# Ned Watch > Wake me when my agent misses its heartbeat. Deadman, overrun, HTTP, TLS, content; US+EU nodes. - name: watch.ned/ned-watch - version: 1.2.0 - connection class: R0 (autonomous) - trust: 81/100 flags: no-repository - quality: 73/100 (needs work) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/watch.ned%2Fned-watch - tools: https://api.protogrid.dev/v1/servers/watch.ned%2Fned-watch/tools **An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe. ## Connection (mcpServers) ```json { "mcpServers": { "ned-watch": { "type": "http", "url": "https://api.ned.watch/mcp", "headers": { "Authorization": "Bearer ${NED_WATCH_TOKEN}" } } } } ``` Placeholders to fill: `${NED_WATCH_TOKEN}`. ## Trust - hygiene: 80 - liveness: 96 - freshness: 100 - provenance: 55 - drivers: +dns-namespace +website +reachable +uptime-91% +updated-19d-ago -no-repository - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 73/100 (needs work) ### protocol: 75 (weight 25) - warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28 - n/a `protocol.stateless`: only applies to 2026-07-28 servers - pass `protocol.transport`: streamable HTTP - n/a `protocol.list_ttl`: only applies to 2026-07-28 servers ### authorization: n/a (weight 15) - n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth - n/a `auth.secret_in_url`: no templated URL ### tool hygiene: 71 (weight 30) - pass `tools.descriptions`: every tool has a description - pass `tools.description_length`: descriptions are concise - pass `tools.schemas`: every tool has an object input schema - fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones - fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: overrun_finish (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); watch_cancel (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); deadman_checkin (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); … - pass `tools.token_cost`: about 1,849 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: 75 (weight 15) - warn `stability.changes`: 10 tool changes in 30 days - pass `stability.rug_pull`: no tool changed its meaning under the same name ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package - tools: 12, about 1,849 tokens to load them all - tool set hash: 334456c0a381ec26a5c32b606b50bd20 - tools last changed: 2026-10-07T08:50:38.153Z - badge: [![protogrid quality](https://protogrid.dev/badge/watch.ned/ned-watch.svg)](https://protogrid.dev/servers/watch.ned/ned-watch) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-10-07 `watch_register` changed (description, inputSchema) - before: Register a watch. type: deadman | http | tls (for overrun and content use overrun_watch / content_watch). target: URL (http/tls); omit for deadman. interval_s >= 300 on the free tier. condition: e.g. {"grace_s": 600} for deadman, {"max_ms": 2000} for http latency, {"warn_days": 14} for tls. Ned POSTs a signed test callback to callback_url within 60s, then fires on change. No agent key yet? Call this without one: the response includes agent_key (shown once). Store it and pass it as NED_AGENT_KEY next time. - after: Register a watch. type: deadman | http | tls (for overrun and content use overrun_watch / content_watch). notify: up to 3 Discord/Slack/Teams webhook URLs told on fire, clear and change, so a human hears even if the agent behind callback_url is the thing that died. Your callback should outlive your agent. target: URL (http/tls); omit for deadman. interval_s >= 300 on the free tier. condition: e.g. {"grace_s": 600} for deadman, {"max_ms": 2000} for http latency, {"warn_days": 14} for tls. Ned POSTs a signed test callback to callback_url within 60s, then fires on change. No agent key yet? Call this without one: the response includes agent_key (shown once). Store it and pass it as NED_AGENT_KEY next time. - 2026-10-07 `is_up` added - Ask before you call. No key needed. Returns the state of everything Ned watches publicly on a host (and its subdomains) from two continents: up, degraded (answered, but their own status page reports an incident), down, reachable (answers 401, handshake measured only) or unknown (not on The Watch). Also since when, the last change seen (tool list, version, auth) and how soon to ask again. Try api.openai.com, api.anthropic.com, mcp.context7.com, status.github.com. If unknown, the answer says how to add it (first five watches free). - 2026-10-05 `overrun_finish` changed (description, inputSchema) - before: The run ended. Returns runtime_s and late. If Ned already fired for this run, your callback gets 'clear' with late: true. Finishing with no run open is an error (409). - after: The run ended. Returns runtime_s and late. If Ned already fired for this run, your callback gets 'clear' with late: true. Finishing with no run open is an error (409). failed=true says the run crashed: Ned fires at once with your short error (up to 200 chars) and clears when a later run finishes ok. - 2026-10-05 `quickstart` changed (description, inputSchema) - before: The fastest way to be watched, in one call. Makes you an agent (if you have no key yet) and a deadman watch that expects a check-in every `every_minutes` (5 to 1440). Miss one and Ned POSTs a signed message to callback_url; check in again and he says it's clear. Returns agent_key (shown once), signing_secret, and the exact check-in line to run on your schedule. The first 5 watches are free. - after: The fastest way to be watched, in one call. Makes you an agent (if you have no key yet) and a deadman watch that expects a check-in every `every_minutes` (5 to 1440). Miss one and Ned POSTs a signed message to callback_url; check in again and he says it's clear. Returns agent_key (shown once), signing_secret, and the exact check-in line to run on your schedule. The first 5 watches are free. arm=true starts the clock now instead of at your first check-in, so a job that never runs at all still wakes you. - 2026-09-30 `pricing` changed (description) - before: Ned Watch pricing: 5 free watches at >=300s, then per-day rates (http/tls 2c, fast 7c, deadman 1c) from a prepaid balance topped up over x402 (USDC on Base). Public, no key needed. Paying is done against POST /v1/topup/{5,20,50}, not here. - after: Ned Watch pricing: 5 free watches at >=300s, then per-day rates (http/tls/content 2c, fast 7c, deadman 1c, overrun 1c) from a prepaid balance topped up over x402 (USDC on Base). Public, no key needed. Paying is done against POST /v1/topup/{5,20,50}, not here. - 2026-09-30 `content_watch` added - Fire when a URL answers but says the wrong thing. expect has 1 to 5 conditions: status (int), contains / not_contains (a string or list of strings), json_path (dotted, e.g. "data.items.0.state") with equals (a JSON scalar) or exists (true/false). No regex. Pages over 256 KB fail as 'size'. The callback names the condition that failed, never the page's content. 2c/day at >= 60s, 7c at >= 30s; free within the first 5 at >= 300s. Example: expect={"status": 200, "json_path": "status", "equals": "ok"} - 2026-09-30 `overrun_finish` added - The run ended. Returns runtime_s and late. If Ned already fired for this run, your callback gets 'clear' with late: true. Finishing with no run open is an error (409). - 2026-09-30 `overrun_start` added - A run began on an overrun watch. Returns run_id and deadline. Sends the watch's signing_secret as Authorization: Bearer for this one call; no agent key needed. run_id is optional (your own id, 1-64 chars); pass one and a retried start is safe (it returns the open run instead of superseding it). - 2026-09-30 `overrun_watch` added - Fire when something is STILL running past its deadline (the other side of a deadman). Register once, then call overrun_start when a run begins and overrun_finish when it ends. If a run isn't finished within max_runtime_s (60 to 86400), Ned POSTs one signed 'fire' (run_id, started_at, deadline); a finish after that sends 'clear' with late: true and the runtime. A start while a run is open closes the old one as superseded (no callback). label: give each job its own watch (the same registration twice returns the same watch). 1c/day; counts toward the free 5. - 2026-09-30 `watch_register` changed (description) - before: Register a watch. type: http | tls | deadman. target: URL (http/tls); omit for deadman. interval_s >= 300 on the free tier. condition: e.g. {"warn_days": 14} for tls, {"grace_s": 600} for deadman, {"max_ms": 2000} for http latency. Ned POSTs a signed test callback to callback_url within 60s, then fires on change. No agent key yet? Call this without one: the response includes agent_key (shown once). Store it and pass it as NED_AGENT_KEY next time. - after: Register a watch. type: deadman | http | tls (for overrun and content use overrun_watch / content_watch). target: URL (http/tls); omit for deadman. interval_s >= 300 on the free tier. condition: e.g. {"grace_s": 600} for deadman, {"max_ms": 2000} for http latency, {"warn_days": 14} for tls. Ned POSTs a signed test callback to callback_url within 60s, then fires on change. No agent key yet? Call this without one: the response includes agent_key (shown once). Store it and pass it as NED_AGENT_KEY next time. Full history: https://api.protogrid.dev/v1/servers/watch.ned%2Fned-watch/changes ## Remotes - https://api.ned.watch/mcp (streamable-http, auth none, reachable true, uptime30d 0.9113924) ## Packages _none_ ## Tools (12) - `balance`: Your balance in cents, free allowance used, burn per day, days left, and the top-up routes. - `content_watch`: Fire when a URL answers but says the wrong thing. expect has 1 to 5 conditions: status (int), contains / not_contains (a string or list of strings), json_path (dotted, e.g. "data.items.0.state") with equals (a JSON scalar) or exists (true/false). No regex. Pages over 256 KB fail as 'size'. The callback names the condition that failed, never the page's content. 2c/day at >= 60s, 7c at >= 30s; free within the first 5 at >= 300s. Example: expect={"status": 200, "json_path": "status", "equals": "ok"} - `deadman_checkin`: Check in on a deadman watch to keep it from firing. Proves you hold the watch's signing_secret (returned at registration): it is sent as Authorization: Bearer for this one call. No agent key needed. - `is_up`: Ask before you call. No key needed. Returns the state of everything Ned watches publicly on a host (and its subdomains) from two continents: up, degraded (answered, but their own status page reports an incident), down, reachable (answers 401, handshake measured only) or unknown (not on The Watch). Also since when, the last change seen (tool list, version, auth) and how soon to ask again. Try api.openai.com, api.anthropic.com, mcp.context7.com, status.github.com. If unknown, the answer says how to add it (first five watches free). - `overrun_finish`: The run ended. Returns runtime_s and late. If Ned already fired for this run, your callback gets 'clear' with late: true. Finishing with no run open is an error (409). failed=true says the run crashed: Ned fires at once with your short error (up to 200 chars) and clears when a later run finishes ok. - `overrun_start`: A run began on an overrun watch. Returns run_id and deadline. Sends the watch's signing_secret as Authorization: Bearer for this one call; no agent key needed. run_id is optional (your own id, 1-64 chars); pass one and a retried start is safe (it returns the open run instead of superseding it). - `overrun_watch`: Fire when something is STILL running past its deadline (the other side of a deadman). Register once, then call overrun_start when a run begins and overrun_finish when it ends. If a run isn't finished within max_runtime_s (60 to 86400), Ned POSTs one signed 'fire' (run_id, started_at, deadline); a finish after that sends 'clear' with late: true and the runtime. A start while a run is open closes the old one as superseded (no callback). label: give each job its own watch (the same registration twice returns the same watch). 1c/day; counts toward the free 5. - `pricing`: Ned Watch pricing: 5 free watches at >=300s, then per-day rates (http/tls/content 2c, fast 7c, deadman 1c, overrun 1c) from a prepaid balance topped up over x402 (USDC on Base). Public, no key needed. Paying is done against POST /v1/topup/{5,20,50}, not here. - `quickstart`: The fastest way to be watched, in one call. Makes you an agent (if you have no key yet) and a deadman watch that expects a check-in every `every_minutes` (5 to 1440). Miss one and Ned POSTs a signed message to callback_url; check in again and he says it's clear. Returns agent_key (shown once), signing_secret, and the exact check-in line to run on your schedule. The first 5 watches are free. arm=true starts the clock now instead of at your first check-in, so a job that never runs at all still wakes you. - `watch_cancel`: Cancel a watch you registered. Frees a free-tier slot. - `watch_get`: Current state of one of your watches: status, fired, fire_count, next_check, last_state. - `watch_register`: Register a watch. type: deadman | http | tls (for overrun and content use overrun_watch / content_watch). notify: up to 3 Discord/Slack/Teams webhook URLs told on fire, clear and change, so a human hears even if the agent behind callback_url is the thing that died. Your callback should outlive your agent. target: URL (http/tls); omit for deadman. interval_s >= 300 on the free tier. condition: e.g. {"grace_s": 600} for deadman, {"max_ms": 2000} for http latency, {"warn_days": 14} for tls. Ned POSTs a signed test callback to callback_url within 60s, then fires on change. No agent key yet? Call this without one: the response includes agent_key (shown once). Store it and pass it as NED_AGENT_KEY next time.