Integration

TestLocally integration

TestLocally (by WonderProxy) loads a web page from real browsers in cities around the world and returns full-page screenshots, thumbnails and video recordings, to check localization, geo-targeted content and regional availability. An agent can list the available test servers (cities), start a test of a URL from up to nine servers with a chosen browser and viewport, read a test's per-city results, list recent tests with filters, and check the current API token. Starting a test counts against the account's daily and monthly test and screenshot limits. Authentication is a TestLocally API token sent as a Bearer token in the Authorization header.

Connect TestLocally How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in TestLocally.Built from the 5 TestLocally tools below, on the connection you add once.

What you can do with TestLocally

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Test, 3 operations

get_testGet testGETReturns one test: target, browser, viewport, servers, locations and one screenshot per server with its state, thumbnail, full-page screenshot and video URLs. Any state but done or error means still running.
list_testsList testsGETLists recent tests matching the filters (time window, owners, locations, target URL, schedule, browser, viewport), paged. Each test carries its per-city screenshots; get_test reads one test by id.
run_testRun testPOSTStarts a test: loads target from each listed server and screenshots it. Returns the test id at once; call get_test until every screenshot state is done or error. Counts against the account's test limits.

Me, 1 operation

get_token_infoGet token infoGETReturns the account behind the current API token (user id, email, team) and the token's name, creation date and expiry. Use it to check the credential.

Server, 1 operation

list_serversList serversGETLists the TestLocally test servers (cities). Pass a server's name to run_test in servers. Each entry gives city, country, continent, coordinates and whether the server is up.

Use TestLocally from Claude Code, Cursor or Codex

Connect TestLocally in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its TestLocally operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect TestLocally

Create your workspace
Sign up free. Nothing to install.
Connect TestLocally once
Add your TestLocally connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.