The MCP server lets an AI assistant work with your Gleap workspace directly — “what came in this week about billing?”, “draft a reply to ticket 4821”, “write a help center article about the new export” — with the assistant reading and writing through Gleap's own tools rather than you copying things between tabs.
It works with any client that speaks the Model Context Protocol: Claude, ChatGPT, Cursor, VS Code and others.
The server URL is:
https://mcp.gleap.io/mcpIn a client that supports OAuth, add that URL as an integration and click Connect. You're sent to Gleap to authorise; you pick the project the assistant may use, and that's the whole setup — no keys to copy.
For clients that don't do OAuth but do let you set headers, authenticate with:
x-gleap-api-key — your API key.
x-gleap-project-id — the project ID.
Both are in your project's API settings.
The tools cover most of what you'd do in the dashboard.
Tickets — search and filter, read one with its full conversation, create, update, assign, tag, snooze, close, reopen, archive, link and merge, and read the activity log.
Messages — read a thread and send a reply or an internal note.
Contacts — search, read, create, update, and list someone's tickets.
Help center — read collections and articles, and create or update them.
Knowledge — search your knowledge base, and find tickets similar to a given one.
Statistics — headline facts, lists, bar charts, and raw data.
Surveys, news, feature requests, teams and workflows — read them, and run a workflow on a ticket.
The set grows as the product does, so what your client lists is the current truth.
Questions that would otherwise be a report: what's been coming in, which topics repeat, what changed since last month. And bulk drudgery — turning a recurring question into a help center article, or finding every ticket that mentions a feature before a release.
For developers, it puts support context where the code is: reading the ticket that describes a bug without leaving the editor.
The connection is scoped to the project you picked when authorising, and inherits your own permissions — an assistant can't do anything you couldn't.
MCP is for people working with an assistant: ad hoc, conversational, different every time. The REST API is for your own code — imports, scheduled jobs, anything that should run identically every time. If you're writing a script, use the API.