MCP SERVER · AGENT-FIRST · FREE FOR INDIVIDUALS

The monitor your agents set up for themselves.

LastPing's MCP server lets an AI agent create its own dead-man's-switch monitor in a single conversation — calling create_monitor and get_ping_instructions to wire in the check-in pings on the spot. Nothing to install. Hosted at mcp.lastping.dev (Streamable HTTP). Works with Claude, Cursor, and Windsurf.

Get started free Connect your client

Connect your client — copy and paste

The server speaks Model Context Protocol over Streamable HTTP. Add a URL and a Bearer token — nothing else to install. Get an API key at app.lastping.dev → Settings → API Keys.

Claude Desktop

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/):

{ "mcpServers": { "lastping": { "url": "https://mcp.lastping.dev", "headers": { "Authorization": "Bearer lp_your_key" } } } }
Claude Code CLI

One command — adds LastPing to your user-scope MCP config:

claude mcp add \ --transport http \ --scope user \ lastping \ https://mcp.lastping.dev \ --header "Authorization: Bearer lp_…"
Cursor

Add to ~/.cursor/mcp.json (user-scope) or .cursor/mcp.json (project-scope):

{ "mcpServers": { "lastping": { "url": "https://mcp.lastping.dev", "headers": { "Authorization": "Bearer lp_your_key" } } } }
Windsurf

Add to ~/.codeium/windsurf/mcp_config.json (note: Windsurf uses serverUrl):

{ "mcpServers": { "lastping": { "serverUrl": "https://mcp.lastping.dev", "headers": { "Authorization": "Bearer lp_your_key" } } } }

One conversation. The agent instruments itself.

The MCP server closes the loop: the agent doesn't just read monitoring data, it creates the monitor and wires in the pings. Three tool calls. No dashboard. No human in the loop.

Create the monitor

Call create_monitor with a name, a stable slug (makes re-runs idempotent — upsert, not duplicate), and a schedule. Heartbeat monitors expect a ping every N seconds or on a cron; CI monitors track pipeline runs; HTTP monitors probe a URL.

create_monitor({ "name": "nightly-summary-agent", "slug": "nightly-summary-agent", "schedule_kind": "cron", "cron_expr": "0 2 * * *", "grace_s": 1800 }) → created · ping_url: https://ping.lastping.dev/<id>

Get ping snippets

Call get_ping_instructions with the monitor's UUID. The tool returns the ping URL plus ready-to-run curl_success, curl_start, and curl_fail commands — no URL construction, no format guessing. This is the tool that makes one-conversation self-instrumentation possible.

get_ping_instructions({ "id": "<monitor-uuid>" }) → { "curl_success": "curl -fsS -m 10 --retry 3 -o /dev/null https://ping.lastping.dev/<id>", "curl_start": "curl -fsS -m 10 --retry 3 -o /dev/null https://ping.lastping.dev/<id>/start", "curl_fail": "curl -fsS -m 10 --retry 3 -o /dev/null https://ping.lastping.dev/<id>/fail" }

Wire pings into the work

The agent adds the success ping to the end of its workflow, the fail ping on any error path, and the start ping at launch to arm overrun detection. From that point on — crash, hang, or a scheduled run that silently stops firing — LastPing opens an incident and alerts the operator. No human check-in required.

# In the agent's wrapper script or tool call: curl -fsS .../<id>/start # arms overrun + never-finished detection # ... do the work ... curl -fsS .../<id> # success — closes any open incident # on error path: curl -fsS .../<id>/fail # opens incident immediately with failure detail

14 tools — the full MCP surface

Every tool is implemented in github.com/tp322d/lastping-app and ships in both the hosted server and the self-host stdio binary.

  • Monitors create_monitor — create or upsert a monitor by slug (heartbeat · ci · http); upsert-by-slug makes it idempotent and safe for agents to retry list_monitors — list all monitors in the project with id, name, slug, status, and ping_url get_monitor — get a single monitor's full config by UUID update_monitor — update an existing monitor's schedule and config by UUID delete_monitor — permanently delete a monitor (cannot be undone) pause_monitor — pause alerting; the monitor still receives pings but does not open incidents resume_monitor — resume a paused monitor; alerting resumes on the next missed ping snooze_monitor — set or clear a maintenance window (by duration e.g. "1h", RFC 3339 timestamp, or clear=true)
  • Incidents list_incidents — list recent incidents for a monitor, newest first; an open incident has closed_at=null; includes the failure detail captured by the CI/CD integration or a /fail ping
  • Destinations list_destinations — list all notification destinations in the project (email, webhook, Slack, Discord, Telegram, ntfy, Pushover, Teams, Google Chat) create_destination — create a notification destination; non-email kinds are ready immediately; email sends a confirmation link before it can be routed test_destination — deliver a synthetic test alert through a destination to verify credentials before routing
  • Routing set_route — route a monitor's down / recovery / fail alerts to a set of destinations; replaces the full set for that event type; empty list clears routing
  • Self-instrumentation get_ping_instructions — the flagship tool: returns the monitor's ping URL plus ready-to-run curl_success, curl_start, and curl_fail snippets. Call this right after create_monitor. The agent creates a monitor and immediately receives the check-in code to embed in its own workflow — one conversation, zero dashboards.

Ping API (plain HTTP, no SDK needed): GET /<id> (success) · /<id>/start (arms overrun detection) · /<id>/fail (POST error body, up to 64 KB, stored on the incident) · /<id>/<exit-code> (0 = success, non-zero = fail) · ?rid=<run-id> (pair start with its later success/fail, record duration). All pings hit https://ping.lastping.dev/.

Prompt cookbook — ask your agent

These prompts work out of the box once LastPing MCP is connected. Paste as-is or adapt for your stack.

"Monitor my nightly Postgres backup and alert me on Telegram if it doesn't check in by 3am."

uses: create_monitor · create_destination · test_destination · set_route · get_ping_instructions

"Add a LastPing dead-man's-switch to the deploy pipeline you just wrote — daily at midnight, 30-minute grace."

uses: create_monitor · get_ping_instructions

"Create a monitor for this nightly summary agent — runs at 2am UTC, alert me on Slack if it goes silent or fails."

uses: create_monitor · create_destination · test_destination · set_route · get_ping_instructions

"Check all my monitors. Which ones have had incidents in the past week?"

uses: list_monitors · list_incidents

"Snooze the nightly-backup monitor for 4 hours while I run a maintenance window."

uses: list_monitors · snooze_monitor

"Set up a LastPing HTTP uptime monitor for api.example.com, probing every 60 seconds."

uses: create_monitor

"Create a webhook destination for my on-call endpoint and route the production-deploy monitor's down and fail events to it."

uses: list_monitors · create_destination · test_destination · set_route

"Instrument yourself: register a heartbeat for this agent at '0 6 * * *' (6am daily, 45-minute grace), get the ping snippets, and add them to your run loop."

uses: create_monitor · get_ping_instructions

Prefer to self-host? Use the stdio binary.

The same 14 tools are available as a single Go binary — no npm, no runtime, no Docker required. MIT-licensed and open source at github.com/tp322d/lastping-app.

Install

# requires Go 1.22+ go install github.com/tp322d/lastping-app/cmd/lastping-mcp@latest

Add to your client config (stdio)

Replace the url + headers block with command + env in your claude_desktop_config.json or .mcp.json:

{ "mcpServers": { "lastping": { "command": "lastping-mcp", "env": { "LASTPING_API_KEY": "lp_your_key_here" } } } }

Optional env vars: LASTPING_BASE_URL (default: https://app.lastping.dev) and LASTPING_PING_HOST (default: https://ping.lastping.dev) — useful when running a self-hosted LastPing instance.

Questions

Front-loaded answers — the most important fact first.

  • What is the LastPing MCP server?

    A hosted Model Context Protocol endpoint at https://mcp.lastping.dev (Streamable HTTP). Point your AI client at it with a Bearer API key and the agent gains 14 tools for creating monitors, querying incidents, managing alert destinations, configuring routing, and — the flagship — instrumenting its own dead-man's-switch check-in loop. Nothing to install; get a key at app.lastping.dev.

  • How is this different from other monitoring MCP servers?

    Competitors (Hyperping, Checkly, Sentry, Cronitor) ship MCP servers for reading and triaging existing monitors created by humans. LastPing is designed for agent-created monitoring: the agent calls create_monitor to register its own heartbeat, then get_ping_instructions to receive ready-to-run curl_success / curl_start / curl_fail snippets — and wires them into its own workflow. The agent owns the monitor it set up. No dashboard visit required.

  • Which AI clients are supported?

    Any client supporting Streamable HTTP MCP: Claude Desktop, Claude Code (claude mcp add --transport http …), Cursor, and Windsurf. For stdio (local process), any client supporting stdio-based MCP — configure with command + env instead of url + headers using the go install binary described in the self-host section above.

  • Does the agent need an SDK or library to send pings?

    No. The MCP server is for creating and managing monitors. Once a monitor exists, pinging it is a plain HTTP GET to https://ping.lastping.dev/<uuid>. The get_ping_instructions tool returns ready-to-run curl commands the agent can embed in any shell script, tool call, or workflow step. No SDK, no import, no language dependency — one HTTP request is all that is needed.

  • Is the LastPing MCP server free?

    Yes. LastPing is free for individuals — no monitor cap, no feature gate. The hosted MCP server at mcp.lastping.dev is included. The open-source stdio binary is MIT-licensed. Get an API key at app.lastping.dev → Settings → API Keys.

MCP SERVER · AGENT-FIRST · FREE FOR INDIVIDUALS

Let your agent set up its own monitor.

Get a free API key, paste one config block, and your agent gains 14 tools for creating and managing dead-man's-switch monitors — no dashboard, no human in the loop.

Get your API key — free Source on GitHub Agent overview