Integration

Currents integration

Currents test-results dashboard API for Cypress and Playwright suites: read a run with every spec and its outcome, find the run that matches a CI build or branch, cancel or reset a run, browse projects and their run history and pull requests, pull project-level insights over a date range, drill into one spec-file execution, and query the spec-file, test and error explorers for flakiness, failure rates and durations. Every response is wrapped in a status and data envelope.

Connect Currents How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Currents.Built from the 17 Currents tools below, on the connection you add once.

Common Currents use cases

reporting on why a CI run failed
reporting weekly suite health to a team
listing the flakiest tests to quarantine
showing test status per open pull request
finding the commit that first broke a test
recovering a run after a CI worker crashed
extracting the stack trace of a failing test
stopping a run after a bad commit was pushed
auditing where run notifications are being sent
finding the one error behind a wave of failures

What you can do with Currents

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.

Run, 6 operations

cancel_runCancel runPUTCancels an in-progress run so its remaining specs are not executed.
delete_runDelete runDELETEDeletes a run permanently, together with its recorded results.
find_runFind runGETFinds the latest completed run for a CI build id, branch or set of tags.
get_runGet runGETReads a full run, including every spec file and its test counters.
list_project_runsList project runsGETLists a project's runs filtered by tag, branch, author, status or date.
reset_runReset runPUTReleases the specs claimed by given machines so another worker can pick them up.

Project, 2 operations

get_projectGet projectGETReads a single project with its default branch and timeout settings.
list_projectsList projectsGETLists projects with their identifiers and default settings.

Error, 1 operation

list_errorsList errorsGETLists recurring test failure messages with counts and a timeline.

Insight, 1 operation

get_project_insightsGet project insightsGETReads run and test totals plus a timeline for a project over a date range.

Instance, 1 operation

get_instanceGet instanceGETReads a single spec file execution, with each test, attempt and error.

Pull request, 1 operation

list_pull_requestsList pull requestsGETLists pull requests with a preview of their most recent runs.

Spec file, 1 operation

list_spec_filesList spec filesGETLists spec files with their duration, failure rate and flakiness metrics.

Term, 1 operation

list_project_termsList project termsGETLists the tags, branches, groups or authors a project has recorded, with counts.

Test, 1 operation

list_testsList testsGETLists tests with their execution, failure, flakiness and duration metrics.

Test result, 1 operation

list_test_resultsList test resultsGETLists every recorded execution of one test, with commit, outcome and attempts.

Webhook, 1 operation

list_webhooksList webhooksGETLists the webhooks a project sends run notifications to.

Use Currents from Claude Code, Cursor or Codex

Connect Currents in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Currents 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 Currents

Create your workspace
Sign up free. Nothing to install.
Connect Currents once
Add your Currents 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.

Currents integration FAQ

What can you do with the Currents integration?

LiveContext exposes 17 operations on Currents, covering run, project, error and insight. Common uses include reporting on why a CI run failed, reporting weekly suite health to a team and listing the flakiest tests to quarantine.