Lets AI coding agents query CI test runs, spec files, and test results from the Currents dashboard to diagnose failures and flaky tests.
Also known as currents-dev/currents-mcp, currents-mcp, @currents/mcp
- Stars
- 21
- Tools
- 43
- Downloads, 30 days
- 321,912
- Latest version
- 1.0.0
- Last commit
- Nov 13, 2026
- License
- Apache-2.0
What is Currents MCP?
Currents lets AI coding agents query CI test runs, spec files, and test results from the Currents dashboard to diagnose failures and flaky tests. It exposes 43 tools, such as currents-list-actions, currents-create-action, currents-get-action.
Summary generated from the project's README
About Currents MCP server
Diagnosing CI failures and flaky tests directly from your coding environment is what Currents enables for developers using AI agents. By connecting tools like Claude or Cursor to your Currents dashboard, your agent gains visibility into real execution data, allowing it to move beyond guesswork when fixing broken code. This connection requires a CURRENTS_API_KEY to function.
Developers use this server to query specific runs, spec files, and individual test results. The available tools allow an agent to manage project settings, handle quarantine rules, and monitor error trends or performance metrics. It can also interact with Jira to create or link issues to specific test runs. Through commands like currents-get-run-details and currents-get-project-insights, an agent can retrieve status, commit information, and aggregated metrics to understand the health of a test suite.
What you can do with it
- 1Diagnose flaky test failuresAsk your AI agent to investigate why a specific test is failing by looking at its recent execution history.
- 2Analyze project performance metricsRequest a summary of error trends and performance metrics for a specific project over a set timeframe.
- 3Manage test quarantine rulesInstruct an agent to programmatically update or manage quarantine rules and other project settings.
- 4Integrate test failures with JiraHave an AI agent create a new Jira issue automatically when it identifies a failing test run.
Written from the project's README. Every use case is checked against a quote from it.
How to install Currents MCP
Formats verified 10 Nov 2026Install Currents MCP in Claude Code
$ claude mcp add currents-mcp -- npx -y @currents/mcpInstall Currents MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"currents-mcp": {
"command": "npx",
"args": [
"-y",
"@currents/mcp"
]
}
}
}Install Currents MCP in VS Code
.vscode/mcp.json
{
"servers": {
"currents-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@currents/mcp"
]
}
}
}Install Currents MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"currents-mcp": {
"command": "npx",
"args": [
"-y",
"@currents/mcp"
]
}
}
}Install Currents MCP in Codex
~/.codex/config.toml
[mcp_servers.currents-mcp] command = "npx" args = ["-y", "@currents/mcp"]
Install Currents MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"currents-mcp": {
"command": "npx",
"args": [
"-y",
"@currents/mcp"
]
}
}
}Currents MCP tools 43
Detected from the READMEcurrents-list-actionscurrents-create-actioncurrents-get-actioncurrents-update-actioncurrents-delete-actioncurrents-enable-actioncurrents-disable-actioncurrents-list-affected-testscurrents-get-affected-test-executionscurrents-get-action-executionscurrents-get-projectscurrents-get-project
| currents-list-actions | — | |
| currents-create-action | — | |
| currents-get-action | — | |
| currents-update-action | — | |
| currents-delete-action | — | |
| currents-enable-action | — | |
| currents-disable-action | — | |
| currents-list-affected-tests | — | |
| currents-get-affected-test-executions | — | |
| currents-get-action-executions | — | |
| currents-get-projects | — | |
| currents-get-project | — |
Show all 43 toolsShow fewer tools
currents-get-project-insightscurrents-list-pull-requestscurrents-list-project-termscurrents-create-jira-issuecurrents-link-jira-issuecurrents-list-jira-projectscurrents-list-jira-issue-typescurrents-get-runscurrents-get-run-detailscurrents-find-runcurrents-cancel-runcurrents-reset-runcurrents-delete-runcurrents-cancel-run-github-cicurrents-get-spec-instancecurrents-get-spec-files-performancecurrents-get-tests-performancecurrents-get-tests-signaturescurrents-get-test-resultscurrents-get-contextcurrents-get-errors-explorercurrents-get-test-evidencecurrents-create-evidence-linkscurrents-create-sessioncurrents-add-attachmentscurrents-list-webhookscurrents-create-share-linkcurrents-create-webhookcurrents-get-webhookcurrents-update-webhookcurrents-delete-webhook
| currents-get-project-insights | — | |
| currents-list-pull-requests | — | |
| currents-list-project-terms | — | |
| currents-create-jira-issue | — | |
| currents-link-jira-issue | — | |
| currents-list-jira-projects | — | |
| currents-list-jira-issue-types | — | |
| currents-get-runs | — | |
| currents-get-run-details | — | |
| currents-find-run | — | |
| currents-cancel-run | — | |
| currents-reset-run | — | |
| currents-delete-run | — | |
| currents-cancel-run-github-ci | — | |
| currents-get-spec-instance | — | |
| currents-get-spec-files-performance | — | |
| currents-get-tests-performance | — | |
| currents-get-tests-signatures | — | |
| currents-get-test-results | — | |
| currents-get-context | — | |
| currents-get-errors-explorer | — | |
| currents-get-test-evidence | — | |
| currents-create-evidence-links | — | |
| currents-create-session | — | |
| currents-add-attachments | — | |
| currents-list-webhooks | — | |
| currents-create-share-link | — | |
| currents-create-webhook | — | |
| currents-get-webhook | — | |
| currents-update-webhook | — | |
| currents-delete-webhook | — |
Configuration
CURRENTS_API_KEY
| Name | Description | |
|---|---|---|
| CURRENTS_API_KEY | — |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubCurrents MCP Server
Give your AI coding agents full visibility into your CI test results. The Currents MCP Server connects tools like Cursor and Claude directly to your Currents dashboard, so agents can diagnose flaky tests, pinpoint failures, and act on real execution data -- without leaving your editor.
- Query runs, spec files, and individual test results from CI
- Surface error trends and performance metrics across your test suite
- Manage quarantine rules, webhooks, and project settings programmatically
- Let agents fix what's broken using actual test output, not guesswork
Tools
| Tool | Description |
|---|---|
currents-list-actions |
List all actions for a project with optional filtering. |
currents-create-action |
Create a new action for a project. |
currents-get-action |
Get a single action by ID. |
currents-update-action |
Update an existing action. |
currents-delete-action |
Delete (archive) an action. |
currents-enable-action |
Enable a disabled action. |
currents-disable-action |
Disable an active action. |
currents-list-affected-tests |
List tests affected by actions (quarantine, skip, tag) for a project within a date range. |
currents-get-affected-test-executions |
Keyed on a test: lists the executions of one test that an action applied to, within a date range, with the run, branch and commit of each. |
currents-get-action-executions |
Keyed on an action: lists the test executions one rule was applied to, across every test it touched, within a date range. |
currents-get-projects |
Retrieves projects available in the Currents platform. |
currents-get-project |
Get a single project by ID. |
currents-get-project-insights |
Get aggregated run and test metrics for a project within a date range. |
currents-list-pull-requests |
List pull-request cards for a project (runs grouped by meta.pr.id). |
currents-list-project-terms |
List cursor-paginated project terms for one type (tag, branch, authorName, etc.). |
currents-create-jira-issue |
Create a Jira issue from a run test using the organization Jira integration. |
currents-link-jira-issue |
Link an existing Jira issue to a run test using the organization Jira integration. |
currents-list-jira-projects |
List Jira projects available for the organization integration. |
currents-list-jira-issue-types |
List Jira issue types and custom fields for a Jira project. |
currents-get-runs |
Retrieves a list of runs for a specific project with optional filtering. |
currents-get-run-details |
Retrieves a run: its status, commit, branch, groups and spec files, each with its instanceId, and how many files the run has by level, type and source (attachmentCounts). |
currents-find-run |
Find a run by query parameters. |
currents-cancel-run |
Cancel a run in progress. |
currents-reset-run |
Reset failed spec files in a run to allow re-execution. |
currents-delete-run |
Delete a run and all associated data. |
currents-cancel-run-github-ci |
Cancel a run by GitHub Actions workflow run ID and attempt number. |
currents-get-spec-instance |
Retrieves the raw result of one spec file execution by instanceId: each test's state and attempts, and the artifact URLs. |
currents-get-spec-files-performance |
Retrieves spec files performance metrics for a specific project within a date range. |
currents-get-tests-performance |
Retrieves aggregated test metrics for a specific project within a date range. |
currents-get-tests-signatures |
Generates a unique test signature based on project, spec file path, and test title. |
currents-get-test-results |
Retrieves historical test execution results for a specific test signature. |
currents-get-context |
Call this first to find out why tests failed in CI, or to fix them: returns the errors, steps and files of the failed tests of a run, a spec file (instance) or one test — the same content as Fix in the Currents dashboard. |
currents-get-errors-explorer |
Get aggregated error metrics for a project within a date range. |
currents-get-test-evidence |
Collect evidence artifacts (screenshots, videos, traces, attachments) produced by tests in a CI run, with signed download URLs grouped per test. |
currents-create-evidence-links |
Create a shareable trace API link to a test attempt's evidence, served from its Playwright trace, and the URLs onto it: a markdown trace summary (the digest URL) of what the attempt did and what failed, a filmstrip, an animated screencast, DOM snapshots, network requests and attachments. |
currents-create-session |
Record a browser session you drove as a Currents session, so its evidence can be read and shared. |
currents-add-attachments |
Add attachments to a session from currents-create-session (send sessionId), or to a CI run (send runId): logs for a spec file, a test, or the run itself. |
currents-list-webhooks |
List all webhooks for a project. |
currents-create-share-link |
Create a public link to test results that anyone can open without signing in, until it expires. purpose "fix" is the failure context, for an agent that will fix the tests — the same content as currents-get-context, with flaky tests included and marked flaky. purpose "report" lists every test with its attempts and files, for a person; for a session it is the session page: status, error, attachments and trace. |
currents-create-webhook |
Create a new webhook for a project. |
currents-get-webhook |
Get a single webhook by ID. |
currents-update-webhook |
Update an existing webhook. |
currents-delete-webhook |
Delete a webhook. |
Skills
Agent skills that teach AI agents multi-step Currents workflows.
| Skill | Description |
|---|---|
browser-evidence |
Experimental: prove a change works in a browser you drove yourself, when there is no test to run. |
collect-evidence |
Show that work you implemented actually works, or demo it, from tests that ran in CI via Currents — a trace API link whose trace summary, filmstrip and accessibility snapshots read inside a comment, plus screenshots, attachments and videos. |
fix-failing-tests |
Fix tests that failed in CI, using the results Currents recorded — errors, steps, traces, screenshots and console output. |
The server publishes every skill as an MCP resource, so a connected agent can list and read them without a local copy:
skill://currents/collect-evidence/SKILL.md
skill://currents/collect-evidence/references/instrumentation.md
Agents that load skills only from disk still need a copy — put the skill
directory in the agent's skills location (e.g. .claude/skills/ for Claude
Code).
Setup
API Key
Get a Currents API key by following the instructions here.
Usage with Cursor
- Go to Cursor Settings > MCP > Enable
- Add the following to your
mcp.json.
{
"mcpServers": {
"currents": {
"command": "npx",
"args": ["-y", "@currents/mcp"],
"env": {
"CURRENTS_API_KEY": "your-api-key"
}
}
}
}
Currents MCP questions
How do I add Currents MCP to Claude Code?
Run claude mcp add currents-mcp -- npx -y @currents/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Currents MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Currents MCP provide?
It exposes 43 tools, including currents-list-actions, currents-create-action, currents-get-action, currents-update-action, currents-delete-action.
What does the Currents MCP server let AI agents do?
It connects coding agents to the Currents dashboard so they can query runs, spec files, and test results, surface error trends, and manage quarantine rules and project settings.
Can agents create or link Jira issues through this server?
Yes, the server includes tools to create a Jira issue from a run test, link an existing Jira issue, and list Jira projects and issue types.
Can I manage quarantine and skip rules with this MCP server?
Yes, tools let agents list, create, update, delete, enable, and disable actions such as quarantine, skip, and tag rules for a project.
Does it support Cursor and Claude?
The Currents MCP Server is designed to connect tools like Cursor and Claude to your Currents dashboard.