Skip to main content
Glama

WebRun Browser Automation

by ai.webrun

Run browser task

browser_task
Destructive

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 the task requires. Do NOT use this to run or test a saved workflow — use trigger_workflow instead: only a workflow run carries the workflow's own rules, tracking and memory, so a session run will behave differently. If the user says "run it", "run it once", "test it" or "try it" about a workflow, that means trigger_workflow, not this tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesNoOptional 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). Max 5 files.
modelNoOptional model name or profile key (from global config). Falls back to the configured default.
proxyNoProxy configuration. WebRun-managed: { source: "WebRun", country: "GB" }. Custom: { source: "custom", type: "http"|"socks", host, port, username?, password? }. Omit for no proxy. Social/messaging automation (WhatsApp, Telegram, Instagram, Facebook, X, LinkedIn, TikTok): prefer country = the country the user is in right now — recommend it and confirm the country with them first; a mismatch is the usual cause of refused logins and sessions that log out repeatedly.
debugCNoEnable debug mode on the instance (default: false)
promptYesTask description in natural language
secretsNoDomain-matched secrets [{match, fields}] passed to instance (not stored)
webhookNoWebhook configuration for task completion notification
policyIdNoPolicy ID to apply automation guardrails (domain restrictions, capability controls, LLM role). Optional.
timezoneNoIANA timezone name for the session, e.g. "America/New_York", "Europe/London", "Asia/Tokyo". Date/time-sensitive instructions (e.g. "tomorrow morning", "today", "in 2 hours") are interpreted in this timezone. Defaults to "UTC" when omitted.
outputTypeNoResponse format (default: text)
maxDurationNoMax duration in minutes (default: 20, max: 60)
startingUrlNoOptional starting URL
outputSchemaNoJSON Schema for structured output (required if outputType is structured_json)
environmentIdNoEnvironment ID for persistent profile session. Use list_environments to find available IDs. Without this, a disposable instance is used.
reach_out_modeNoControls proactive chat-platform messages (Telegram/WhatsApp/Slack/Discord/Teams) to bot users on the same environment. Default: "off" — no messages are sent unless this is set explicitly. "guardrail_only" forwards guardrail prompts (CAPTCHA/2FA/verification) to chat when the API caller is offline. "full" also forwards the task result on completion. Each bot user additionally filters by their own reachOutMode preference.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoTask output payload (instance-authored shape)
typeNoResult type, e.g. 'task_completed', 'task_failed', 'guardrail_trigger'
errorNo
statusNoPresent on guardrail results: 'awaiting_input'
taskIdNo
messageNo
pendingNoTrue when the task is still running — poll get_task_status
successNo
sessionIdNo
environmentNo
liveViewURLNoPage for watching the run live, present while it is still running or awaiting input. The only URL here that is safe to show a user or open in a browser.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / files / description
      Previous value: -"Optional file IDs to attach (from /files/upload). Max 5 files."New value: +"Optional 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). Max 5 files."
  2. Changed1 schema field changed
    • changedInput schema / properties / proxy / description
      Previous value: -"Proxy configuration. WebRun-managed: { source: \"WebRun\", country: \"GB\" }. Custom: { source: \"custom\", type: \"http\"|\"socks\", host, port, username?, password? }. Omit for no proxy."New value: +"Proxy configuration. WebRun-managed: { source: \"WebRun\", country: \"GB\" }. Custom: { source: \"custom\", type: \"http\"|\"socks\", host, port, username?, password? }. Omit for no proxy. Social/messaging automation (WhatsApp, Telegram, Instagram, Facebook, X, LinkedIn, TikTok): prefer country = the country the user is in right now — recommend it and confirm the country with them first; a mismatch is the usual cause of refused logins and sessions that log out repeatedly."
  3. Changed1 schema field changed
    • addedOutput schema / properties / liveViewURL
      Added value: +{
+  "description": "Page for watching the run live, present while it is still running or awaiting input. The only URL here that is safe to show a user or open in a browser.",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • changedInput schema / properties / maxDuration / description
      Previous value: -"Max duration in minutes (default: 5)"New value: +"Max duration in minutes (default: 20, max: 60)"
  5. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Task outcome envelope: a completion (success/type/data), a pending marker (poll get_task_status), or an awaiting_input guardrail. `data` is the task output; its shape is task-defined (freeform text or the caller-supplied structured schema).",
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "description": "Task output payload (instance-authored shape)",
+      "type": "object"
+    },
+    "environment": {
+      "properties": {
+        "environmentId": {
+          "type": "string"
+        },
+        "name": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "type": "object"
+    },
+    "error": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "pending": {
+      "description": "True when the task is still running — poll get_task_status",
+      "type": "boolean"
+    },
+    "sessionId": {
+      "type": "string"
+    },
+    "status": {
+      "description": "Present on guardrail results: 'awaiting_input'",
+      "type": "string"
+    },
+    "success": {
+      "type": "boolean"
+    },
+    "taskId": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "type": {
+      "description": "Result type, e.g. 'task_completed', 'task_failed', 'guardrail_trigger'",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=true, and the description reinforces those by disclosing the tool 'may navigate, fill forms, and submit data on third-party websites.' It adds value beyond the annotations by describing the session lifecycle (creates and auto-terminates) and warning that a session run 'will behave differently' from a workflow run. No contradiction; the only gap is no clarification of behavior when environmentId supplies a persistent profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description runs about 100 words — longer than the minimum, but each sentence earns its place: environment, lifecycle, best-use scope, exclusion with sibling, and literal phrase disambiguation. The core purpose is front-loaded. The phrase-examples section is slightly verbose but delivers genuine agent-routing value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter tool with nested objects, an output schema, and 19 siblings, the description handles the critical dimensions: tool-selection routing (browser_task vs trigger_workflow), side-effect profile, and lifecycle. Remaining details (proxy, webhook, secrets, environmentId) are thoroughly documented in the schema itself, so their absence from the description is acceptable. The persistent-profile behavior via environmentId is not mentioned, but the schema covers it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and several parameter descriptions (proxy, timezone, reach_out_mode, outputSchema) are already rich and self-explanatory, so the description carries no parameter burden. The description adds no parameter-level detail beyond the schema, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Execute a browser automation task in a real Chrome browser') plus the hosting environment (WebRun cloud). The lifecycle summary ('Creates a session, runs the task, and auto-terminates') and the explicit contrast with trigger_workflow distinguish this tool from its closest sibling without needing to inspect the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Scopes usage explicitly to 'simple one-off tasks that no saved workflow covers' and gives a hard exclusion with a named alternative: 'Do NOT use this to run or test a saved workflow — use trigger_workflow instead.' It even supplies literal user phrases ('run it once', 'test it', 'try it') that should route to the sibling, giving an agent unambiguous decision rules.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All WebRun Browser Automation toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Most tools target a distinct resource and action, and the descriptions strongly separate the main overlapping workflow: browser_task, create_session, send_task, and trigger_workflow are all clearly scoped. A few pairs like pause_session_task/stop_session_task and browser_task/send_task could still be confused on name alone, but the explicit usage guidance makes misselection unlikely.

Naming Consistency4/5

The dominant pattern is verb_noun (create_workflow, list_sessions, pause_agent, trigger_workflow), which is consistent and predictable. Exceptions such as browser_task, guardrail_response, and screenshot break the pattern, but they are few and do not obscure the intended resource.

Tool Count3/5

With 21 tools the surface feels heavy for a single server, even though the broad domain of workflows, agents, sessions, tasks, and environments largely justifies the count. Each tool has a purpose, but the set is at the upper edge of what is comfortably scoped.

Completeness3/5

Session and task lifecycle coverage is strong, and workflows support create, read, update, list, and trigger. However, there is no delete for workflows or agents and no update for agents, leaving notable lifecycle gaps for managing these resources.

Resources