
Currents MCP Server: Setup for Claude, Cursor and Other Apps
Lets Claude and Cursor read your Currents CI test runs, find flaky tests and manage quarantine rules and webhooks.
This is Currents' own server for its test dashboard. Your assistant can look up failed runs, see why a test broke, check how flaky a test has been, and file Jira issues from a failure. It runs on your computer with a Currents API key, and the same server is also available as a hosted address. It can also change things in Currents: it can delete runs, rules and webhooks, so check what the assistant plans to do before you approve it.
Good for
- Developers who want Claude or Cursor to fix tests that failed in CI
- QA engineers tracking flaky tests and slow spec files
- Teams that manage quarantine rules and webhooks in Currents
- Anyone who files Jira bugs from failed test runs
Works in
12 should work
Tap an app to see how to set it up and any known problems.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Supports local MCP servers.
Client does not support this transport.
Client does not support this transport.
Install Currents MCP
Claude Code
- 1
Copy this prompt.
Add the Currents MCP server to Claude Code. Run this command: claude mcp add currents -e CURRENTS_API_KEY=<CURRENTS_API_KEY> -- npx -y @currents/mcp Ask me for CURRENTS_API_KEY and only put the values in that config, nowhere else. Then check that it loaded and tell me if I need to sign in or restart.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Requires Node.js.
Built from the package data we hold. Not yet tested by us.
Tools
Shows why a CI run, spec file or test failed, with errors and steps
Returns the errors, steps and files of the failed tests in a run, a spec file or a single test. It is the same content as the Fix button in the Currents dashboard, and the server tells the assistant to call it first when tests fail.
Try: “Why did the checkout tests fail in the latest CI run on main?”
Network ·
currents-get-contextLists recent test runs for a project, with filters
Lists runs for a project and filters them by branch, tags, status, date range, author or free text such as a commit message or pull request title. It needs a project ID, which the assistant can look up first.
Try: “Show the failed runs on the main branch from the last 3 days.”
Network ·
currents-get-runsShows one run: status, commit, branch and spec files
Returns a run's status, commit, branch, groups and spec files, each with its instance ID, and how many attached files the run has.
Try: “Give me the details of this run: https://app.currents.dev/run/abc123”
Network ·
currents-get-run-detailsFinds a run from details such as a commit or build
Looks up a run by query parameters instead of its ID, for when you know the branch, commit or CI build but not the run.
Try: “Find the run for commit 4f2a9c1 in the web-app project.”
Network ·
currents-find-runShows the raw result of one spec file execution
Returns each test's state and attempts for one spec file execution, plus links to its artifacts such as screenshots.
Try: “Show every attempt of the tests in checkout.spec.ts for this run.”
Network ·
currents-get-spec-instanceShows the history of one test across runs
Returns past executions of a single test, found by its signature. You can filter by date, branch, tags, author, status or flaky state.
Try: “Has the 'applies coupon' test failed on main in the last two weeks?”
Network ·
currents-get-test-resultsWorks out the ID used to look up one test
Builds the unique signature for a test from the project, spec file path and test title. The history tools need this signature.
Try: “Get the signature for the 'logs in' test in auth.spec.ts.”
Network ·
currents-get-tests-signaturesRanks tests by failures, flakiness or duration
Returns aggregated metrics per test for a date range. You can sort by failures, flakiness, duration or runs, and filter by spec, title, tags, branches or authors.
Try: “Which 10 tests were flakiest this month?”
Network ·
currents-get-tests-performanceRanks spec files by failure rate, flake rate or duration
Returns metrics per spec file for a date range, sortable by average duration, failure rate, flake rate or timeout rate.
Try: “Which spec files are the slowest on average this quarter?”
Network ·
currents-get-spec-files-performanceGroups errors across a project
Returns aggregated error metrics for a project over a date range, so you can see which errors repeat most.
Try: “What are the most common errors in our CI tests this week?”
Network ·
currents-get-errors-explorerShows project-wide run and test metrics
Returns summary numbers for a project over a date range, such as how many runs passed or failed.
Try: “Give me a pass/fail summary for the web-app project over the last 30 days.”
Network ·
currents-get-project-insightsLists pull requests with their test runs
Returns one card per pull request, with the runs grouped under it.
Try: “Which open pull requests have failing test runs?”
Network ·
currents-list-pull-requestsLists the tags, branches and authors in a project
Returns the values used in a project for one type of term, such as tag, branch or author name. It uses paging for long lists.
Try: “List all branch names that have test runs in this project.”
Network ·
currents-list-project-termsLists the Currents projects you can see
Returns the projects available to your API key. Most other tools need a project ID from here.
Try: “Which Currents projects do I have?”
Network ·
currents-get-projectsShows one project
Returns a single project by its ID.
Try: “Show me the settings of project 'web-app'.”
Network ·
currents-get-projectGets screenshots, videos and traces from a CI run
Collects the files tests produced in a CI run, such as screenshots, videos, traces and attachments, with signed download links grouped by test.
Try: “Get the screenshots and trace for the failed login test in this run.”
Network ·
currents-get-test-evidenceMakes a shareable link to a test's trace and summary
Creates a link built from the test's Playwright trace. It carries a written summary of what the test did and where it failed, plus a filmstrip, screencast, page snapshots and network requests. The link opens without a Currents sign-in and expires.
Try: “Create an evidence link for the failed checkout test so I can paste it in the pull request.”
Write ·
currents-create-evidence-linksMakes a public link to test results
Creates a link that anyone can open without signing in, until it expires. It can hold the failure details for an agent that will fix the tests, or a full report for a person. The tool is meant to be used only when you ask to hand results to someone.
Try: “Create a share link of this run's failures I can send to my teammate.”
Write ·
currents-create-share-linkRecords a browser session you drove as a Currents session
Saves a browser session as a Currents session so its evidence can be read and shared. It returns upload links for the files you declare. Uploading the files needs a shell on your machine.
Try: “Record this browser session against my pull request so the trace can be reviewed.”
Write ·
currents-create-sessionAdds log files or other files to a session or CI run
Declares attachments on a session or a CI run, such as logs for a spec file, a test or the run itself. It returns upload links, and the files themselves are uploaded separately.
Try: “Attach the Docker log to this run.”
Write ·
currents-add-attachmentsLists rules that quarantine, skip or tag tests
Lists a project's actions, the rules that quarantine, skip or tag tests, with optional filtering.
Try: “What quarantine rules are active on the web-app project?”
Network ·
currents-list-actionsShows one rule
Returns a single action by its ID.
Try: “Show me the quarantine rule with ID act_42.”
Network ·
currents-get-actionLists tests hit by quarantine, skip or tag rules
Lists the tests that actions applied to in a date range.
Try: “Which tests were quarantined in the last month?”
Network ·
currents-list-affected-testsShows when a rule was applied to one test
Lists the executions of one test that an action applied to, with the run, branch and commit of each.
Try: “When was the 'applies coupon' test last skipped by a rule, and in which run?”
Network ·
currents-get-affected-test-executionsShows every test one rule was applied to
Lists the test executions that one action touched, across all tests, in a date range.
Try: “Show every execution the 'quarantine flaky' rule affected this week.”
Network ·
currents-get-action-executionsCreates a quarantine, skip or tag rule
Creates a new action for a project. The rule then changes how matching tests run in later CI runs.
Try: “Create a rule that quarantines the 'applies coupon' test.”
Write ·
currents-create-actionChanges an existing rule
Updates an existing action's settings.
Try: “Change the quarantine rule so it only applies to the main branch.”
Write ·
currents-update-actionTurns a disabled rule back on
Enables an action that was disabled.
Try: “Turn the quarantine rule back on.”
Write ·
currents-enable-actionTurns a rule off without deleting it
Disables an active action.
Try: “Disable the skip rule for the payments tests.”
Write ·
currents-disable-actionArchives a rule
Deletes (archives) an action.
Try: “Delete the old tagging rule.”
Delete ·
currents-delete-actionStops a run that is in progress
Cancels a run that is still running.
Try: “Cancel the run on the release branch.”
Write ·
currents-cancel-runStops a run by its GitHub Actions run
Cancels a run using the GitHub Actions workflow run ID and attempt number.
Try: “Cancel the Currents run for GitHub Actions run 8123456, attempt 1.”
Write ·
currents-cancel-run-github-ciLets failed spec files in a run run again
Resets the failed spec files in a run so they can be executed again.
Try: “Reset the failed specs in this run so CI retries them.”
Write ·
currents-reset-runDeletes a run and all its data
Deletes a run together with everything stored for it.
Try: “Delete the run from the broken test branch.”
Delete ·
currents-delete-runFiles a Jira issue for a failed test
Creates a Jira issue from a test in a run, using the Jira integration your organization has set up in Currents.
Try: “Create a Jira bug for the failed checkout test in this run.”
Write ·
currents-create-jira-issueLinks an existing Jira issue to a failed test
Links a Jira issue you already have to a test in a run.
Try: “Link PROJ-123 to the failed login test.”
Write ·
currents-link-jira-issueLists Jira projects available for the integration
Returns the Jira projects your organization's integration can reach.
Try: “Which Jira projects can I file test failures in?”
Network ·
currents-list-jira-projectsLists Jira issue types and fields for a project
Returns the issue types and custom fields of a Jira project.
Try: “What issue types does the QA Jira project have?”
Network ·
currents-list-jira-issue-typesLists a project's webhooks
Lists all webhooks set up for a project.
Try: “Which webhooks does the web-app project have?”
Network ·
currents-list-webhooksShows one webhook
Returns a single webhook by its ID.
Try: “Show the settings of the Slack webhook.”
Network ·
currents-get-webhookAdds a webhook to a project
Creates a webhook so Currents can send run events to a URL.
Try: “Create a webhook that posts failed runs to https://example.com/hooks/ci.”
Write ·
currents-create-webhookChanges a webhook
Updates an existing webhook.
Try: “Point the Slack webhook at the new URL.”
Write ·
currents-update-webhookDeletes a webhook
Deletes a webhook from a project.
Try: “Delete the old Slack webhook.”
Delete ·
currents-delete-webhook
Read from the source code
Permissions
high risk · 4 things to watch
High risk
The assistant can read your test results and also delete runs, rules and webhooks, change quarantine rules and make public links to test results. Use a key from a project you can afford to change, and approve each write or delete yourself.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
It can delete runs, rules and webhooks
Delete tools remove a run and all its data, archive a rule or delete a webhook. Ask the assistant to confirm before it calls them. github.com
It can change how tests run
Creating, updating, disabling or enabling a rule can quarantine or skip tests in later CI runs. Read the rule before you approve it. github.com
It can make public links to test results
Share and evidence links open without signing in until they expire. Create one only when you mean to hand results to someone. github.com
Your test data goes to your AI app
Results, errors and CI details pass through whichever assistant you connect. The README tells you to vet any AI service you give access. github.com
Security advisories
No published security advisories as of Nov 1, 2026.
Technical details
| Turning on read-only | No read-only mode is documented. The local server turns on every tool whatever the key allows, because it cannot see its key's scope. |
|---|---|
| Talks to | Currents API (api.currents.dev) |
| Sign-in and keys | Your Currents API key goes in the CURRENTS_API_KEY setting of your MCP config. The hosted address takes the same key as a Bearer token. |
| Scopes |
|
Questions
Is the Currents MCP server official?
Yes. It is published by Currents (the currents-dev organization) for its own test dashboard.
Do I need a Currents API key?
Yes. Create one by following the Currents API key guide, then put it in the CURRENTS_API_KEY setting shown in the install box.
What is the Currents MCP server URL?
The hosted address is https://mcp.currents.dev/mcp. It needs your Currents API key sent as an Authorization Bearer header. VS Code's install link instead opens a Currents sign-in page, so no key is needed there.
Can it be read-only?
No read-only switch is documented, and the local server turns on all tools. Use a key for a project where changes are acceptable.
Can it delete my test runs?
Yes. It has tools that delete a run, archive a rule and delete a webhook, so approve those calls one at a time.
Does it work with Claude Code and Cursor?
Yes. The README gives setup for Cursor, Claude Code, Claude Desktop, VS Code with GitHub Copilot and Copilot CLI. Follow the tab for your app in the install box.
Does it include skills?
Yes, but separately. The repository also ships three skills for fixing failing tests and collecting evidence, and the server lists them as resources. The skills are not required for the tools to work.
Information
updated Nov 2, 2026
- Publisher
- Official
- Package
@currents/mcp- Registry
- npm
- Endpoint
https://mcp.currents.dev/mcp- Transport
- stdio, Streamable HTTP
- Auth
- API key
- Version
- 1.0.0
- License
- Apache-2.0
- Last commit
- Oct 30, 2026
- Open issues
- 0
- Listed in
- Official MCP registry
Sources
Docs, issue trackers and discussions this page is built from. Issues, quotes and findings above link to their own source.
Show all 2Hide
- github.com · github.com
- github.com · github.com