Connecting to the Gleap MCP Server

What is an MCP Server?

An MCP (Model Context Protocol) server allows AI tools, assistants, or other clients to connect and interact with your system via a standardized API. It acts as a bridge between your data or services and the client, exposing “tools” (endpoints) that the client can call in a structured, machine-readable way.

With MCP, your AI assistant can directly query tickets, contacts, and statistics from Gleap, or create new entries — all without manually logging into the dashboard.

Gleap MCP Server URL

Your MCP server is available at:

https://mcp.gleap.io/mcp

Authentication

Option 1: OAuth (Recommended)

Connect via OAuth and authenticate using your Gleap account. The server will guide you through the OAuth flow automatically.

Supported OAuth Clients

The following MCP clients are officially supported for OAuth authentication:

If you are building a custom MCP client or using a tool not listed here, please contact us to get your redirect domain whitelisted.

Option 2: API Key Headers (Legacy)

Provide the following custom HTTP headers:

Available Tools

The following tools are available once connected:

Ticket Management

• search_tickets – Search tickets based on criteria.

• find_tickets – Find tickets with advanced filters.

• get_ticket – Retrieve details of a specific ticket.

• create_ticket – Create a new ticket.

Contact Management

• search_contacts – Search for contacts.

• get_contacts – Retrieve a list of contacts.

• get_contact – Get details of a single contact.

• create_contact – Create a new contact.

Statistics

• get_statistics_facts – Get numerical statistics.

• get_statistics_list – Retrieve a list-based set of statistics.

• get_statistics_bar_chart – Get data formatted for bar charts.

• get_raw_data_statistics – Retrieve raw data for statistics.

Help Center Management

Collections

• get_help_center_collections – Retrieve help center collections.

• get_help_center_collections_tree – Retrieve all collections including subcollections in a tree structure.

• create_help_center_collection – Create a new help center collection (requires title as localized object).

• update_help_center_collection – Update an existing help center collection.

Articles

• get_help_center_articles – Retrieve articles in a collection.

• get_help_center_article – Retrieve details of a single article by ID.

• create_help_center_article – Create a new help center article (requires localized title, description, content).

• update_help_center_article – Update an existing help center article (requires localized title, description, content).

News & Changelog

• get_news – Retrieve news and changelog items with optional pagination.

• get_news_item – Retrieve a specific news or changelog item by ID.

• create_news – Create a new news or changelog entry (requires name, localized subject, and localized TipTap message).

• update_news – Update an existing news or changelog entry by ID.

• delete_news – Permanently delete a news or changelog item by ID.

Examples

Example 1: Triage unassigned tickets

Prompt: "Show me all open high-priority tickets that haven't been assigned to anyone"

What happens:

• The assistant calls find_tickets with status: "open" and priority: "HIGH"

• Filters the results to surface unassigned tickets

• Returns a ranked list with ticket IDs, titles, and creation dates so you can start triaging immediately

Example 2: Look up a customer and their history

Prompt: "Find the contact for sarah@acme.com and show me her recent support tickets"

What happens:

• The assistant calls search_contacts with the email address

• Retrieves the contact record including name, company, and custom attributes

• Calls find_tickets filtered by the contact's session ID

• Summarizes the contact profile and ticket history in one response

Example 3: Create a ticket from a conversation

Prompt: "Create a high-priority bug report titled 'Payment fails on checkout for EU customers'"

What happens:

• The assistant calls get_ticket_types to find the right ticket type and required fields

• Calls create_ticket with the type, title, and priority

• Returns the new ticket ID and a direct link to it in Gleap

Example 4: Browse and navigate the help center

Prompt: "What help center collections do we have, and which articles are in the 'Getting Started' collection?"

What happens:

• The assistant calls get_help_center_collections_tree to get the full structure

• Identifies the matching collection and calls get_help_center_articles

• Returns a structured list of all articles with their titles and IDs

Example 5: Write a new help center article

Prompt: "Create a help center article explaining how to reset a password. Write it in English and German."

What happens:

• The assistant asks which collection to add it to (or uses get_help_center_collections to list options)

• Drafts localized title, description, and body content in TipTap JSON format for both locales

• Calls create_help_center_article with isDraft: true so you can review before publishing

Example 6: Check support performance

Prompt: "What was our average first response time last month, and how does it compare to the month before?"

What happens:

• The assistant calls get_statistics_facts with chartType: "MEDIAN_FIRST_RESPONSE_TIME" for each date range

• Compares the two values and calculates the percentage change

• Presents a concise summary with the trend direction

Example 7: Publish a changelog entry

Prompt: "Create a changelog post announcing our new dark mode feature, in English and German"

What happens:

• The assistant drafts a localized subject and message (TipTap document) for both locales

• Calls create_news with type: "NEWS" and subType: "CHANGELOG"

• Returns the new entry ID so you can review and publish it from the Gleap dashboard

How to Connect

1. Open your MCP-compatible client or AI assistant settings.

2. Add a new MCP server connection.

3. Enter the URL:

   https://mcp.gleap.io/mcp

4. Select Streamable HTTP as the transport.

Authenticate via OAuth — or set authentication to Custom Headers and add:

• project → your Project ID

• api-key → your API Key

1. Save and connect.

Once connected, you can call any of the listed tools directly from your client.