WebArm24 MCP server

• Registry nameonline.webarm24/webarm24verified in the MCP registry

The registry name sits under webarm24.online. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-11-02
• Tools61
• Server calls itselfwebarm24
• Protocol version2025-06-18

On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 470 ms.

• Its tools do every use case we checked: draft a multi-step pipeline from a plain-language description; run and inspect pipelines from a coding agent via MCP.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer494 ms
• Space in an agent's context≈ 5,236 tokensthe definitions of all its tools (61), which an agent carries on every turn
• Tool definitionsC · 68 of 100
• Typed results0 of 61 toolsdeclared outputSchema: results come typed, read once

• No description an agent can choose by: 4 of 61
• Parameters without a type: in 1 of 61
• Parameters without a description: in 52 of 61
• Not saying whether it only reads or can destroy: 61 of 61

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• browser_navigate

  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.

• browser_screenshot

  Screenshot of the current page (JPEG). Costs 1 mcp_call.

• browser_click

  Click an element by visible text, label or CSS selector. Costs 1 mcp_call.

• browser_click_at

  Click at pixel coordinates of the (resized) viewport. Costs 1 mcp_call.

• browser_fill

  Type a value into an input identified by label/placeholder/selector. Costs 1 mcp_call.

• browser_extract_text

  Extract text from a described area of the page. Costs 1 mcp_call.

• browser_scroll

  Scroll 'up' or 'down'. Costs 1 mcp_call.

• browser_get_html

  Return the current page HTML. Costs 1 mcp_call.

• browser_close_session

  Close your browser session (free). Idle sessions are closed after 30 minutes.

• send_email

  Send an email through the server SMTP (subject to server allowlists/limits). Costs 1 mcp_call.

• analyze_json

  Inspect large JSON: mode summary|schema|value|preview, optional dotted path. Costs 1 mcp_call.

• pipeline_list

  List your pipelines.

• pipeline_get

  Get one pipeline incl. steps, schedule and inbound trigger URL.

• pipeline_create

  Create 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.

• pipeline_update

  Patch 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…

• pipeline_delete

  Delete a pipeline and its schedule (restorable later via pipeline_deleted_restore).

• pipeline_history_list

  Change 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…

• pipeline_history_get

  One revision: {revision, snapshot (full pipeline state after that change), diff (vs previous revision)}.

• pipeline_history_restore

  Restore a pipeline to the state of a revision (recorded as a new `restore` revision). Returns the pipeline.

• pipeline_deleted_list

  Deleted pipelines that can be restored: [{pipeline_id, name, steps_count, deleted_at, source}].

• pipeline_deleted_restore

  Re-create a deleted pipeline from its last snapshot (same id, starts disabled, new inbound trigger URL).

• pipeline_group_list

  List your sidebar pipeline groups, each with its pipeline_ids. Ungrouped pipelines are in no group.

• pipeline_group_create

  Create a sidebar group, optionally moving the given pipelines into it.

• pipeline_group_update

  Rename a group and/or set whether it is collapsed in the sidebar.

• pipeline_group_delete

  Delete a group. Its pipelines are kept, just ungrouped.

• pipeline_group_assign

  Move a pipeline into a group; omit group_id (or pass null) to remove it from its group.

• pipeline_test_step

  Run a single step in isolation. `previous_outputs[i]` feeds {{step_{i+1}_output}}.

• pipeline_run

  Start a run (async; returns run_id). Costs the usual pipeline_run credits. Follow with pipeline_run_wait or pipeline_run_get.

• pipeline_run_get

  Run status (running|cancelling|ok|error|cancelled), current_step_index, per-step results, answer_preview.

• pipeline_run_wait

  Block until the run finishes or timeout_sec (max 600) elapses; returns the latest run state (check `status` — still 'running' means timed out).

• pipeline_runs_list

  Recent runs of a pipeline (max 50).

• pipeline_run_cancel

  Request cancellation of an active run (takes effect between steps).

• pipeline_builder_chat

  Ask 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.

• pipeline_debug_chat

  Ask the AI to analyse a finished run (costs builder_call credits).

• agent_job_submit

  Run the browsing agent on a task (async; costs agent_job credits). Jobs are in-memory (lost on restart).

• agent_job_get

  Job status/result (queued|running|completed|failed).

• agent_job_list

  Recent agent jobs.

• schedule_list

  List automations (single-task schedules).

• schedule_get

  Automation details plus recent runs.

• schedule_create

  Create an automation. `schedule` follows ScheduleCreate: mode (agent|replay), task_text, target_url, webhook_url, cron_expr, run_at, lang, output_json_schema, task_variables, ...

• schedule_update

  Patch an automation (ScheduleUpdate fields).

• schedule_delete

  Delete an automation.

• schedule_run

  Run an automation now (synchronous; costs schedule_run credits).

• schedule_export

  Export an automation as portable JSON.

• schedule_import

  Import an exported automation.

• storage_list

  List your JSON/text stores.

• storage_read

  Read a store.

• storage_write

  Write a store (mode 'auto' keeps JSON, 'text' stores a string).

• storage_delete

  Delete a store.

• storage_files_list

  List stored files.

• storage_file_put

  Upload a file (base64 content). Size caps: USER_FILES_FILE_MAX_BYTES / per-user total.

• storage_file_get

  Download a file as base64 (limited to 8 MiB of base64).

• storage_file_delete

  Delete a stored file.

• browser_session_list

  List saved logins (Playwright storageState slots).

• browser_session_get

  Get a saved storageState.

• browser_session_put

  Save a Playwright storageState (stored encrypted).

• browser_session_delete

  Delete a saved login.

• account_me

  Your account incl. credit balance.

• credits_history

  Balance and last 100 ledger entries.

• credit_packs

  Purchasable credit packs.

The first 60 of 61, as the server listed them.