MCP server · Engineering and operations

BrowserStack MCP server

BrowserStack in any MCP client, through Memtro: BrowserStack does not publish this server. Memtro's BrowserStack connector reads BrowserStack through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

BrowserStack testing: the Automate plan and parallel sessions in use, Automate projects, builds and their sessions with status, failure reason, platform and duration; Test Management projects, test cases, test runs with progress, and the results recorded in a run. When you ask, can mark an Automate session passed or failed, rename or delete a session or build, create, clone, close or delete a test run, record a test result, and create a test case.

Reads

  • browserstack_automate_overviewBrowserStack Automate plan and projects: plan name, parallel sessions running and allowed (user and team), sessions queued and the queue limit…
  • browserstack_list_buildsRecent BrowserStack Automate builds, newest first: id, name, status (running, done, timeout, failed), duration and tag.
  • browserstack_get_buildOne BrowserStack Automate build's sessions, newest first: name, status, failure reason, platform (OS, browser or device)…
  • browserstack_get_sessionOne BrowserStack Automate session: name, status and the reason (as marked or as BrowserStack ended it), platform, duration, build, project, priority…
  • browserstack_tm_projectsBrowserStack Test Management projects, with the PR- identifiers the other Test Management tools take.
  • browserstack_tm_test_casesTest cases in a BrowserStack Test Management project: id, title, priority, type, status, automation status, folder, tags, linked issues…
  • browserstack_tm_test_runsTest runs in a BrowserStack Test Management project: id, name, state (new, in progress, under review, rejected, done, closed)…
  • browserstack_tm_run_resultsThe results recorded in a BrowserStack Test Management test run: test case, status (Passed, Failed, Blocked, Retest...), notes…

Acts, when you ask

These change something in BrowserStack. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

  • browserstack_set_session_statusMarks a BrowserStack Automate session passed or failed with a reason, overriding the status BrowserStack recorded…
  • browserstack_rename_sessionRenames a BrowserStack Automate session.
  • browserstack_delete_sessionPermanently deletes a BrowserStack Automate session with its video and logs; BrowserStack says deleted sessions cannot be recovered.
  • browserstack_rename_buildRenames a finished BrowserStack Automate build (letters, digits and . : - [ ] / @ & ' _ only, up to 255).
  • browserstack_delete_buildPermanently deletes a BrowserStack Automate build and every session in it, with their videos and logs…
  • browserstack_tm_create_test_runCreates a test run in a BrowserStack Test Management project with the named test cases (or every test case in the project when include_all is set)…
  • browserstack_tm_clone_test_runCreates a new BrowserStack test run by cloning an existing one, with all its test cases or only those whose latest result had the given statuses…
  • browserstack_tm_close_test_runCloses a BrowserStack Test Management test run, so it stops taking results.
  • browserstack_tm_delete_test_runPermanently deletes a BrowserStack Test Management test run and the results recorded in it.
  • browserstack_tm_add_test_resultRecords a result for a test case in a BrowserStack test run (a status that exists in Test Management, such as Passed, Failed, Blocked…
  • browserstack_tm_create_test_caseCreates a test case in a folder of a BrowserStack Test Management project, with optional description, preconditions, steps…

Connect it

First connect BrowserStack on Dashboard → Connections, then add Memtro to your client once. The BrowserStack tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Pi

One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared BrowserStack connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

  • › Which sessions failed in last night's build, and why?
  • › How many parallel sessions are we using right now?
  • › How far along is the regression test run?
  • › Which test cases failed in the release candidate run?
  • › Clone the regression run with only the failed test cases.

Questions

Is this an official BrowserStack MCP server?
No. It is Memtro's MCP server with Memtro's BrowserStack connector behind it: the connector reads BrowserStack through its API with the credentials you connect on Dashboard → Connections, and BrowserStack publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?
Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in BrowserStack?
Only when you ask, and only what it has been granted: mark an Automate session passed or failed; rename an Automate session; delete an Automate session; rename an Automate build; delete an Automate build and its sessions; create a test run; clone a test run; close a test run; delete a test run; record a test result in a test run; create a test case. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
Which clients work?
Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations

Where agents remember your company

Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.

7-day free trial · card on file, nothing charged until it ends · cancel any time