ai.webrun/webrun

MCPCommunitylive
v1.0.2ai.webrunUnknownAktualisiert vor 1 Mon.

Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.

Endpunkt-Statuslive
geprüft vor 12 Std. · 171 ms
100 % der letzten 4 Prüfungen haben diesen Endpunkt erreicht
Läuft in
ClaudeCursorCopilotChatGPTGemini

Abgeleitet aus den Transporten, die dieser Eintrag deklariert (streamable-http). Ein Client, der hier nicht steht, ist damit nicht ausgeschlossen — Forge kann ihn nur nicht bestätigen.

Automatisch aus öffentlichen Quellen indexiert. Vom Entwickler auf Forge noch nicht verifiziert.Diesen Eintrag beanspruchen →
vor 1 Mon.Letzte Aktualisierung
Paket
Autorai.webrun
LizenzUnknown
Version1.0.2
Quellemcp-registry
Trust-Status
D
30/100Risiko
Im Forge-Index gelistet+10/10
Publisher-Identität verifiziert+0/30
Publisher: für diesen Eintrag ist kein Repository hinterlegt, daher kann `forge publish` die Inhaberschaft nicht automatisch prüfen. Nutze oben „Diesen Eintrag beanspruchen“ — Forge prüft diese Fälle von Hand.
Domain-Verifizierung+0/10
Für diesen Eintragstyp derzeit nicht verfügbar — die Domain-Prüfung läuft heute nur für npm-gestützte Pakete, diese Zeile lässt sich hier also noch nicht erreichen, unabhängig davon, was auf der Domain liegt.
Prompt-Injection-Scan · Befunde+0/30
Publisher: entferne aus dem Quellcode Anweisungen, die sich an KI-Clients statt an menschliche Leser richten
Obfuskations-/Exfiltrations-Scan · sauber+20/20
StatusVon der Community indexiert
PublisherNicht verifiziert
SignaturNicht signiert
Domain
Herkunft
AbhängigkeitenNicht auditiert
Tool-Oberfläche21 Tools · keines privilegiert
Sicherheits-Scan⚠ Warnungen (3)vlive · heuteWie gut funktioniert dieser Scan?
PROMPTtool:browser_task#filesExfiltration-shaped instruction
PROMPTtool:send_task#filesExfiltration-shaped instruction
PROMPTtool:guardrail_response#filesExfiltration-shaped instruction
EvaluierungenKeine
Indexiert11. Aug. 2026

Die Verifizierung bestätigt die Identität des Publishers (die Inhaberschaft am Repo), nicht die Sicherheit des Codes. Der Sicherheits-Scan deckt bekannte CVEs und verdächtige Installationsskripte ab.

Tools

21 Tools · keines privilegiert · 3 wegen Injektion markiert
Live am Endpunkt des Anbieters beobachtet12h ago

Aus einem echten MCP-Handshake initialize → tools/list gegen den deklarierten Endpunkt gelesen. Es wurde nie ein Tool aufgerufen — tools/list ist der lesende Introspektionsaufruf, den das Protokoll dafür vorsieht. Es spiegelt wider, was der Server in diesem Moment angeboten hat; ein gehosteter Endpunkt ist an keine Version gebunden und kann sich ohne Ankündigung ändern.

  • https://api.webrun.ai/mcp21 Tools · 171 ms
browser_taskInjektionsrisikoExecute a browser automation task in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai). Creates a session, runs the task, and auto-terminates. Best for simple one-off tasks that no saved workflow covers. May navigate, fill forms, and submit data on third-party websites as…

Execute a browser automation task in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai). Creates a session, runs the task, and auto-terminates. Best for simple one-off tasks that no saved workflow covers. May navigate, fill forms, and submit data on third-party websites as…

INJEKTIONIm Parameter files: Exfiltration-shaped instructionDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /en…
ParameterTypBeschreibung
prompt*stringTask description in natural language
startingUrlstringOptional starting URL
maxDurationnumberMax duration in minutes (default: 20, max: 60)
outputTypestringResponse format (default: text)
outputSchemaobjectJSON Schema for structured output (required if outputType is structured_json)
webhookobjectWebhook configuration for task completion notification
secretsarrayDomain-matched secrets [{match, fields}] passed to instance (not stored)
environmentIdstringEnvironment ID for persistent profile session. Use list_environments to find available IDs. Without this, a disposable instance is used.
policyIdstringPolicy ID to apply automation guardrails (domain restrictions, capability controls, LLM role). Optional.
debugCbooleanEnable debug mode on the instance (default: false)
filesarrayOptional file IDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /environments/:id/files). M…
proxyobjectProxy configuration. WebRun-managed: { source: "WebRun", country: "GB" }. Custom: { source: "custom", type: "http"|"socks", host, port, username?, password? }.…
reach_out_modestringControls proactive chat-platform messages (Telegram/WhatsApp/Slack/Discord/Teams) to bot users on the same environment. Default: "off" — no messages are sent u…
modelstringOptional model name or profile key (from global config). Falls back to the configured default.
timezonestringIANA timezone name for the session, e.g. "America/New_York", "Europe/London", "Asia/Tokyo". Date/time-sensitive instructions (e.g. "tomorrow morning", "today",…
create_sessionCreate a persistent session in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai), for multi-step interactive work. Returns a sessionId for subsequent commands. With an initial task the browser may act on third-party websites immediately. Do NOT use this to run or test a s…

Create a persistent session in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai), for multi-step interactive work. Returns a sessionId for subsequent commands. With an initial task the browser may act on third-party websites immediately. Do NOT use this to run or test a s…

ParameterTypBeschreibung
modestringSession mode (default: default)
taskobjectInitial task configuration
environmentIdstringEnvironment ID for persistent profile session. Use list_environments to find available IDs. Without this, a disposable instance is used.
policyIdstringPolicy ID to apply automation guardrails (domain restrictions, capability controls, LLM role). Optional.
debugCbooleanEnable debug mode on the instance (default: false)
proxyobjectProxy configuration. WebRun-managed: { source: "WebRun", country: "GB" }. Custom: { source: "custom", type: "http"|"socks", host, port, username?, password? }.…
reach_out_modestringControls proactive chat-platform messages (Telegram/WhatsApp/Slack/Discord/Teams) to bot users on the same environment. Default: "off" — no messages are sent u…
modelstringOptional model name or profile key (from global config). Falls back to the configured default.
timezonestringIANA timezone name for the session, e.g. "America/New_York", "Europe/London", "Asia/Tokyo". Date/time-sensitive instructions (e.g. "tomorrow morning", "today",…
send_taskInjektionsrisikoSend a new task to an existing browser session (from create_session). The real Chrome browser may navigate, fill forms, and submit data on third-party websites as the task requires.

Send a new task to an existing browser session (from create_session). The real Chrome browser may navigate, fill forms, and submit data on third-party websites as the task requires.

INJEKTIONIm Parameter files: Exfiltration-shaped instructionDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /en…
ParameterTypBeschreibung
sessionId*stringSession ID from create_session
prompt*stringTask description
startingUrlstringURL to navigate to before starting this task (optional)
maxDurationnumberMax duration for this task in minutes (3-60). Defaults to the value the session was created with.
maxInputTokensnumberMax input tokens for this task (100-3000000). Defaults to the value the session was created with.
maxOutputTokensnumberMax output tokens for this task (100-1000000). Defaults to the value the session was created with.
terminateOnCompletionbooleanAuto-terminate after task (default: false)
outputTypestringResponse format
outputSchemaobjectJSON Schema for structured output (required if outputType is structured_json)
webhookobjectWebhook configuration
secretsarrayDomain-matched secrets [{match, fields}] (not stored)
filesarrayOptional file IDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /environments/:id/files). M…
pause_session_taskPause the task currently running in a browser session. Resume it later with resume_session_task.

Pause the task currently running in a browser session. Resume it later with resume_session_task.

ParameterTypBeschreibung
sessionId*stringSession ID
resume_session_taskResume a previously paused task in a browser session.

Resume a previously paused task in a browser session.

ParameterTypBeschreibung
sessionId*stringSession ID
stop_session_taskCancel the task currently running in a browser session, keeping the session alive for new tasks.

Cancel the task currently running in a browser session, keeping the session alive for new tasks.

ParameterTypBeschreibung
sessionId*stringSession ID
terminate_sessionEnd a browser session and free its resources. The session and any running task cannot be resumed afterwards.

End a browser session and free its resources. The session and any running task cannot be resumed afterwards.

ParameterTypBeschreibung
sessionId*stringSession ID
guardrail_responseInjektionsrisikoRespond to a guardrail trigger when the browser agent needs human input (credentials, clarification, approval). The response is handed to the live agent, which continues acting on it.

Respond to a guardrail trigger when the browser agent needs human input (credentials, clarification, approval). The response is handed to the live agent, which continues acting on it.

INJEKTIONIm Parameter files: Exfiltration-shaped instructionDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /en…
ParameterTypBeschreibung
sessionId*stringSession ID
responsestringYour response/instructions to the agent. Required when newState is 'resume'.
newStatestringHow to continue: 'resume' (default) provides the requested input and continues the task; 'deny' declines the request (response text optional).
filesarrayOptional file IDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /environments/:id/files). M…
get_task_statusCheck the status of a task previously started in a browser session. Use to poll for completion or detect guardrails. Read-only: reports on the task without affecting it.

Check the status of a task previously started in a browser session. Use to poll for completion or detect guardrails. Read-only: reports on the task without affecting it.

ParameterTypBeschreibung
sessionId*stringSession ID
taskId*stringTask ID to check
screenshotCapture a screenshot of the current browser page in an active session. Returns the screenshot as an inline image. Read-only.

Capture a screenshot of the current browser page in an active session. Returns the screenshot as an inline image. Read-only.

ParameterTypBeschreibung
sessionId*stringSession ID
list_sessionsList all active browser sessions for this account. Read-only.

List all active browser sessions for this account. Read-only.

Für dieses Tool wurde kein Eingabeschema veröffentlicht.

list_environmentsList available browser environments (persistent profiles) for this account. Returns environment IDs needed for persistent sessions in browser_task or create_session. Read-only. NOTE: workflows and agents use the connection's environment automatically — you rarely need this tool for those, and shoul…

List available browser environments (persistent profiles) for this account. Returns environment IDs needed for persistent sessions in browser_task or create_session. Read-only. NOTE: workflows and agents use the connection's environment automatically — you rarely need this tool for those, and shoul…

Für dieses Tool wurde kein Eingabeschema veröffentlicht.

list_workflowsList the user's saved workflows (prompt-templated browser automations, docs.webrun.ai). Shows each workflow's title, schedule, {{variables}}, and run stats. Scoped to the bound environment when this connection has one; pass scope "all" for every environment. Read-only.

List the user's saved workflows (prompt-templated browser automations, docs.webrun.ai). Shows each workflow's title, schedule, {{variables}}, and run stats. Scoped to the bound environment when this connection has one; pass scope "all" for every environment. Read-only.

ParameterTypBeschreibung
scopestring'environment' (default when this connection is bound to one) lists workflows deployed to the bound environment; 'all' lists every workflow on the account.
get_workflowFull detail of one workflow: prompt template, {{variables}} and their defaults, trigger + schedule, run settings (starting URL, timezone, model, proxy, output contract, files), memory state, and any pending logins. Identify by workflowId or exact title. Read-only; proxy credentials are masked.

Full detail of one workflow: prompt template, {{variables}} and their defaults, trigger + schedule, run settings (starting URL, timezone, model, proxy, output contract, files), memory state, and any pending logins. Identify by workflowId or exact title. Read-only; proxy credentials are masked.

ParameterTypBeschreibung
workflowIdstring24-hex workflow id (from list_workflows or create_workflow)
titlestringExact workflow title (case-insensitive) — alternative to workflowId
create_workflowCreate a new saved workflow. READINESS BAR: if you could not execute the prompt yourself as a human in a browser — which site, which records, which fields, delivered where, matched to each recipient how — it is not ready; first collect the missing business facts from the user (see the TASK INTERVIE…

Create a new saved workflow. READINESS BAR: if you could not execute the prompt yourself as a human in a browser — which site, which records, which fields, delivered where, matched to each recipient how — it is not ready; first collect the missing business facts from the user (see the TASK INTERVIE…

ParameterTypBeschreibung
title*stringWorkflow title (shown on the dashboard).
promptTemplate*stringThe task the browser agent runs, written as a BROWSING RUNBOOK. Structure it as: `Goal:` — one sentence naming the outcome. `Ground rules (every stage, every t…
shortDescriptionstringOne-line summary shown in workflow lists.
triggerPhrasestringNatural-language phrase that invokes this workflow in chat.
useCaseTagsarrayCategorisation tags.
departmentstringFree-text department label (e.g. "inventory").
triggerobjectHow the workflow is meant to be invoked (informational — see notes). Defaults to {type:'manual', source:'manual'}.
scheduleobjectSaved schedule setting. NOTE: record-only — the workflow does NOT run on a timer until deployed as a scheduled agent (dashboard or Telegram bot).
startingUrlstringPage Chrome opens at the start of each run. Omit to let the prompt decide.
timezonestringIANA timezone for runs of this workflow (e.g. "America/New_York"). Leave unset to follow the proxy country.
modelstringModel profile key. Omit for the account default.
proxyobjectProxy for runs. {source:"WebRun", country?} or {source:"custom", type:"http"|"socks", host, port, username?, password?}. Custom passwords are encrypted at rest…
outputTypestringOutput contract: 'text' (default), 'structured' (JSON matching outputSchema), 'structured_csv' (rows for the outputSchema column names).
outputSchemaobject | arrayJSON Schema object (outputType "structured") or array of column-name strings (outputType "structured_csv").
requiredFilesarrayPer-run file attachments. Each row may name its own environmentId; ownership is enforced per-file at dispatch.
deployedPolicyIdstringPolicy id to run under (must be owned by you).
reachOutModestring | nullProactive-chat policy for runs: 'off', 'guardrail_only', or 'full'. Omit (or pass null) to inherit the account default (MCP-initiated runs treat inherit as 'of…
memoryEnabledbooleanPersist per-workflow agent memory across runs (default true).
memorystringThe agent's private notebook: shown to it at the start of every run, updated automatically after each run. Seed it ONLY with durable facts the next run must al…
orchestrateFirstbooleanDiscovery mode: one run gathers the WHOLE work list up front, later runs claim one item each.
workListEnabledbooleanAdvanced — set automatically when memoryContract is supplied; leave unset.
listTypestringAdvanced — defaults automatically ('monitor' when memoryContract is supplied); leave unset.
policyOptedOutbooleanOpt this workflow out of the environment's default policy.
conciergeNotifystringWhere the concierge announces results (e.g. 'Telegram', 'Slack', 'WhatsApp', 'Microsoft Teams', 'concierge').
update_workflowUpdate an existing workflow. Supply workflowId plus only the fields to change: prompt, trigger, schedule, run settings, variables, presentation. Object and array fields are replaced whole; pass null to clear an optional field. Renaming via title keeps the slug stable. The stored schedule stays a sa…

Update an existing workflow. Supply workflowId plus only the fields to change: prompt, trigger, schedule, run settings, variables, presentation. Object and array fields are replaced whole; pass null to clear an optional field. Renaming via title keeps the slug stable. The stored schedule stays a sa…

ParameterTypBeschreibung
workflowId*string24-hex id of the workflow to update (from list_workflows or create_workflow). Required — the title property here is the NEW title for renames, never an identif…
environmentIdstringMove the workflow to a different environment you own.
titlestringWorkflow title (shown on the dashboard).
promptTemplatestringThe task the browser agent runs, written as a BROWSING RUNBOOK. Structure it as: `Goal:` — one sentence naming the outcome. `Ground rules (every stage, every t…
shortDescriptionstringOne-line summary shown in workflow lists.
triggerPhrasestringNatural-language phrase that invokes this workflow in chat.
useCaseTagsarrayCategorisation tags.
departmentstringFree-text department label (e.g. "inventory").
triggerobjectHow the workflow is meant to be invoked (informational — see notes). Defaults to {type:'manual', source:'manual'}.
scheduleobjectSaved schedule setting. NOTE: record-only — the workflow does NOT run on a timer until deployed as a scheduled agent (dashboard or Telegram bot).
startingUrlstringPage Chrome opens at the start of each run. Omit to let the prompt decide.
timezonestringIANA timezone for runs of this workflow (e.g. "America/New_York"). Leave unset to follow the proxy country.
modelstringModel profile key. Omit for the account default.
proxyobjectProxy for runs. {source:"WebRun", country?} or {source:"custom", type:"http"|"socks", host, port, username?, password?}. Custom passwords are encrypted at rest…
outputTypestringOutput contract: 'text' (default), 'structured' (JSON matching outputSchema), 'structured_csv' (rows for the outputSchema column names).
outputSchemaobject | arrayJSON Schema object (outputType "structured") or array of column-name strings (outputType "structured_csv").
requiredFilesarrayPer-run file attachments. Each row may name its own environmentId; ownership is enforced per-file at dispatch.
deployedPolicyIdstringPolicy id to run under (must be owned by you).
reachOutModestring | nullProactive-chat policy for runs: 'off', 'guardrail_only', or 'full'. Omit (or pass null) to inherit the account default (MCP-initiated runs treat inherit as 'of…
memoryEnabledbooleanPersist per-workflow agent memory across runs (default true).
memorystringThe agent's private notebook: shown to it at the start of every run, updated automatically after each run. Seed it ONLY with durable facts the next run must al…
orchestrateFirstbooleanDiscovery mode: one run gathers the WHOLE work list up front, later runs claim one item each.
workListEnabledbooleanAdvanced — set automatically when memoryContract is supplied; leave unset.
listTypestringAdvanced — defaults automatically ('monitor' when memoryContract is supplied); leave unset.
trigger_workflowRun a workflow now in its deployed environment. This is the ONLY correct way to run or TEST a saved workflow — a run started here carries the workflow's rules, tracking and memory; browser_task/create_session runs do not. When the user says "run it", "run it once", "test it" or "try it" about a wor…

Run a workflow now in its deployed environment. This is the ONLY correct way to run or TEST a saved workflow — a run started here carries the workflow's rules, tracking and memory; browser_task/create_session runs do not. When the user says "run it", "run it once", "test it" or "try it" about a wor…

ParameterTypBeschreibung
workflowIdstring24-hex workflow id
titlestringExact workflow title (case-insensitive) — alternative to workflowId
variablesobjectValues for the workflow's {{variables}}, keyed by exact variable name. Merged over the workflow's stored variableValues defaults.
forcebooleanWork-list workflows only: when the list reports complete, re-open it for a fresh full pass.
create_agentCreate a scheduled agent — a recurring or one-time automation that runs on a timer in a real Chrome browser. Two modes. WORKFLOW MODE: pass workflowId plus a schedule — the platform copies everything else (prompt, starting URL, output contract, model, proxy, policy, files) from the workflow and bak…

Create a scheduled agent — a recurring or one-time automation that runs on a timer in a real Chrome browser. Two modes. WORKFLOW MODE: pass workflowId plus a schedule — the platform copies everything else (prompt, starting URL, output contract, model, proxy, policy, files) from the workflow and bak…

ParameterTypBeschreibung
workflowIdstringWORKFLOW MODE: 24-hex id of the workflow to deploy (from list_workflows). The prompt, starting URL, output contract, model, proxy, policy, and files are all co…
schedule*objectWhen the agent fires. Required.
expiresAtstringISO 8601 date-time after which the agent auto-pauses (recurring schedules).
namestringAgent name. Required standalone; defaults to the workflow title in workflow mode.
variablesobjectWORKFLOW MODE, and only when the workflow's prompt actually contains {{variables}}: values for them, BAKED IN at deploy and reused every run (stored variableVa…
promptstringSTANDALONE MODE (required there): The task the browser agent runs, written as a BROWSING RUNBOOK. Structure it as: `Goal:` — one sentence naming the outcome. `…
startingUrlstringSTANDALONE MODE: page Chrome opens at the start of each run.
proxyobjectSTANDALONE MODE (workflow mode inherits the workflow proxy instead): Proxy for runs. {source:"WebRun", country?} or {source:"custom", type:"http"|"socks", host…
outputTypestringSTANDALONE MODE: output contract (same rules as create_workflow).
outputSchemaobject | arraySTANDALONE MODE: JSON Schema object (structured) or column-name array (structured_csv).
memorystringSTANDALONE MODE: the agent's private notebook, shown to it every run and updated automatically after each run. Seed ONLY durable facts the next run must know (…
environmentIdstringSTANDALONE MODE, rarely needed — OMIT it: the connection-bound environment (or your only one) is applied automatically; never ask the user to choose. Workflow…
list_agentsList the account's scheduled agents (cron deployments): schedule, status, next/last run, and whether each is standalone or deployed from a workflow. Scoped to the bound environment when this connection has one; pass scope "all" for every environment. Read-only.

List the account's scheduled agents (cron deployments): schedule, status, next/last run, and whether each is standalone or deployed from a workflow. Scoped to the bound environment when this connection has one; pass scope "all" for every environment. Read-only.

ParameterTypBeschreibung
scopestring'environment' (default when bound) lists agents in the bound environment; 'all' lists every agent on the account.
pause_agentPause an active scheduled agent — it stops firing until resumed. Get agentId from list_agents.

Pause an active scheduled agent — it stops firing until resumed. Get agentId from list_agents.

ParameterTypBeschreibung
agentId*string24-hex agent id (from list_agents or create_agent)
resume_agentResume a paused scheduled agent — recomputes its next run and reactivates it. A completed work-list agent restarts with a fresh full pass. Refuses if the agent's expiry has passed (extend it on the dashboard first).

Resume a paused scheduled agent — recomputes its next run and reactivates it. A completed work-list agent restarts with a fresh full pass. Refuses if the agent's expiry has passed (extend it on the dashboard first).

ParameterTypBeschreibung
agentId*string24-hex agent id (from list_agents)

21 von 21 Tools haben eine Beschreibung veröffentlicht.

Tool-Namen und -Beschreibungen stammen vom Publisher und werden wortgetreu als inerter Text angezeigt. Es sind die Zeichenketten, die ein MCP-Client an ein Modell übergibt, deshalb prüft Forge sie auf Prompt-Injection-Muster — jeder Befund erscheint oben beim Sicherheits-Scan. „Privilegiert“ ist ein Schlagwort-Treffer im Tool-Namen, keine Prüfung dessen, was das Tool tut: ein harmlos klingender Name kann trotzdem alles tun.

Über

Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.

Schlagwörter
mcp
Alternativen
Tool-Oberflächen werden verglichen…

Keine Abdeckung der Abhängigkeiten

Dieser Eintrag veröffentlicht kein npm-Paket, daher hat Forge keinen Abhängigkeitsbaum dafür. Das ist eine Lücke in der Abdeckung — keine Aussage, dass er keine Abhängigkeiten hat.

Themen

Verwandtes in browser automation & scraping