Verfy

MCP servers / @currents/mcp

MCP tool changes

@currents/mcp

3 of its last 5 updates changed what the agent reads: 11 tool descriptions rewritten, up to 2.7.0.

npm package · last recorded on 13 November 2026 on a clean machine with placeholder settings; only tools/list was sent. A changed description is not a vulnerability. npm page · Method and limits · this data as JSON.

Release by release

2.6.1 → 2.7.0

minor release, 14 October 2026

Added: currents-add-attachments, currents-create-evidence-links, currents-create-session, currents-create-share-link, prompt:fix-failing-tests

currents-cancel-run: title, annotations or output schema changed

currents-cancel-run-github-ci: title, annotations or output schema changed

currents-create-action: title, annotations or output schema changed

currents-create-jira-issue: title, annotations or output schema changed

currents-create-webhook: description changed
Before (2.6.1)
Create a new webhook for a project. Specify the URL to receive POST notifications, optional custom headers (as JSON string), events to trigger on (RUN_FINISH, RUN_START, RUN_TIMEOUT, RUN_CANCELED), and an optional label. Requires projectId and url.
After (2.7.0)
Create a new webhook for a project. Specify the URL to receive POST notifications, optional custom headers (as JSON string), events to trigger on (RUN_FINISH, RUN_START, RUN_TIMEOUT, RUN_CANCELED), and an optional label. Requires projectId and url. The payload Currents sends and how to verify it are documented at https://docs.currents.dev/resources/integrations/http-webhooks.

currents-delete-action: title, annotations or output schema changed

currents-delete-run: title, annotations or output schema changed

currents-delete-webhook: title, annotations or output schema changed

currents-disable-action: title, annotations or output schema changed

currents-enable-action: title, annotations or output schema changed

currents-find-run: title, annotations or output schema changed

currents-get-action: title, annotations or output schema changed

currents-get-action-executions: title, annotations or output schema changed

currents-get-affected-test-executions: title, annotations or output schema changed

currents-get-context: description and input schema changed; new arguments: include_flaky
Before (2.6.1)
Get test failure context for AI debugging at run, instance, or test level. Supports json or md format, detail level, and pagination for failed tests. Requires run_id for run-level, or instance_id with optional test_id.
After (2.7.0)
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. Takes the IDs from dashboard links: /run/<runId> is run_id, /instance/<instanceId>/test/<testId> (or /i/<instanceId>/test/<testId>) is instance_id and test_id. Flaky tests are left out of a run unless include_flaky is set. The context of a run lists the attachments of the run itself, by CI machine (`runAttachments`). Supports json or md format, detail level, and pagination for failed tests. Target a run (run_id), a spec file (run_id + instance_id) or a test (instance_id + test_id). The steps for fixing them are at skill://currents/fix-failing-tests/SKILL.md.

currents-get-errors-explorer: title, annotations or output schema changed

currents-get-project: title, annotations or output schema changed

currents-get-project-insights: title, annotations or output schema changed

currents-get-projects: title, annotations or output schema changed

currents-get-run-details: description changed
Before (2.6.1)
Retrieves details of a specific test run. Requires a user-provided runId.
After (2.7.0)
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`). Requires runId, the ID in a /run/<runId> dashboard link. For why the run's tests failed, and for the files attached to the run itself such as Docker logs, call currents-get-context with run_id instead; for its screenshots, videos and traces, currents-get-test-evidence.

currents-get-runs: title, annotations or output schema changed

currents-get-spec-files-performance: title, annotations or output schema changed

currents-get-spec-instance: description changed
Before (2.6.1)
Retrieves debugging data from a specific execution of a test spec file by instanceId.
After (2.7.0)
Retrieves the raw result of one spec file execution by instanceId: each test's state and attempts, and the artifact URLs. For why its tests failed, currents-get-context with run_id and instance_id returns the errors, steps and trace links ready to read.
currents-get-test-evidence: description changed
Before (2.6.1)
Collect evidence artifacts (screenshots, videos, traces, attachments) produced by tests in a CI run, with signed download URLs grouped per test. Use to gather proof or a demo of an implemented feature from CI — e.g. before/after screenshots, text output stored as test attachments, or Playwright videos and traces — instead of running tests locally. Locates the run by runId, or by projectId with ciBuildId or branch (latest run). Supports filtering by spec file, test title, and test status. URLs are signed and time-limited, so download the files promptly.
After (2.7.0)
Collect evidence artifacts (screenshots, videos, traces, attachments) produced by tests in a CI run, with signed download URLs grouped per test. Read skill://currents/collect-evidence/SKILL.md before the first call. Use to gather proof or a demo of an implemented feature from CI — e.g. before/after screenshots, text output stored as test attachments, or Playwright videos and traces — instead of running tests locally. Locates the run by runId, or by projectId with ciBuildId or branch (latest run). Supports filtering by spec file, test title, and test status. URLs are signed and time-limited, so download the files promptly.

currents-get-test-results: title, annotations or output schema changed

currents-get-tests-performance: title, annotations or output schema changed

currents-get-tests-signatures: title, annotations or output schema changed

currents-get-webhook: title, annotations or output schema changed

currents-link-jira-issue: title, annotations or output schema changed

currents-list-actions: title, annotations or output schema changed

currents-list-affected-tests: title, annotations or output schema changed

currents-list-jira-issue-types: title, annotations or output schema changed

currents-list-jira-projects: title, annotations or output schema changed

currents-list-project-terms: title, annotations or output schema changed

currents-list-pull-requests: title, annotations or output schema changed

currents-list-webhooks: title, annotations or output schema changed

currents-reset-run: title, annotations or output schema changed

currents-update-action: title, annotations or output schema changed

currents-update-webhook: description changed
Before (2.6.1)
Update an existing webhook. You can update the url, headers (as JSON string), hookEvents array, or label. All fields are optional. The hookId is a UUID.
After (2.7.0)
Update an existing webhook. You can update the url, headers (as JSON string), hookEvents array, or label. All fields are optional. The hookId is a UUID. The payload Currents sends and how to verify it are documented at https://docs.currents.dev/resources/integrations/http-webhooks.
prompt:browser-evidence: description changed
Before (2.6.1)
Prove a change works in a browser you drove yourself, when there is no test to run — reproduce a bug, fix it, and post before/after evidence on a pull request or issue. Use when asked to "reproduce this", "show the bug", "prove the fix", "record a session", "capture before and after", or to demonstrate a change on a ticket that has no automated test. Records the browser as a Currents run and returns links that read without a Currents login. For evidence from tests that already run in CI, use collect-evidence instead.
After (2.7.0)
Experimental: prove a change works in a browser you drove yourself, when there is no test to run. Use when asked to "reproduce this", "show the bug", "prove the fix", "record a session", "capture before and after", or to demonstrate a change on a ticket that has no automated test. Reproduce a bug, fix it, record each state as a Currents session, and post before/after evidence on a pull request or issue with a link that reads without a Currents login. For evidence from tests that already run in CI, use collect-evidence instead.
prompt:collect-evidence: description changed
Before (2.6.1)
Show that work you implemented actually works, or demo it, using artifacts from tests running in CI via Currents — before/after screenshots, text and JSON attachments, videos, traces, and GIFs. Use when asked to "collect evidence", "prove it works", "show me it works", "demo the feature", "capture a before/after", or to attach proof of a change to a PR, issue, ticket, or status update. Evidence comes from CI runs retrieved through the Currents MCP tools or REST API, not from a local run.
After (2.7.0)
Show that work you implemented actually works, or demo it, from tests that ran in CI via Currents — a trace link whose digest, filmstrip and accessibility snapshots read inside a comment, plus screenshots, attachments and videos. Use when asked to "collect evidence", "prove it works", "show me it works", "demo the feature", "capture a before/after", or to attach proof of a change to a PR, issue, ticket, or status update. Evidence comes from CI runs retrieved through the Currents MCP tools or REST API, not from a local run.

2.6.0 → 2.6.1

patch release, 23 September 2026

No tool definition changed.

2.5.0 → 2.6.0

minor release, 23 September 2026

Added: currents-get-action-executions, prompt:browser-evidence, prompt:collect-evidence

Removed: currents-get-affected-executions

currents-cancel-run: title, annotations or output schema changed

currents-cancel-run-github-ci: title, annotations or output schema changed

currents-create-action: title, annotations or output schema changed

currents-create-jira-issue: title, annotations or output schema changed

currents-create-webhook: title, annotations or output schema changed

currents-delete-action: title, annotations or output schema changed

currents-delete-run: title, annotations or output schema changed

currents-delete-webhook: title, annotations or output schema changed

currents-disable-action: title, annotations or output schema changed

currents-enable-action: title, annotations or output schema changed

currents-find-run: title, annotations or output schema changed

currents-get-action: title, annotations or output schema changed

currents-get-affected-test-executions: description changed
Before (2.5.0)
Get execution details for a specific affected test (by signature) within a date range. Returns individual test execution records with action info. Uses cursor-based pagination. Requires projectId, signature, date_start, and date_end.
After (2.6.0)
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. Requires projectId, signature, date_start and date_end; if the signature is not known, first call 'currents-get-tests-signatures'. For the executions of one rule across every test it touched, call 'currents-get-action-executions' instead. Uses cursor-based pagination.

currents-get-context: title, annotations or output schema changed

currents-get-errors-explorer: title, annotations or output schema changed

currents-get-project: title, annotations or output schema changed

currents-get-project-insights: title, annotations or output schema changed

currents-get-projects: title, annotations or output schema changed

currents-get-run-details: title, annotations or output schema changed

currents-get-runs: description and input schema changed
Before (2.5.0)
Retrieves a list of runs for a specific project with optional filtering. Supports filtering by branch, tags (with AND/OR operators), status (PASSED/FAILED/RUNNING/FAILING), completion state, date range, commit author, and search by ciBuildId or commit message. Requires a projectId. If the projectId is not known, first call 'currents-get-projects' and ask the user to select the project.
After (2.6.0)
Retrieves a list of runs for a specific project with optional filtering. Supports filtering by branch, tags (with AND/OR operators), status (PASSED/FAILED/RUNNING/FAILING), completion state, date range, commit author, and free-text search over the run's CI build id, commit message, branch, sha, author, pull request title/number/branches, tags, environments, framework and browser. Requires a projectId. If the projectId is not known, first call 'currents-get-projects' and ask the user to select the project.

currents-get-spec-files-performance: title, annotations or output schema changed

currents-get-spec-instance: title, annotations or output schema changed

currents-get-test-evidence: title, annotations or output schema changed

currents-get-test-results: title, annotations or output schema changed

currents-get-tests-performance: title, annotations or output schema changed

currents-get-tests-signatures: title, annotations or output schema changed

currents-get-webhook: title, annotations or output schema changed

currents-link-jira-issue: title, annotations or output schema changed

currents-list-actions: title, annotations or output schema changed

currents-list-affected-tests: title, annotations or output schema changed

currents-list-jira-issue-types: title, annotations or output schema changed

currents-list-jira-projects: title, annotations or output schema changed

currents-list-project-terms: title, annotations or output schema changed

currents-list-pull-requests: description and input schema changed; new arguments: completion_state, date_end, date_start, dir, environments, order, pr_id, pr_search, search
Before (2.5.0)
List pull-request cards for a project (runs grouped by meta.pr.id). Supports cursor pagination, runs_per_pr preview count, and filters by tags, branches, authors, and latest-run status. Requires projectId.
After (2.6.0)
List pull-request cards for a project (runs grouped by meta.pr.id). Run filters (date range, tags, branches, authors, environments, pr_id, search) choose which runs count; status, completion_state and pr_search are checked on each PR's latest run among those runs. Supports order and dir, cursor pagination and the runs_per_pr preview count. Requires projectId.

currents-list-webhooks: title, annotations or output schema changed

currents-reset-run: title, annotations or output schema changed

currents-update-action: title, annotations or output schema changed

currents-update-webhook: title, annotations or output schema changed

2.4.2 → 2.5.0

minor release, 15 September 2026

currents-cancel-run: input schema changed

currents-cancel-run-github-ci: title, annotations or output schema changed

currents-create-action: input schema changed

currents-create-jira-issue: input schema changed

currents-create-webhook: input schema changed

currents-delete-action: input schema changed

currents-delete-run: input schema changed

currents-delete-webhook: input schema changed

currents-disable-action: input schema changed

currents-enable-action: input schema changed

currents-find-run: input schema changed

currents-get-action: input schema changed

currents-get-affected-executions: input schema changed

currents-get-affected-test-executions: input schema changed

currents-get-context: title, annotations or output schema changed

currents-get-errors-explorer: input schema changed

currents-get-project: input schema changed

currents-get-project-insights: input schema changed

currents-get-projects: input schema changed

currents-get-run-details: input schema changed

currents-get-runs: input schema changed

currents-get-spec-files-performance: input schema changed

currents-get-spec-instance: input schema changed

currents-get-test-evidence: title, annotations or output schema changed

currents-get-test-results: input schema changed

currents-get-tests-performance: input schema changed

currents-get-tests-signatures: input schema changed

currents-get-webhook: input schema changed

currents-link-jira-issue: input schema changed

currents-list-actions: input schema changed

currents-list-affected-tests: input schema changed

currents-list-jira-issue-types: title, annotations or output schema changed

currents-list-jira-projects: title, annotations or output schema changed

currents-list-project-terms: input schema changed

currents-list-pull-requests: input schema changed

currents-list-webhooks: input schema changed

currents-reset-run: input schema changed

currents-update-action: input schema changed

currents-update-webhook: input schema changed

2.4.1 → 2.4.2

patch release, 16 August 2026

No tool definition changed.

Releases tried: 2.4.1 (2026-08-16); 2.4.2 (2026-08-16); 2.5.0 (2026-09-15); 2.6.0 (2026-09-23); 2.6.1 (2026-09-23); 2.7.0 (2026-10-14).

Tools in 2.7.0

The pin is the SHA-256 of the tool's name, description and input schema, as verfy.lock records it. The same pin in your lock means your agent reads this exact definition. Verfy 0.16.0 and later also pin a tool's title, annotations and output schema when the server sends them, so such a tool shows a different pin in your lock.

Tools in 2.7.0
ToolDescriptionPin
currents-list-actionsList all actions for a project with optional filtering. Actions are rules that automatically modify test behavior (skip, quarantine, tag). Supports filtering by status (active/disabled/archived/expired) and search by name. Requires a projectId.3e6d5ba1a256
currents-create-actionCreate a new action for a project. Actions define rules that automatically skip, quarantine, or tag tests based on conditions like test title, file path, git branch, etc. Requires projectId, name, action array, and matcher object.a385fc4e11a9
currents-get-actionGet a single action by ID. The actionId is globally unique, so projectId is not required. Returns full action details including matcher conditions and current status.562360bb2def
currents-update-actionUpdate an existing action. The actionId is globally unique. You can update name, description, action array, matcher, or expiration date. All fields are optional.d8f0421c041e
currents-delete-actionDelete (archive) an action. This is a soft delete - the action will be marked as archived but not permanently removed. The actionId is globally unique.b3ef1bd50ec9
currents-enable-actionEnable a disabled action. Changes the action status from disabled to active, making it apply to matching tests again. The actionId is globally unique.0edbee8c34b1
currents-disable-actionDisable an active action. Changes the action status to disabled, temporarily preventing it from applying to tests. The actionId is globally unique.dcf27599286f
currents-list-affected-testsList tests affected by actions (quarantine, skip, tag) for a project within a date range. Returns aggregated data grouped by test signature. Supports filtering by action types, action ID, status, and search. Requires projectId, date_start, and date_end. Preview endpoint: fields and path may change.206dd9423b7f
currents-get-affected-test-executionsKeyed 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. Requires projectId, signature, date_start and date_end; if the signature is not known, first call 'currents-get-tests-signatures'. For the executions of one rule across every test it touched, call 'currents-get-action-executions' instead. Uses cursor-based pagination.fae7bd82f203
currents-get-action-executionsKeyed on an action: lists the test executions one rule was applied to, across every test it touched, within a date range. Requires actionId, date_start and date_end; if the actionId is not known, first call 'currents-list-actions'. For the executions of one test, call 'currents-get-affected-test-executions' instead. Uses cursor-based pagination.2b896b00f989
currents-get-projectsRetrieves projects available in the Currents platform. Supports cursor-based pagination with limit, starting_after, ending_before parameters, or set fetchAll=true for automatic pagination. This is a prerequisite for using any other tools that require project-specific information.8e7a50aa88c1
currents-get-projectGet a single project by ID. Returns project details including name, creation date, failFast setting, inactivity timeout, and default branch name.4898fccb7576
currents-get-project-insightsGet aggregated run and test metrics for a project within a date range. Returns overall metrics and timeline data with configurable resolution (1h/1d/1w). Supports filtering by tags, branches, groups, and authors. Requires projectId, date_start, and date_end.57f06a15ca7e
currents-list-pull-requestsList pull-request cards for a project (runs grouped by meta.pr.id). Run filters (date range, tags, branches, authors, environments, pr_id, search) choose which runs count; status, completion_state and pr_search are checked on each PR's latest run among those runs. Supports order and dir, cursor pagination and the runs_per_pr preview count. Requires projectId.c52e6056d8ec
currents-list-project-termsList cursor-paginated project terms for one type (tag, branch, authorName, etc.). Supports search, sort direction, and starting_after or ending_before cursors. Requires projectId and termType.041fb06539e8
currents-create-jira-issueCreate a Jira issue from a run test using the organization Jira integration. Requires projectId, runId, testId, jiraInstallationId, jiraProjectId, and jiraIssueType. Optional customFields array.bc00f9a95024
currents-link-jira-issueLink an existing Jira issue to a run test using the organization Jira integration. Requires projectId, jiraIssueKey, runId, testId, jiraInstallationId, jiraProjectId, and jiraIssueType. Optional comment and includeContextInComment.30ff85f308e1
currents-list-jira-projectsList Jira projects available for the organization integration. Use returned project IDs as jiraProjectId when creating issues. Requires jira_installation_id.7deeb1012fd1
currents-list-jira-issue-typesList Jira issue types and custom fields for a Jira project. Requires jiraProjectId and jira_installation_id.afac5e2b58cc
currents-get-runsRetrieves a list of runs for a specific project with optional filtering. Supports filtering by branch, tags (with AND/OR operators), status (PASSED/FAILED/RUNNING/FAILING), completion state, date range, commit author, and free-text search over the run's CI build id, commit message, branch, sha, author, pull request title/number/branches, tags, environments, framework and browser. Requires a projectId. If the projectId is not known, first call 'currents-get-projects' and ask the user to select the project.bf72b78a4b5c
currents-get-run-detailsRetrieves 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`). Requires runId, the ID in a /run/<runId> dashboard link. For why the run's tests failed, and for the files attached to the run itself such as Docker logs, call currents-get-context with run_id instead; for its screenshots, videos and traces, currents-get-test-evidence.c45b31aff6ec
currents-find-runFind a run by query parameters. Returns the most recent completed run matching the criteria. Can search by ciBuildId (exact match) or by branch/tags. Supports pwLastRun flag for Playwright last run info. Requires projectId.c7d67855fc08
currents-cancel-runCancel a run in progress. This will stop the run and mark it as cancelled. Requires runId.6fb7f67e059c
currents-reset-runReset failed spec files in a run to allow re-execution. Requires runId and machineId array (1-63 machine IDs). Optionally supports batched orchestration.2f037610df87
currents-delete-runDelete a run and all associated data. This is a permanent deletion. Requires runId.d01d7aa93c4f
currents-cancel-run-github-ciCancel a run by GitHub Actions workflow run ID and attempt number. Optionally scope by projectId or ciBuildId. Requires githubRunId and githubRunAttempt.0c765a84f5a2
currents-get-spec-instanceRetrieves the raw result of one spec file execution by instanceId: each test's state and attempts, and the artifact URLs. For why its tests failed, currents-get-context with run_id and instance_id returns the errors, steps and trace links ready to read.4d709d8ea0e4
currents-get-spec-files-performanceRetrieves spec files performance metrics for a specific project within a date range. Supports ordering by avgDuration, failedExecutions, failureRate, flakeRate, flakyExecutions, fullyReported, overallExecutions, suiteSize, timeoutExecutions, or timeoutRate. Supports filtering by tags, branches, groups, and authors. Requires a projectId. If the projectId is not known, first call 'currents-get-projects' and ask the user to select the project.609adb5cbac0
currents-get-tests-performanceRetrieves aggregated test metrics for a specific project within a date range. Supports ordering by failures, passes, flakiness, duration, executions, title, and various delta metrics. Supports filtering by spec name, test title, tags, branches, groups, authors, minimum executions, test state, and annotations. Requires a projectId. If the projectId is not known, first call 'currents-get-projects' and ask the user to select the project.6b2c0b7b3a81
currents-get-tests-signaturesGenerates a unique test signature based on project, spec file path, and test title. The test title can be a string or array of strings (for nested describe blocks). Requires a projectId. If the projectId is not known, first call 'currents-get-projects' and ask the user to select the project.edcebf601d2b
currents-get-test-resultsRetrieves historical test execution results for a specific test signature. Supports filtering by date range, branch, tags, git author, test status (passed/failed/pending/skipped), run group, flaky status, and annotations. Requires the test signature. If the signature is not known, first call 'currents-get-tests-signatures'.c5d18dbf4990
currents-get-contextCall 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. Takes the IDs from dashboard links: /run/<runId> is run_id, /instance/<instanceId>/test/<testId> (or /i/<instanceId>/test/<testId>) is instance_id and test_id. Flaky tests are left out of a run unless include_flaky is set. The context of a run lists the attachments of the run itself, by CI machine (`runAttachments`). Supports json or md format, detail level, and pagination for failed tests. Target a run (run_id), a spec file (run_id + instance_id) or a test (instance_id + test_id). The steps for fixing them are at skill://currents/fix-failing-tests/SKILL.md.43cd156c0275
currents-get-errors-explorerGet aggregated error metrics for a project within a date range. Supports filtering by error_target, error_message, error_category, error_action, tags, branches, authors, and groups. Supports grouping by target, action, category, or message. Returns error counts, affected tests and branches, with timeline data. Requires projectId, date_start, and date_end.f20a61c470fd
currents-get-test-evidenceCollect evidence artifacts (screenshots, videos, traces, attachments) produced by tests in a CI run, with signed download URLs grouped per test. Read skill://currents/collect-evidence/SKILL.md before the first call. Use to gather proof or a demo of an implemented feature from CI — e.g. before/after screenshots, text output stored as test attachments, or Playwright videos and traces — instead of running tests locally. Locates the run by runId, or by projectId with ciBuildId or branch (latest run). Supports filtering by spec file, test title, and test status. URLs are signed and time-limited, so download the files promptly.d4877db1336e
currents-create-evidence-linksCreate a shareable link to a test attempt's evidence, served from its Playwright trace, and the URLs onto it: a markdown digest of what the attempt did and what failed, a filmstrip, an animated screencast, DOM snapshots, network requests and attachments. Use it to read a trace without downloading it, and to put evidence in a pull request comment or an issue — the link reads without a Currents credential and expires. Start from the digest it returns. For a session recorded with currents-create-session, send sessionId and the trace's attachmentId; for a CI test, instanceId and testId. Before posting evidence, read the workflow at skill://currents/browser-evidence/SKILL.md for a session you recorded, or skill://currents/collect-evidence/SKILL.md for a CI run.7f3d233de453
currents-create-sessionRecord a browser session you drove as a Currents session, so its evidence can be read and shared. Use it when there is no test to run — a bug reproduced by hand, a fix demonstrated in a browser. Pass commit and pr, read from git when you can run git in the repository, so the session shows up by branch and pull request. Returns the sessionId and an upload URL per attachment you declared; more can be added later with currents-add-attachments; PUT the bytes to those, and the response says what to do next. A trace attached this way can then be turned into a link that needs no Currents credential. Read the workflow at skill://currents/browser-evidence/SKILL.md before the first call. With the `currents` command, that workflow uses `currents session` instead of this tool, and it zips the trace and uploads the files for you; use this tool when you have a shell but not the command. Without a shell nothing can upload the files.95c26189c2b8
currents-add-attachmentsAdd 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. For a CI run, name where they go with instanceId and testId (and attempt) or with spec and testTitle; name none for the run itself, with an optional machineId. A session takes none of those. Send each attachment's exact size in bytes. Returns an upload URL per attachment; PUT the bytes to those, and the response says what to do next. A trace can then be turned into a link that needs no Currents credential with currents-create-evidence-links: for a session, with sessionId and the trace's attachmentId; for a CI test attempt, with instanceId, testId, attemptIndex and the trace's name as artifactName.54ef38096042
currents-list-webhooksList all webhooks for a project. Webhooks allow you to receive HTTP POST notifications when certain events occur in your test runs: RUN_FINISH (run completed), RUN_START (run started), RUN_TIMEOUT (run timed out), RUN_CANCELED (run was cancelled). Requires a projectId.a7c64759ff68
currents-create-share-linkCreate 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. Target a run (run_id), a spec file (run_id + instance_id) or a test (instance_id + test_id), or a session recorded with currents-create-session (session_id alone, purpose "report" only). Returns url (markdown, for agents) and pageUrl (web page, for people). Create one only when asked to hand results to someone.5c8487d7dd7d
currents-create-webhookCreate a new webhook for a project. Specify the URL to receive POST notifications, optional custom headers (as JSON string), events to trigger on (RUN_FINISH, RUN_START, RUN_TIMEOUT, RUN_CANCELED), and an optional label. Requires projectId and url. The payload Currents sends and how to verify it are documented at https://docs.currents.dev/resources/integrations/http-webhooks.b05c2a625342
currents-get-webhookGet a single webhook by ID. The hookId is a UUID. Returns full webhook details including url, headers, events, label, and timestamps.cdf624183677
currents-update-webhookUpdate an existing webhook. You can update the url, headers (as JSON string), hookEvents array, or label. All fields are optional. The hookId is a UUID. The payload Currents sends and how to verify it are documented at https://docs.currents.dev/resources/integrations/http-webhooks.e490bb664190
currents-delete-webhookDelete a webhook. This permanently removes the webhook. The hookId is a UUID.8cc02f114f8a
prompt:browser-evidenceExperimental: prove a change works in a browser you drove yourself, when there is no test to run. Use when asked to "reproduce this", "show the bug", "prove the fix", "record a session", "capture before and after", or to demonstrate a change on a ticket that has no automated test. Reproduce a bug, fix it, record each state as a Currents session, and post before/after evidence on a pull request or issue with a link that reads without a Currents login. For evidence from tests that already run in CI, use collect-evidence instead.77deee5e0219
prompt:collect-evidenceShow that work you implemented actually works, or demo it, from tests that ran in CI via Currents — a trace link whose digest, filmstrip and accessibility snapshots read inside a comment, plus screenshots, attachments and videos. Use when asked to "collect evidence", "prove it works", "show me it works", "demo the feature", "capture a before/after", or to attach proof of a change to a PR, issue, ticket, or status update. Evidence comes from CI runs retrieved through the Currents MCP tools or REST API, not from a local run.d3696a6d38d9
prompt:fix-failing-testsFix tests that failed in CI, using the results Currents recorded — errors, steps, traces, screenshots and console output. Use when CI is red, a pull request check failed, a build broke, someone asks why a test failed, or you are given a Currents run or test link. Works from a developer's machine or from a CI job that runs after the tests failed.a520322d5272

Lock these tools

Pin what @currents/mcp serves you today, commit the lock, and a pull request fails when a tool changes, with the text before and after. Pin the package version in your MCP config as well.

$ pip install verfy
$ verfy lock check --update   # shows each tool, then writes verfy.lock
$ git add verfy.lock
# .github/workflows/verfy.yml, after actions/checkout
- uses: verfy-dev/verfy-action@v1

Maintain this server? Run the same check on your releases and add the Locked by Verfy badge to your README.