Skip to main content
Glama

WebRun Browser Automation

Server Details

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

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 23 tools

Disambiguation4/5

The tools target mostly distinct resources and actions, and descriptions explicitly clarify high-risk overlaps such as browser_task vs create_session vs trigger_workflow. A few boundaries remain close, especially one-off browser_task versus persistent create_session/send_task flows, but the set is generally distinguishable.

Naming Consistency4/5

Most names follow a readable snake_case verb_noun pattern: list_workflows, create_agent, pause_session_task, update_work_list. There are minor deviations such as browser_task, screenshot, and guardrail_response, but they are understandable and not chaotic.

Tool Count3/5

The 23 tools cover several subdomains—sessions, tasks, workflows, agents, work lists, environments—so the size is plausible, but it is on the heavy side. The set is broad enough that users must navigate many related operations.

Completeness3/5

Core lifecycles are partially covered: sessions can be created/listed/terminated, workflows created/listed/read/updated/triggered, and agents listed/created/paused/resumed. However, notable gaps exist, including no delete_workflow, no update_agent or delete_agent, and limited agent detail retrieval.

Available Tools

23 tools
browser_taskRun browser taskA
Destructive
Inspect

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.

Inputs: prompt (required), files, model, proxy, +11 more. Returns: Task outcome envelope: a completion (success/type/data), a pending marker (poll…

create_agentCreate scheduled agentAInspect

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 bakes your variables into the prompt; results and memory stay centralised on the workflow. STANDALONE MODE: omit workflowId and provide name, prompt (a Goal / Ground rules / Stages / Output browsing runbook — see the prompt field description), and a schedule; the connection's environment is used automatically. Ask the user only what it should do and when it should run, in plain language — pick sensible defaults for everything else and state them; never ask about environments or technical settings. Results are delivered to your connected chat and appear in session history.

Inputs: schedule (required), name, proxy, memory, +8 more. Returns: mode, name, notes, agentId, +5 more

create_sessionCreate browser sessionA
Destructive
Inspect

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 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.

Inputs: mode, task, model, proxy, +5 more. Returns: taskId, message, sessionId, streaming, +1 more

create_workflowCreate workflowAInspect

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 INTERVIEW in the server instructions), then create. Requires title and promptTemplate — write the prompt as a browsing runbook following the Goal / Ground rules / Stages / Output contract in the promptTemplate field description. For tasks that must handle each new item exactly once (new messages, forward once, skip seen), memoryContract is REQUIRED — three plain-English fields addressed to the agent: groundRules, memoryInstruction and itemIdentity (see the field descriptions); the platform wires the tracking itself — never write memory or tracking steps into the prompt. Created in the connection's environment automatically — omit environmentId and never ask the user to choose one. Write the user's concrete values (names, URLs, numbers) directly into the prompt; use {{variables}} ONLY when the user explicitly wants a reusable template with per-run inputs. Everything else is optional and defaults sensibly — do not quiz the user about settings. A supplied schedule is stored as a setting only — the workflow does not run on a timer until deployed via create_agent. To run or TEST the workflow, use trigger_workflow ONLY — never browser_task or create_session.

Inputs: title (required), promptTemplate (required), flow, model, +34 more. Returns: slug, notes, title, success, +4 more

get_task_statusGet task statusA
Read-onlyIdempotent
Inspect

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.

Inputs: taskId (required), sessionId (required). Returns: data, type, status, taskId, +3 more

get_workflowGet workflow detailsA
Read-onlyIdempotent
Inspect

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, any pending logins, and a summary of its work list when it keeps one (for a typed list: its bands, counts and newest or watched items — page it with get_work_list). Identify by workflowId or exact title. Read-only; proxy credentials are masked.

Inputs: title, workflowId. Returns: slug, notes, title, trigger, +9 more

get_work_listGet work listA
Read-onlyIdempotent
Inspect

Page through the work list a workflow keeps between runs. Each item comes with its band: on a watch list failing, unreadable, changed_today or watching; on a collect list needs_approval, new_today, handled or seen. Identify the workflow by workflowId or exact title; filter by band or a search query; pass nextCursor back as cursor for the next page. Read-only.

Inputs: band, limit, query, title, +2 more. Returns: view, items, total, typed, +2 more

guardrail_responseAnswer guardrail promptA
Destructive
Inspect

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.

Inputs: sessionId (required), askId, files, newState, +2 more. Returns: taskId, message, success, sessionId

list_agentsList scheduled agentsA
Read-onlyIdempotent
Inspect

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.

Inputs: scope. Returns: count, scope, agents

list_environmentsList environmentsA
Read-onlyIdempotent
Inspect

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 should not ask the user to choose an environment.

Inputs: no named parameters. Returns: hint, count, environments, boundEnvironment

list_sessionsList sessionsA
Read-onlyIdempotent
Inspect

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

Inputs: no named parameters. Returns: count, sessions

list_workflowsList workflowsA
Read-onlyIdempotent
Inspect

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.

Inputs: scope. Returns: count, scope, workflows

pause_agentPause scheduled agentA
Destructive
Inspect

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

Inputs: agentId (required). Returns: name, status, agentId, message, +1 more

pause_session_taskPause session taskA
DestructiveIdempotent
Inspect

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

Inputs: sessionId (required). Returns: action, message, success, sessionId

resume_agentResume scheduled agentA
Destructive
Inspect

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).

Inputs: agentId (required). Returns: name, status, agentId, message, +2 more

resume_session_taskResume session taskA
DestructiveIdempotent
Inspect

Resume a previously paused task in a browser session.

Inputs: sessionId (required). Returns: action, message, success, sessionId

screenshotTake screenshotA
Read-onlyIdempotent
Inspect

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

Inputs: sessionId (required). Returns: Capture confirmation — the screenshot itself is returned as inline image conten…

send_taskSend task to sessionA
Destructive
Inspect

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.

Inputs: prompt (required), sessionId (required), files, secrets, +8 more. Returns: Task outcome envelope: a completion (success/type/data), a pending marker (poll…

stop_session_taskStop session taskA
DestructiveIdempotent
Inspect

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

Inputs: sessionId (required). Returns: action, message, success, sessionId

terminate_sessionTerminate sessionA
DestructiveIdempotent
Inspect

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

Inputs: sessionId (required). Returns: action, message, success, sessionId

trigger_workflowTrigger workflowA
Destructive
Inspect

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 workflow, this is the tool they mean. Drives a real Chrome browser: the run may navigate, fill forms, and submit data on third-party websites as the workflow's prompt requires. Pass values for the workflow's {{variables}} in variables (stored variableValues defaults fill any gaps). Returns a sessionId — poll get_task_status for the result.

Inputs: force, title, variables, workflowId. Returns: taskId, message, success, sessionId, +3 more

update_workflowUpdate workflowA
DestructiveIdempotent
Inspect

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 saved setting — scheduled agents already deployed from this workflow keep their own timing. promptTemplate follows the same Goal / Ground rules / Stages / Output runbook contract as create_workflow (see that field's description). memoryContract is the exception to whole-replace: supplying its three fields updates them while platform tracking details are preserved. On a workflow that keeps a typed list: an outputSchema change needs workList keep or empty (ask the user); listType and queue mode can't change; a different result type goes through resultType, previewed first and applied once the user confirms.

Inputs: workflowId (required), flow, model, proxy, +39 more. Returns: slug, notes, title, changes, +2 more

update_work_listUpdate work listA
Destructive
Inspect

Change the work list a workflow keeps between runs. op: add (items; on a watch list, new watched items), remove (items; on a watch list, stop watching them), mark_handled or unmark (items), skip_approval (drafts waiting for approval), clear (empty the list; keepHandled keeps handled items on a collect list; a watch list keeps its watched items and drops their readings). Confirm with the user before remove or clear. Refused while a run of this workflow is in progress. To change what the list records, use update_workflow.

Inputs: op (required), items, title, workflowId, +1 more. Returns: op, items, notes, changed, +2 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Give your AI agents a real Chrome on your own Linux server. Connect through MCP or REST, watch live, take over for login and 2FA, then hand control back. Keep encrypted saved sessions, upload files and receive downloads. Open source under AGPL-3.0, with no usage fees; you provide the server.
      106
      AGPL 3.0
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables clients to drive a real Chrome browser through structured snapshots and actions, including opening pages, clicking, typing, taking screenshots, and inspecting network and console activity while preserving login state in an isolated profile.
      178 npm
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources