online.webarm24Published by webarm24.onlineOfficial publisherv1.0.0Updated Nov 3, 2026
AI automation platform (n8n/Zapier alternative): build, schedule and run workflows from your agent.
WebArm24's hosted MCP server (webarm24.online), published by webarm24.online; API key required; Streamable HTTP; 61 tools.
No AI overview yet: these facts come from the registry entry and the server itself.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/online.webarm24%2Fwebarm24/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"webarm24": {
"type": "http",
"url": "https://webarm24.online/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}Open a URL in your private server-side browser session. `browser_session_label` loads a saved login (see browser_session_put) when the session is first created. Costs 1 mcp_call.
urlrequiredsessionbrowser_session_labelScreenshot of the current page (JPEG). Costs 1 mcp_call.
sessionClick an element by visible text, label or CSS selector. Costs 1 mcp_call.
sessiondescriptionrequiredClick at pixel coordinates of the (resized) viewport. Costs 1 mcp_call.
xrequiredyrequiredsessionType a value into an input identified by label/placeholder/selector. Costs 1 mcp_call.
valuerequiredsessionfield_descriptionrequiredExtract text from a described area of the page. Costs 1 mcp_call.
sessionarea_descriptionrequiredScroll 'up' or 'down'. Costs 1 mcp_call.
amountsessiondirectionReturn the current page HTML. Costs 1 mcp_call.
sessionClose your browser session (free). Idle sessions are closed after 30 minutes.
sessionSend an email through the server SMTP (subject to server allowlists/limits). Costs 1 mcp_call.
torequiredbodyrequiredis_htmlsubjectrequiredInspect large JSON: mode summary|schema|value|preview, optional dotted path. Costs 1 mcp_call.
modepathjson_textrequiredList your pipelines.
Takes no parameters.
Get one pipeline incl. steps, schedule and inbound trigger URL.
pipeline_idrequiredCreate a pipeline. See resource webarm://docs/pipeline-steps for the step schema. `extra` may carry webhook_url, webhook_secret, webhook_structured_data_only, inbound_trigger_only.
namerequiredextrastepsrequiredrun_atenabledcron_exprtask_variablesPatch a pipeline. `fields` may contain any of: name, enabled, cron_expr, run_at (null clears), steps, task_variables, webhook_url, webhook_secret, clear_webhook_secret, webhook_structured_data_only, inbound_trigger_only, regenerate_trigger_token. `steps` replaces the whole step list.
fieldsrequiredpipeline_idrequiredDelete a pipeline and its schedule (restorable later via pipeline_deleted_restore).
pipeline_idrequiredChange history of a pipeline, newest first: [{id, seq, action (create|update|delete|restore), source (manual|assistant|mcp|api), source_detail, changed_fields, created_at, updated_at}]. Consecutive manual UI edits within a few minutes are merged into one revision. Page with `before_seq`.
limitbefore_seqpipeline_idrequiredOne revision: {revision, snapshot (full pipeline state after that change), diff (vs previous revision)}.
pipeline_idrequiredrevision_idrequiredRestore a pipeline to the state of a revision (recorded as a new `restore` revision). Returns the pipeline.
pipeline_idrequiredrevision_idrequiredDeleted pipelines that can be restored: [{pipeline_id, name, steps_count, deleted_at, source}].
Takes no parameters.
Re-create a deleted pipeline from its last snapshot (same id, starts disabled, new inbound trigger URL).
pipeline_idrequiredList your sidebar pipeline groups, each with its pipeline_ids. Ungrouped pipelines are in no group.
Takes no parameters.
Create a sidebar group, optionally moving the given pipelines into it.
namerequiredpipeline_idsRename a group and/or set whether it is collapsed in the sidebar.
namegroup_idrequiredcollapsedDelete a group. Its pipelines are kept, just ungrouped.
group_idrequiredMove a pipeline into a group; omit group_id (or pass null) to remove it from its group.
group_idpipeline_idrequiredRun a single step in isolation. `previous_outputs[i]` feeds {{step_{i+1}_output}}.
steprequiredprevious_outputspipeline_variablesStart a run (async; returns run_id). Costs the usual pipeline_run credits. Follow with pipeline_run_wait or pipeline_run_get.
variablesskip_stepspipeline_idrequiredinitial_step_outputsRun status (running|cancelling|ok|error|cancelled), current_step_index, per-step results, answer_preview.
run_idrequiredpipeline_idrequiredBlock until the run finishes or timeout_sec (max 600) elapses; returns the latest run state (check `status` — still 'running' means timed out).
run_idrequiredpipeline_idrequiredtimeout_secRecent runs of a pipeline (max 50).
limitpipeline_idrequiredRequest cancellation of an active run (takes effect between steps).
run_idrequiredpipeline_idrequiredAsk the built-in AI pipeline builder (costs builder_call credits). `messages`=[{role,content}], `pipeline`=current draft. Returns {text, pipeline}; the draft is NOT saved — pass it to pipeline_create/update.
messagesrequiredpipelinerequiredbuilder_contextAsk the AI to analyse a finished run (costs builder_call credits).
run_idrequiredquestionrequiredpipeline_idrequiredRun the browsing agent on a task (async; costs agent_job credits). Jobs are in-memory (lost on restart).
langtextrequiredvariablestarget_urloutput_json_schemaJob status/result (queued|running|completed|failed).
job_idrequiredstructured_data_onlyRecent agent jobs.
limitList automations (single-task schedules).
Takes no parameters.
Automation details plus recent runs.
schedule_idrequiredCreate an automation. `schedule` follows ScheduleCreate: mode (agent|replay), task_text, target_url, webhook_url, cron_expr, run_at, lang, output_json_schema, task_variables, ...
schedulerequiredPatch an automation (ScheduleUpdate fields).
fieldsrequiredschedule_idrequiredDelete an automation.
schedule_idrequiredRun an automation now (synchronous; costs schedule_run credits).
variablesschedule_idrequiredExport an automation as portable JSON.
schedule_idrequiredImport an exported automation.
documentrequiredList your JSON/text stores.
Takes no parameters.
Read a store.
namerequiredWrite a store (mode 'auto' keeps JSON, 'text' stores a string).
modenamerequiredvaluerequiredDelete a store.
namerequiredList stored files.
prefixUpload a file (base64 content). Size caps: USER_FILES_FILE_MAX_BYTES / per-user total.
namerequiredcontent_base64requiredDownload a file as base64 (limited to 8 MiB of base64).
namerequiredDelete a stored file.
namerequiredList saved logins (Playwright storageState slots).
Takes no parameters.
Get a saved storageState.
labelrequiredSave a Playwright storageState (stored encrypted).
labelrequiredstorage_staterequiredDelete a saved login.
labelrequiredYour account incl. credit balance.
Takes no parameters.
Balance and last 100 ledger entries.
Takes no parameters.
Purchasable credit packs.
Takes no parameters.
Create a Stripe Checkout URL for a pack; a human must open it to pay.
credits_amountrequired83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.