mcpField
M
mabl

mabl

Remote
github.comDeveloper Tools0Updated 11w ago

About mabl

mabl MCP server connects AI assistants and agents to mabl workspaces for test automation and result analysis. It is a managed remote service, with OAuth sign-in and AI features subject to workspace entitlements.

Key features

  1. 01Run mabl tests
  2. 02Analyze test failures
  3. 03Create tests in the cloud
  4. 04Query results across workspaces
  5. 05Connect over Streamable HTTP or SSE

Use cases

  1. 01Run tests from an MCP client
  2. 02Investigate failures in a test run
  3. 03Create cloud tests from an AI workflow
  4. 04Query results across mabl workspaces

MCP support

The managed MCP server exposes tools for running tests, analyzing failures, creating cloud tests, and querying workspace results. Clients connect over Streamable HTTP or SSE and authenticate through OAuth using a mabl account.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.mabl.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://mcp.mabl.com/mcp
SSEhttps://mcp.mabl.com/sse

Tools

Details

From the project README

mabl MCP server

The mabl Model Context Protocol (MCP) server lets AI assistants and agents work directly with your mabl tests — run tests, analyze failures, create tests in the cloud, and query results across your workspaces.

This repository hosts the public documentation and registry listing for the hosted mabl MCP server. The server is operated by mabl as a managed remote service — there is nothing to install or self-host.

Endpoints

The server is hosted at mcp.mabl.com and supports two transports:

TransportURL
Streamable HTTP (recommended)https://mcp.mabl.com/mcp
Server-Sent Events (SSE)https://mcp.mabl.com/sse

Requirements

  • A mabl account — you sign in with your existing mabl credentials.
  • The AI-powered tools (failure analysis, results-analysis chat, cloud test generation) require the corresponding mabl AI entitlements on your workspace.

Authentication

The server uses standard MCP OAuth. The first time your client connects it opens a browser to sign in with your mabl identity and authorize access; after that your client caches the token and reconnects automatically — there are no API keys to copy or manage. See docs/authentication.md for the full flow.

Connect a client

Point any MCP-capable client at the Streamable HTTP endpoint https://mcp.mabl.com/mcp (or the SSE endpoint https://mcp.mabl.com/sse for clients that require SSE). A few common clients:

Claude Code
claude mcp add --transport http mabl https://mcp.mabl.com/mcp
Codex CLI
codex mcp add mabl --url https://mcp.mabl.com/mcp
Gemini CLI

This repository doubles as a Gemini CLI extension, so it installs in one command — no JSON to edit:

gemini extensions install https://github.com/mablhq/mabl-mcp-server

The extension configures the endpoint and ships a GEMINI.md with guidance on using the mabl tools. Verify it with gemini extensions list.

Cursor / VS Code / other JSON-configured clients

Add an HTTP MCP server entry pointing at the endpoint:

{
  "mcpServers": {
    "mabl": {
      "type": "http",
      "url": "https://mcp.mabl.com/mcp"
    }
  }
}
Claude Desktop

Add a custom connector with the URL https://mcp.mabl.com/mcp.

On first use, the client will prompt you to sign in to mabl in your browser.

Available tools

The canonical, always-current tool reference is the mabl help center article, regenerated from the live server on every release. docs/TOOLS.md summarizes the high-level tool areas and links to it. You can also call tools/list from any connected client to see exactly what the server exposes.

Support

License

MIT © 2026 mabl, Inc.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.