Currents MCP Server

Endpoint

Hosted endpoint · transport streamable-http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• currents-get-projects — Lists the projects
• currents-get-project — Gets one project and its settings
• currents-list-project-terms — Lists the tags, branches, authors and other values in a project's runs
• currents-get-runs — Lists a project's runs, filtered by branch, tag, status, date or text
• currents-get-run-details — Gets one run: its status, commit, branch, groups and spec files
• currents-find-run — Finds the latest completed run by CI build ID, branch or tags
• currents-get-spec-instance — Gets the raw result of one spec file execution
• currents-get-test-results — Gets the history of one test
• currents-get-context — Gets why tests failed: the errors, steps and files of a run, a spec file or a test
• currents-get-test-evidence — Lists the screenshots, videos, traces and attachments of each test in a CI run
• currents-create-evidence-links — Creates a trace API link for a test attempt or a session trace
• currents-list-pull-requests — Lists a project's pull requests with their runs
• currents-get-project-insights — Gets run and test metrics for a project over time
• currents-get-spec-files-performance — Ranks spec files by duration, failures or flakiness
• currents-get-tests-performance — Ranks tests by failures, flakiness or duration
• currents-get-errors-explorer — Groups and counts errors across runs
• currents-list-actions — Lists the actions: rules that skip, quarantine or tag tests
• currents-get-action — Gets one action and its conditions
• currents-list-affected-tests — Lists the tests that actions applied to
• currents-get-affected-test-executions — Lists the executions of one test that an action applied to
• currents-get-action-executions — Lists the test executions that one action applied to
• currents-create-action — Creates an action
• currents-update-action — Changes an action
• currents-delete-action — Archives an action
• currents-enable-action — Turns an action on
• currents-disable-action — Turns an action off
• currents-create-session — Creates a session and returns upload URLs for its files
• currents-add-attachments — Adds files to a session or a CI run
• currents-cancel-run — Cancels a run in progress
• currents-cancel-run-github-ci — Cancels the run of a GitHub Actions workflow run
• currents-reset-run — Resets the failed spec files of a run so they run again
• currents-delete-run — Deletes a run and all its data, permanently
• currents-create-share-link — Creates a public share link to a run, a spec file, a test or a session
• currents-list-webhooks — Lists a project's webhooks
• currents-get-webhook — Gets one webhook
• currents-create-webhook — Creates a webhook that sends run events to a URL
• currents-update-webhook — Changes a webhook
• currents-delete-webhook — Deletes a webhook, permanently
• currents-list-jira-projects — Lists the projects in your connected Jira
• currents-list-jira-issue-types — Lists the issue types and fields of a Jira project
• currents-create-jira-issue — Creates a Jira issue for a test in a run
• currents-link-jira-issue — Links an existing Jira issue to a test in a run
• currents-get-tests-signatures — Computes the ID Currents gives a test from the project, spec file path and test title. Reads no data.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/currents-mcp-server"

curl "https://apis.io/api/v1/mcp?limit=25"