ACTIVE before running any workflows

Core Workflows

1. Manage Conversations

When to use: User wants to create, list, search, or manage support conversations

Tool sequence:

  1. INTERCOM_LIST_ALL_ADMINS - Get admin IDs for assignment [Prerequisite]
  2. INTERCOM_LIST_CONVERSATIONS - List all conversations [Optional]
  3. INTERCOM_SEARCH_CONVERSATIONS - Search with filters [Optional]
  4. INTERCOM_GET_CONVERSATION - Get conversation details [Optional]
  5. INTERCOM_CREATE_CONVERSATION - Create a new conversation [Optional]

Key parameters:

  • from: Object with type ('user'/'lead') and id for conversation creator
  • body: Message body (HTML supported)
  • id: Conversation ID for retrieval
  • query: Search query object with field, operator, value

Pitfalls:

  • CREATE_CONVERSATION requires a contact (user/lead) as the from field, not an admin
  • Conversation bodies support HTML; plain text is auto-wrapped in <p> tags
  • Search query uses structured filter objects, not free-text search
  • Conversation IDs are numeric strings

2. Reply and Manage Conversation State

When to use: User wants to reply to, close, reopen, or assign conversations

Tool sequence:

  1. INTERCOM_GET_CONVERSATION - Get current state [Prerequisite]
  2. INTERCOM_REPLY_TO_CONVERSATION - Add a reply [Optional]
  3. INTERCOM_ASSIGN_CONVERSATION - Assign to admin/team [Optional]
  4. INTERCOM_CLOSE_CONVERSATION - Close conversation [Optional]
  5. INTERCOM_REOPEN_CONVERSATION - Reopen closed conversation [Optional]

Key parameters:

  • conversation_id / id: Conversation ID
  • body: Reply message body (HTML supported)
  • type: Reply type ('admin' or 'user')
  • admin_id: Admin ID for replies from admin, assignment, and close/reopen
  • assignee_id: Admin or team ID for assignment
  • message_type: 'comment' (default) or 'note' (internal)

Pitfalls:

  • admin_id is REQUIRED for admin replies, close, reopen, and assignment operations
  • Always fetch admin IDs first with LIST_ALL_ADMINS or IDENTIFY_AN_ADMIN
  • Duplicate sends can occur on retry; implement idempotency checks
  • Internal notes use message_type: 'note'; visible only to workspace members
  • Closing requires an admin_id and optional body message

3. Manage Contacts

When to use: User wants to search, view, or manage contacts (users and leads)

Tool sequence:

  1. INTERCOM_SEARCH_CONTACTS - Search contacts with filters [Required]
  2. INTERCOM_GET_A_CONTACT - Get specific contact [Optional]
  3. INTERCOM_SHOW_CONTACT_BY_EXTERNAL_ID - Look up by external ID [Optional]
  4. INTERCOM_LIST_CONTACTS - List all contacts [Optional]
  5. INTERCOM_LIST_TAGS_ATTACHED_TO_A_CONTACT - Get contact tags [Optional]
  6. INTERCOM_LIST_ATTACHED_SEGMENTS_FOR_CONTACT - Get contact segments [Optional]
  7. INTERCOM_DETACH_A_CONTACT - Remove contact from company [Optional]

Key parameters:

  • contact_id: Contact ID for retrieval
  • external_id: External system ID for lookup
  • query: Search filter object with field, operator, value
  • pagination: Object with per_page and starting_after cursor

Pitfalls:

  • SEARCH_CONTACTS uses structured query filters, not free-text; format: {field, operator, value}
  • Supported operators: =, !=, >, <, ~ (contains), !~ (not contains), IN, NIN
  • Contact types are 'user' (identified) or 'lead' (anonymous)
  • LIST_CONTACTS returns paginated results; use starting_after cursor for pagination
  • External IDs are case-sensitive

4. Manage Admins and Teams

When to use: User wants to list workspace admins or identify specific admins

Tool sequence:

  1. INTERCOM_LIST_ALL_ADMINS - List all admins and teams [Required]
  2. INTERCOM_IDENTIFY_AN_ADMIN - Get specific admin details [Optional]

Key parameters:

  • admin_id: Admin ID for identification

Pitfalls:

  • LIST_ALL_ADMINS returns both admins and teams
  • Admin IDs are required for conversation replies, assignment, close, and reopen
  • Teams appear in the admins list with type: 'team'

5. View Segments and Counts

When to use: User wants to view segments or get aggregate counts

Tool sequence:

  1. INTERCOM_LIST_SEGMENTS - List all segments [Optional]
  2. INTERCOM_LIST_ATTACHED_SEGMENTS_FOR_CONTACT - Segments for a contact [Optional]
  3. INTERCOM_LIST_ATTACHED_SEGMENTS_FOR_COMPANIES - Segments for a company [Optional]
  4. INTERCOM_GET_COUNTS - Get aggregate counts [Optional]

Key parameters:

  • contact_id: Contact ID for segment lookup
  • company_id: Company ID for segment lookup
  • type: Count type ('conversation', 'company', 'user', 'tag', 'segment')
  • count: Sub-count type

Pitfalls:

  • GET_COUNTS returns approximate counts, not exact numbers
  • Segment membership is computed; changes may not reflect immediately

6. Manage Companies

When to use: User wants to list companies or manage company-contact relationships

Tool sequence:

  1. INTERCOM_LIST_ALL_COMPANIES - List all companies [Required]
  2. INTERCOM_LIST_ATTACHED_SEGMENTS_FOR_COMPANIES - Get company segments [Optional]
  3. INTERCOM_DETACH_A_CONTACT - Remove contact from company [Optional]

Key parameters:

  • company_id: Company ID
  • contact_id: Contact ID for detachment
  • page: Page number for pagination
  • per_page: Results per page

Pitfalls:

  • Company-contact relationships are managed through contact endpoints
  • DETACH_A_CONTACT removes the contact-company association, not the contact itself

Common Patterns

Search Query Filters

Single filter:

json
{
  "field": "email",
  "operator": "=",
  "value": "user@example.com"
}

Multiple filters (AND):

json
{
  "operator": "AND",
  "value": [
    {"field": "role", "operator": "=", "value": "user"},
    {"field": "created_at", "operator": ">", "value": 1672531200}
  ]
}

Supported fields for contacts: email, name, role, created_at, updated_at, signed_up_at, last_seen_at, external_id

Supported fields for conversations: created_at, updated_at, source.type, state, open, read

Pagination

  • Most list endpoints use cursor-based pagination
  • Check response for pages.next with starting_after cursor
  • Pass cursor in pagination.starting_after for next page
  • Continue until pages.next is null

Admin ID Resolution

1. Call INTERCOM_LIST_ALL_ADMINS to get all admins
2. Find the desired admin by name or email
3. Use admin.id for replies, assignments, and state changes

Known Pitfalls

Admin ID Requirement:

  • Admin ID is required for: reply (as admin), assign, close, reopen
  • Always resolve admin IDs first with LIST_ALL_ADMINS

HTML Content:

  • Conversation bodies are HTML
  • Plain text is auto-wrapped in paragraph tags
  • Sanitize HTML input to prevent rendering issues

Idempotency:

  • Replies and conversation creation are not idempotent
  • Duplicate sends can occur on retry or timeout
  • Track message IDs to prevent duplicates

Rate Limits:

  • Default: ~1000 requests per minute (varies by plan)
  • 429 responses include rate limit headers
  • Implement exponential backoff for retries

Quick Reference

TaskTool SlugKey Params
List conversationsINTERCOM_LIST_CONVERSATIONS(pagination)
Search conversationsINTERCOM_SEARCH_CONVERSATIONSquery
Get conversationINTERCOM_GET_CONVERSATIONid
Create conversationINTERCOM_CREATE_CONVERSATIONfrom, body
Reply to conversationINTERCOM_REPLY_TO_CONVERSATIONconversation_id, body, admin_id
Assign conversationINTERCOM_ASSIGN_CONVERSATIONconversation_id, admin_id, assignee_id
Close conversationINTERCOM_CLOSE_CONVERSATIONid, admin_id
Reopen conversationINTERCOM_REOPEN_CONVERSATIONid, admin_id
Search contactsINTERCOM_SEARCH_CONTACTSquery
Get contactINTERCOM_GET_A_CONTACTcontact_id
Contact by external IDINTERCOM_SHOW_CONTACT_BY_EXTERNAL_IDexternal_id
List contactsINTERCOM_LIST_CONTACTS(pagination)
Contact tagsINTERCOM_LIST_TAGS_ATTACHED_TO_A_CONTACTcontact_id
Contact segmentsINTERCOM_LIST_ATTACHED_SEGMENTS_FOR_CONTACTcontact_id
Detach contactINTERCOM_DETACH_A_CONTACTcontact_id, company_id
List adminsINTERCOM_LIST_ALL_ADMINS(none)
Identify adminINTERCOM_IDENTIFY_AN_ADMINadmin_id
List segmentsINTERCOM_LIST_SEGMENTS(none)
Company segmentsINTERCOM_LIST_ATTACHED_SEGMENTS_FOR_COMPANIEScompany_id
Get countsINTERCOM_GET_COUNTStype, count
List companiesINTERCOM_LIST_ALL_COMPANIESpage, per_page

Powered by Composio

Frequently asked questions

What does the Intercom Automation AI skill do?

Automate Intercom tasks via Rube MCP (Composio): conversations, contacts, companies, segments, admins. Always search tools first for current schemas.

Why use Intercom Automation on TypingMind?

Because you install it once and use it with any model. Intercom Automation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Intercom Automation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/intercom-automation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Intercom Automation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Intercom Automation?

As many as you like. As long as a model supports skills, you can use Intercom Automation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Intercom Automation AI skill free?

Yes. It is published on GitHub by davepoon under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇