Playrunner
Discover Playwright workflows, start runs, and inspect results in Playrunner Cloud.
Connector by playrunner.dev · Domain verified by the MCP Registry
Install
Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install connector/playrunner-dev-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Remote endpoint
https://playrunner.cloud/mcpRemote (HTTP)
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 11 read · 3 write · 1 delete
- Secrets
- None asked for
- Install scripts
- Nothing to install (hosted)
- Runs as
- Hosted (remote endpoint)
Tools by what they do 15
Read from the source code; the running server may list different tools.
Read 11 · Look things up without changing anything.
get_authoring_guideget_release_policyget_release_verdictget_run_eventsget_run_feedbackget_run_statuslist_projectslist_runslist_server_toolslist_serverslist_workflows
Write 3 · Create, change, send or run things.
run_workflowsave_workflowselect_server
Delete 1 · Delete, drop, revoke or wipe things.
call_server_tool
Network hosts it talks to 32
accounts.google.com· found in codeagent-plugins.org· found in codeapi.atlassian.com· found in codeapi.github.com· found in codeapi.openai.com· found in codeapi.resend.com· found in codeapple.com· found in codeartifactregistry.googleapis.com· found in codeauth.atlassian.com· found in codecloudresourcemanager.googleapis.com· found in codecloudscheduler.googleapis.com· found in codeconceptai.dev· found in codeexample.test· found in codegithub.com· found in codegoogleapis.com· found in codegraph.microsoft.com· found in codehooks.slack.com· found in codehooks.slack.test· found in codehost.docker.internal· found in codehuggingface.co· found in codeiam.googleapis.com· found in codeiamcredentials.googleapis.com· found in codelogin.microsoftonline.com· found in codeoauth2.googleapis.com· found in codeplatform.openai.com· found in codeplayrunner.cloud· found in remote endpoint, install command, codeplayrunner.dev· found in codeplaywright.dev· found in codepubsub.googleapis.com· found in coderun.googleapis.com· found in code
Show 2 more hosts
serviceusage.googleapis.com· found in codeslack.com· found in code
Files it touches
/dev/null/home/playrunner- Your home directory (~)
Tools (15)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
call_server_toolcan change or delete dataCall a discovered tool on the explicitly named self-hosted server. May create, modify, delete or run workflows; obtain authorization appropriate to the underlying tool. Never retry an ambiguous mutation automatically. Cloud uses native playrunner tools.
get_authoring_guideGet workflow authoring guideread-onlyRead the saved Playwright regression mapping, immutable run request and feedback contract before authoring change-aware test workflows.
get_release_policyGet release policyread-onlyRead a saved workflow's release requirements and policyVersion. The saved test plan must map RELEASE_IDENTITY to exactly one node and contain at least one other requirement. The successful identity node must emit output.releaseCandidate observed from the target, never copied from the request. Release checks support Environment, Playwright, JavaScript and Webhook nodes. Repository test sources require a full commit SHA in branch; mutable workspaces and AI generation are unsupported. The policy pins the test plan, nodes, connections, linked environment values and secret revisions. A protected re…
get_release_verdictGet release verdictread-onlyEvaluate execution evidence against the expected candidate and pinned policyVersion. Only status PASS with allowed true for that exact candidate and policy permits release. FAIL or BLOCKED forbids release; completed run status alone is insufficient. Call again immediately before release to check evidence freshness and policy changes. This reads evidence and does not start a run or deploy anything.
get_run_eventsGet run eventsRead sanitized execution events after a cursor. Use event IDs as the next after value.
get_run_feedbackGet run feedbackread-onlyRead compact progress, selected journeys, final failures and authenticated report paths for an existing execution. Never starts another run. Pass nextCursor as after; drain while hasMore. Truncated or incomplete evidence is not a passing result. A failing head run alone is not a confirmed regression against baseline.
get_run_statusGet run statusRead the current status of one run. Cheap enough to poll, but leave a few seconds between calls.
list_projectsList projectsList owned projects. Requires an unrestricted workflow:write key.
list_runsList recent runsList recent runs of one workflow, newest first. Use this to answer questions like whether last night’s run passed.
list_server_toolsread-onlyRead available tool schemas from a configured self-hosted Playrunner server before calling them. Use native playrunner tools for Cloud.
list_serversread-onlyList configured Playrunner servers. Reloads configuration immediately; never returns tokens. Cloud uses the plugin native OAuth tools.
list_workflowsList workflowsList the saved Playrunner workflows this token is allowed to run. Call this before run_workflow: an agent cannot run a workflow whose id it does not know.
run_workflowRun a workflowStart a saved Playrunner workflow. For release verification, pass release with the exact candidate and pinned policyVersion, then call get_release_verdict. Completion alone never allows a release. Returns an execution id immediately without waiting for the run to finish. Runs consume the account quota, so do not retry a call that already returned an execution id.
save_workflowSave a workflowRead get_authoring_guide before configuring regression mappings. After the first save call open_workflow_editor, then save incremental node additions to show progress. Create or update a workflow using a machine API definition with project and workflow keys, nodes, connections, cloudProvider, optional concurrency and testPlan. Requires unrestricted workflow:write. Keep secrets in environment references.
select_serverSelect a configured server as an advisory preference for this router process. Returns routing information, not proof of authentication. The process may be shared by chats; every remote call must still include serverId.
Compare and alternatives
Featured in
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 17
- Last commit
- Oct 24, 2026 (4 days ago)
- Last release
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
dev.playrunner/mcp- Version
- 0.1.1
- Auth
- Auth not stated
- License
- License unknown
- Repository
- github.com/playrunner/playrunner
- Website
- playrunner.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Playrunner MCP server. Agent Mart. https://agentmart.dev/connectors/playrunner-dev-mcp (last updated 2026-10-24)