Integration

Visualping integration

Visualping watches web pages for changes on a schedule and alerts when they change. Create, list, read, update and delete monitoring jobs (a URL checked every N minutes in visual, text or web mode), read a job's check history and its detected changes with AI summaries and diff links, and read the user's workspaces and credits. Checks consume the plan's credits, and detected changes send alerts to the job's notification channels (email, SMS, Slack, Teams, Discord, webhooks). Business accounts must pass workspaceId (from describe_user) on job calls. Running checks on demand, the workspace activity feed, labels, saved job settings (presets), bulk import, pre-check page actions and email/password tokens are not included. Authentication is an API key from the Developer page of the Visualping app, sent as a Bearer token.

Connect Visualping How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Visualping.Built from the 6 Visualping tools below, on the connection you add once.

What you can do with Visualping

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Job, 5 operations

create_jobCreate jobPOSTCreates a monitoring job that checks a URL every interval minutes and returns its jobid. Checks use the plan's credits, and detected changes send alerts to the job's notification channels.
delete_jobDelete jobDELETEPermanently deletes a monitoring job, which stops its checks. Returns whether anything changed and the ids of the deleted jobs.
get_jobGet jobGETReturns one job's settings (URL, mode, interval, threshold, crop, keywords, schedule, alert flags) with its check history and detected changes: percent difference, screenshot links, AI summary and HTML diff link.
list_jobsList jobsGETLists monitoring jobs a page at a time: id, URL, description, mode, active flag, check interval in minutes, labels and whether a check is running, with totals. Filters: state, mode, frequency, recent events, labels, text.
update_jobUpdate jobPUTChanges a job's settings: send only the fields to change (active false pauses it). Returns the impact of the change and the job's new estimated credit consumption per day, week and month.

Describe user, 1 operation

describe_userDescribe userGETReturns the connected Visualping user (id, email, country, locale, time zone), a business account's organisation (id, name, role, plan, credit renewal, counts) and the workspaces with id, role, plan, credits and job counts. Personal data.

Use Visualping from Claude Code, Cursor or Codex

Connect Visualping in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Visualping operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Visualping

Create your workspace
Sign up free. Nothing to install.
Connect Visualping once
Add your Visualping connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.