hookpulse MCP server
net.hookpulse/hookpulsehookpulse.netstreamable-httpv1.1.0Scanned
Know when a job stops or a site goes down after the agent exits. Free monitors; paid extra coverage.
29 tools: 4 can delete or cancel things, 1 do something that can't be undone, 13 change things and 11 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 3
- 10 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the hookpulse MCP server can do
The hookpulse MCP server is published by hookpulse.net, a domain the MCP Registry verified. It has 29 tools. It can delete or cancel things (4 tools: cancel_plan, delete_endpoint, ingest_key_rotate and status_feed_rotate), do things that cannot be undone, such as sending, paying or publishing (signal_slug) and create or change data (13 tools: buy_plan, api_index, create_guest, create_endpoint and 9 more). 11 tools only read.
6 tools bring in text other people can write (create_endpoint, create_site, check_site and 3 more); 3 tools can send data out of your system (create_site, signal_slug and get_api_x402_check).
The fixed checks matched 10 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
29 tools
Deletes or cancels 4Claude Code: deny
cancel_planCancel the active plan.1 finding
Why it is in this group
- The name "cancel_plan" says "cancel": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
The server marks "cancel_plan" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "cancel_plan" says "cancel": a word for removing or ending something.
Description, as the server wrote it Cancel the active plan. Nothing else is charged; a purchase under 7 days and a paid period that has not started are refunded and end now, and the rest of the paid period stays active until keeps_until. Requires accept_data_removal: true. Send `{ "accept_data_removal": true }`. The monthly card subscription stops. A purchase made less than 7 days ago and a paid period that has not started yet, such as a renewal, go back the same way they were paid (card or Pix) and end now. The rest of the paid period stays active until `keeps_until`; then what the plan added ends (`account.cancel.losses` in `GET /api/plans` says what). A purchase paid with USDC or with credit from another purchase stays active until its end; ask for its refund by e-mail, as the cancellation page says.
Annotations the server declares
- title: Cancel plan
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
delete_endpointRemoves the owner's endpoint.No findings
Why it is in this group
- The name "delete_endpoint" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Removes the owner's endpoint.
Annotations the server declares
- title: Delete endpoint
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
ingest_key_rotateRotates the ingest key; the previous one stops creating monitors.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Rotates the ingest key; the previous one stops creating monitors. Existing ones keep working. Monitors already created keep working — rotating only revokes the power to create new ones.
Annotations the server declares
- title: Ingest key rotate
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
status_feed_rotateRotates the status feed token; the previous URL stops working.Reads text others write1 finding
Why it is in this group
- The name "status_feed_rotate" says "status": a word for reading.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "status_feed_rotate" destructive (destructiveHint: true), and its name says "status", a word for reading.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":true,"idempotentHint":true,"openWorldHint":false}; The name "status_feed_rotate" says "status": a word for reading.
Description, as the server wrote it Rotates the status feed token; the previous URL stops working.
Annotations the server declares
- title: Status feed rotate
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 1Claude Code: ask
signal_slugSend start, fail or an exit code by name, with the ingest key; the first signal of a new name creates its monitor.Can send data out1 finding
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Findings
- Warn
The server marks "signal_slug" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it Send start, fail or an exit code by name, with the ingest key; the first signal of a new name creates its monitor. The same signals as `/in/:id/start`, `/in/:id/fail` and `/in/:id/:exit_code`, for a fleet that only knows the ingest key: the job sends its name, not the monitor id. The first signal of a new name creates the monitor, with the same rules and the same `cron`, `tz` and `grace_sec` as the plain ping by name.
Annotations the server declares
- title: Signal slug
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 13Claude Code: ask
api_indexFull index of the HookPulse API.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Full index of the HookPulse API.
Annotations the server declares
- title: API index
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
buy_planBuy a plan: starter (40 more monitors, up to 50), team (90 more monitors, up to 100), business (490 more monitors, up to 500).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Buy a plan: starter (40 more monitors, up to 50), team (90 more monitors, up to 100), business (490 more monitors, up to 500). Each purchase lasts 30 days, with no automatic renewal. Answers 402 with the price; pay with x402 or prepaid credit and repeat. Each purchase lasts 30 days, with no automatic renewal. Without payment, the answer is 402 with the price. Pay with prepaid credit (`X-Credito`) or x402 (`PAYMENT-SIGNATURE` v2 or `X-PAYMENT` v1). Without an account, the verified paying wallet owns the purchase. Use wallet agent authentication to read its plan, or claim it after account sign-in. The `compra` mark prevents repeat credit debits. An x402 nonce can settle only once; keep the receipt after a delivery error.
Annotations the server declares
- title: Buy plan
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
check_siteCheck a site monitor now.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check a site monitor now. One call every 10 seconds per destination host. One call every 10 seconds per destination host, for everyone: the button cannot hammer a site. The first state of a new site comes from here, without an alert — you are looking at it. After that, the state and the alerts come from the check that runs every minute.
Annotations the server declares
- title: Check site
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
contactWrite to the people behind the product: a question, or a sponsorship/partnership/advertising proposal.No findings
Why it is in this group
- The description's first verb is "write": a word for a change.
Description, as the server wrote it Write to the people behind the product: a question, or a sponsorship/partnership/advertising proposal. Free, no captcha and no payment; one message every 10 s per network (one that arrives sooner waits its turn). One route for a question and for a sponsorship, partnership or ad proposal (`tipo`, with the placements of `GET /api/partners`). No captcha, no account, no payment. One message every 10 seconds per network: one that arrives sooner waits its turn and then goes out — no error. The message reaches the team by e-mail, with `email` as the reply address. For voice, send multipart/form-data: `dados` is this JSON (up to 32 KiB), and `audio` is one WebM, Ogg or M4A audio file (up to 2 MB). Audio can replace message. The browser records up to two minutes. Audio is attached to the owner's e-mail.
Annotations the server declares
- title: Contact
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_endpointCreate a monitor for a routine.Reads text others writeNo findings
Why it is in this group
- The name "create_endpoint" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Create a monitor for a routine. Use cron, tz and grace_sec for a schedule, or interval_sec for a fixed check-in interval. Set max_duration_sec to detect an open run that exceeds its time limit. Without an owner token, creation returns guest_token; keep it private for later calls. Read billing before a paid option. A charged request returns HTTP 402. We keep the schedule, detect missing runs and send configured alerts. Your agent can stop after setting up the monitor. A check-in proves the signal arrived, not that a backup can be restored. Alert timing depends on the check cycle. A single paid probe does not create continuous monitoring.
Annotations the server declares
- title: Create endpoint
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_guestCreates a guest token hp_… Keep the token: without it there is no way back to the monitors, unless you have already tied them to an e-mail.No findings
Why it is in this group
- The name "create_guest" says "create": a word for a change.
Description, as the server wrote it Creates a guest token hp_… Keep the token: without it there is no way back to the monitors, unless you have already tied them to an e-mail.
Annotations the server declares
- title: Create guest
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_siteMonitor a website: HookPulse calls check.url every interval_sec (default 300) and alerts when it goes down and when it is back.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "create_site" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.check.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Monitor a website: HookPulse calls check.url every interval_sec (default 300) and alerts when it goes down and when it is back. Without an owner token, creation returns guest_token; keep it private. Read billing before a paid option. A charged request returns HTTP 402. We keep the schedule, detect missing runs and send configured alerts. Your agent can stop after setting up the monitor. A check-in proves the signal arrived, not that a backup can be restored. Alert timing depends on the check cycle. A single paid probe does not create continuous monitoring.
Annotations the server declares
- title: Create site
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
get_api_x402_checkChecks a URL once for an agent, paid per call: status, response time, keyword and TLS certificate, with no account and no monitor.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "get_api_x402_check" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "get_api_x402_check" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "get_api_x402_check" says "get": a word for reading.
Description, as the server wrote it Checks a URL once for an agent, paid per call: status, response time, keyword and TLS certificate, with no account and no monitor. One reading with the probe of the site monitors, and the certificate of an https address that answered. A request without payment gets the 402 with the price; a paid one gets the reading in the same response, with the payment in `cobranca`. A site that is down is the answer (`ok: false` with `reason`) and is charged: the call was made. When our own probe network fails, the answer is 503 and nothing is charged.
Annotations the server declares
- title: Get API X402 check
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
import_crontabReads a crontab and proposes one monitor per scheduled line.1 finding
Why it is in this group
- The name "import_crontab" says "import": a word for a change.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...schedule line was recognised.; 401: No credential, or an invalid one. See this endpoint's..."
Description, as the server wrote it Reads a crontab and proposes one monitor per scheduled line. Without apply=1 nothing is written; the proposal says what was ignored and why. Passwords in the command are redacted. The body is the crontab itself, as `text/plain`. Without `?apply=1` **nothing is written**: you get the proposal — what would become a monitor, what was ignored and why, and what still fits in the free tier. With `apply=1` it is all or nothing, under the same rules as `POST /api/endpoints`. Comments, variables and `@reboot` are ignored (there is no way to know when to expect a reboot); `@daily` and friends become the equivalent expression. The command becomes the monitor name, with passwords and tokens redacted first — the name travels in the alert e-mail, in the public dashboard and in the badge. Returns: { applied, recognized, ignored, existing, would_create, created?, free_tier } Example: crontab -l | curl -s -XPOST "$ORIGIN/api/import/crontab?apply=1" -H "X-Guest-Token: $HP" -H "content-type: text/plain" --data-binary @- Errors: 400: `crontab_sem_agenda` — no schedule line was recognised.; 401: No credential, or an invalid one. See this endpoint's auth.; 402: Payment required. The x402 terms (USDC on Base) come in the `PAYMENT-REQUIRED` header and in `accepts[]`: pay and repeat the same call with `PAYMENT-SIGNATURE` (x402 v2) or `X-PAYMENT` (v1). A standard x402 client such as `@x402/fetch` does this for you.
Annotations the server declares
- title: Import crontab
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
ping_slugCreate a monitor on its first check-in.1 finding
Why it is in this group
- The name "ping_slug" says "ping": a word for reading.
- The description's first verb is "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "ping_slug" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "ping_slug" says "ping": a word for reading.
Description, as the server wrote it Create a monitor on its first check-in. The same slug uses the same monitor. Service and billing limits apply. A rejected creation writes no monitor or event. The slug becomes the monitor name and its identity: the same slug always means the same monitor, so a retry never creates a second one. Normalised to lowercase, `[a-z0-9-]`, 40 chars. Creation happens **only inside the free tier** (or the trial); past it the ping is a 402 with `accepts[]` and nothing is written — not even the event. Works by GET or POST. Returns: { ok, endpoint_id, created } Example: curl -fsS "$ORIGIN/in/$INGEST_KEY/nightly-backup?cron=0%203%20*%20*%20*&tz=UTC&grace_sec=900" Errors: 400: `slug_invalido` — nothing usable left after normalising. With `cron`: `cron_invalido`, `tz_invalida`, `grace_invalido` or `cron_sem_ocorrencia`.; 402: The free tier is full: pay and repeat, or delete a monitor.; 404: Unknown or rotated ingest key.
Annotations the server declares
- title: Ping slug
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
signal_exit_codeThe shell exit status: 0 behaves like a ping, 1-255 record the code as a failure.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The shell exit status: 0 behaves like a ping, 1-255 record the code as a failure. `curl -fsS $ORIGIN/in/ID/$?` at the end of a script is the whole integration. `0` behaves exactly like a plain ping; 1 to 255 record the code and leave the failure for the cron.
Annotations the server declares
- title: Signal exit code
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
signal_failRecord a failed run.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Record a failed run. The next five-minute check sends the alert with reason fail. The monitor's alert_repeat_sec controls repeated alerts; the default is 24 hours. Failing is not proof of life either: the clock keeps running. The ingest never sends e-mail and never calls out — it records `alert_pending` and the cron turns it into an alert with `reason: "fail"` within 5 minutes, under the same one-per-24h cap. Works by GET or POST.
Annotations the server declares
- title: Signal fail
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
signal_startSays the run STARTED.1 finding
Why it is in this group
- The name "signal_start" says "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "signal_start" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "signal_start" says "start": a word for a change.
Description, as the server wrote it Says the run STARTED. Does not clear the dead-man clock: a routine that starts and hangs still becomes a miss. The next success records the duration. `start` is not proof of life: it does not move `last_event_at` and does not clear the miss counter, so a routine that starts and hangs still becomes a miss at the right time. The next success closes the run and records `last_duration_ms` — pass `?rid=` on both ends when runs can overlap, or the duration is measured against the wrong start. With `max_duration_sec` set on the monitor, a run left open past that ceiling alerts with `reason: "too_long"` on the next 5-minute check. Works by GET or POST.
Annotations the server declares
- title: Signal start
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 11Show 11 read-only tools
get_endpointStatus of one endpoint (use the endpoint token if you have it).1 finding
Why it is in this group
- The name "get_endpoint" says "get": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...hboard without handing over the owner's credential. With a schedule it is here that `next_..."
Description, as the server wrote it Status of one endpoint (use the endpoint token if you have it). The monitor token only reads: it lets you put the state on a third-party dashboard without handing over the owner's credential. With a schedule it is here that `next_expected_at` says when the next run is due. Only this endpoint carries `duration`: `p50_ms` (the low median, so always a duration that really happened) and `max_ms` over the last runs we measured, computed at read time over the event window we already keep — the list does not pay for it.
Annotations the server declares
- title: Get endpoint
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
healthRead service liveness before using HookPulse.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read service liveness before using HookPulse. Returns the health response; does not check a monitor.
Annotations the server declares
- title: Health
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
ingest_keyReturns (minting the first time) the key for /in/<key>/<slug>, where a ping creates its own monitor inside the free tier.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns (minting the first time) the key for /in/<key>/<slug>, where a ping creates its own monitor inside the free tier. Instruments a whole fleet with no setup call per job. One key per owner. Point a whole fleet at `/in/<key>/<slug>` and each job creates its monitor on the first check-in, **inside the free tier** — beyond it the ping answers 402 without creating anything. The key survives signing in: the crontab you deployed keeps working.
Annotations the server declares
- title: Ingest key
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_endpointsLists the guest's/session's endpoints.No findings
Why it is in this group
- The name "list_endpoints" says "list": a word for reading.
Description, as the server wrote it Lists the guest's/session's endpoints.
Annotations the server declares
- title: List endpoints
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_eventsLatest ingest pings.No findings
Why it is in this group
- The name "list_events" says "list": a word for reading.
Description, as the server wrote it Latest ingest pings.
Annotations the server declares
- title: List events
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_plansThe plans for sale, with price and term, and the account's active plan.1 finding
Why it is in this group
- The name "list_plans" says "list": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...c renewal. Without an account or wallet credential, `account` is `null`."
Description, as the server wrote it The plans for sale, with price and term, and the account's active plan. Each purchase lasts 30 days, with no automatic renewal. Each purchase lasts 30 days, with no automatic renewal. Without an account or wallet credential, `account` is `null`.
Annotations the server declares
- title: List plans
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_sitesThe state of every site you monitor (up, down, waiting, paused), with the last check.No findings
Why it is in this group
- The name "list_sites" says "list": a word for reading.
Description, as the server wrote it The state of every site you monitor (up, down, waiting, paused), with the last check. The same answer is the snapshot of the live subscription (`/api/realtime/`): after it, every check arrives as an event, so a screen never has to poll.
Annotations the server declares
- title: List sites
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_templatesIngest snippets and the JSON HookPulse POSTs on a miss.No findings
Why it is in this group
- The name "list_templates" says "list": a word for reading.
Description, as the server wrote it Ingest snippets and the JSON HookPulse POSTs on a miss. It exists so nobody guesses the alert format: `miss_json` and `recovery_json` here are the same bodies that arrive at your `alert_url`. Slack and Discord receive only the field they read.
Annotations the server declares
- title: List templates
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
ping_ingestSimulates the cron: GET on /in/:id.1 finding
Why it is in this group
- The name "ping_ingest" says "ping": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Simulates the cron: GET on /in/:id. No credential on purpose — the caller is a cron, and..."
Description, as the server wrote it Simulates the cron: GET on /in/:id. No credential on purpose — the caller is a cron, and the ID is already the secret. It costs nothing and there is no quota per ping.
Annotations the server declares
- title: Ping ingest
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
pricingRead current free allowances, options with billing off, prices and the account's 7-day trial.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read current free allowances, options with billing off, prices and the account's 7-day trial. E-mail alerts cost $0.10 once per additional monitor, even with a reused address. Check before creating the second monitor or lowering the interval: it is the number IN FORCE, not the documentation's. After the account's trial, alerts come from the ten oldest monitors and from each extra monitor that was paid for; the other monitors need a plan for alerts (`GET /api/plans`).
Annotations the server declares
- title: Pricing
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
status_feed_urlPublic URL (JSON and RSS) with the status of all the owner's endpoints.Reads text others writeNo findings
Why it is in this group
- The name "status_feed_url" says "status": a word for reading.
What it can reach
- untrusted-inputThe name "status_feed_url" says "status" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Public URL (JSON and RSS) with the status of all the owner's endpoints. The feed token only reads status: it does not create, change or delete. Whoever has the link sees the dashboard — treat it as a secret.
Annotations the server declares
- title: Status feed URL
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:16 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 18
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://hookpulse.net/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://hookpulse.net/connect
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 18 tools that change things (4 destructive, 1 irreversible, 13 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://hookpulse.net/mcp: tools/list returned 29 tools to an anonymous client, including cancel_plan (destructive), delete_endpoint (destructive), ingest_key_rotate (destructive), status_feed_rotate (destructive), signal_slug (irreversible) and 13 more
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 19 to 18
- Nov 6, 2026
- Tools that change things, listed without credentials: 16 to 19
- Authorization servers: https://hookpulse.net to https://hookpulse.net/connect
Findings
Matches of fixed checks, with the text they matched.
- Warncancel_plan
The server marks "cancel_plan" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "cancel_plan" says "cancel": a word for removing or ending something.
- Warnsignal_start
The server marks "signal_start" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "signal_start" says "start": a word for a change.
- Warnping_slug
The server marks "ping_slug" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "ping_slug" says "ping": a word for reading.
- Warnsignal_slug
The server marks "signal_slug" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
The server marks "status_feed_rotate" destructive (destructiveHint: true), and its name says "status", a word for reading.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":true,"idempotentHint":true,"openWorldHint":false}; The name "status_feed_rotate" says "status": a word for reading.
The server marks "get_api_x402_check" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "get_api_x402_check" says "get": a word for reading.
Show 4 more findingsShow fewer
- Infolist_plans
The description mentions "credential".
What this check looks forMatched text
description: "...c renewal. Without an account or wallet credential, `account` is `null`."
- Infoimport_crontab
The description mentions "credential".
What this check looks forMatched text
description: "...schedule line was recognised.; 401: No credential, or an invalid one. See this endpoint's..."
- Infoget_endpoint
The description mentions "credential".
What this check looks forMatched text
description: "...hboard without handing over the owner's credential. With a schedule it is here that `next_..."
- Infoping_ingest
The description mentions "credential".
What this check looks forMatched text
description: "Simulates the cron: GET on /in/:id. No credential on purpose — the caller is a cron, and..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 19 -> 18.View diff
- Tools that change things, listed without credentials: 19 to 18
Tools1 removed, 15 changed.−1 removed~15 changedView diff
- Removed:billing
- Changed:check_siteChanges thingsinputSchema
- Changed:create_siteChanges thingsinputSchema
- Changed:delete_endpointDeletes or cancelsinputSchema
- Changed:get_endpointOnly readsinputSchema
- Changed:healthOnly readsdescription
- Changed:import_crontabChanges thingsdescriptioninputSchema
- Changed:ingest_keyOnly readsinputSchema
- Changed:ingest_key_rotateDeletes or cancelsinputSchema
- Changed:list_endpointsOnly readsinputSchema
- Changed:list_eventsOnly readsinputSchema
- Changed:list_sitesOnly readsinputSchema
- Changed:ping_slugChanges thingsdescription
- Changed:pricingOnly readsdescriptioninputSchema
- Changed:status_feed_rotateDeletes or cancelsinputSchema
- Changed:status_feed_urlOnly readsinputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 16 -> 19; Authorization servers: https://hookpulse.net -> https://hookpulse.net/connect.View diff
- Tools that change things, listed without credentials: 16 to 19
- Authorization servers: https://hookpulse.net to https://hookpulse.net/connect
Tools6 added, 9 changed.+6 added~9 changedView diff
- Added:billingOnly reads
- Added:buy_planChanges things
- Added:cancel_planDeletes or cancels
- Added:get_api_x402_checkChanges things
- Added:list_plansOnly reads
- Added:pricingChanges things
- Changed:contactChanges thingsdescriptioninputSchema
- Changed:create_endpointChanges thingsdescriptioninputSchema
- Changed:create_siteChanges thingsdescriptioninputSchema
- Changed:get_endpointOnly readsdescription
- Changed:ingest_keyOnly readsdescription
- Changed:list_sitesOnly readsdescription
- Changed:ping_ingestOnly readsdescription
- Changed:ping_slugChanges thingsdescriptioninputSchema
- Changed:signal_slugCan't be undoneinputSchema
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http hookpulse https://hookpulse.net/mcpclaude mcp add --transport http hookpulse https://hookpulse.net/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__hookpulse__list_plans",
"mcp__hookpulse__health",
"mcp__hookpulse__list_endpoints",
"mcp__hookpulse__list_sites",
"mcp__hookpulse__get_endpoint",
"mcp__hookpulse__list_events",
"mcp__hookpulse__ping_ingest",
"mcp__hookpulse__ingest_key",
"mcp__hookpulse__pricing",
"mcp__hookpulse__status_feed_url",
"mcp__hookpulse__list_templates"
],
"ask": [
"mcp__hookpulse__buy_plan",
"mcp__hookpulse__api_index",
"mcp__hookpulse__create_guest",
"mcp__hookpulse__create_endpoint",
"mcp__hookpulse__create_site",
"mcp__hookpulse__check_site",
"mcp__hookpulse__import_crontab",
"mcp__hookpulse__signal_start",
"mcp__hookpulse__signal_fail",
"mcp__hookpulse__signal_exit_code",
"mcp__hookpulse__ping_slug",
"mcp__hookpulse__signal_slug",
"mcp__hookpulse__contact",
"mcp__hookpulse__get_api_x402_check"
],
"deny": [
"mcp__hookpulse__cancel_plan",
"mcp__hookpulse__delete_endpoint",
"mcp__hookpulse__ingest_key_rotate",
"mcp__hookpulse__status_feed_rotate"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as hookpulse. Review it before you use it.
Capability tags behind 7 rules
- mcp__hookpulse__create_endpoint untrusted-input
- mcp__hookpulse__create_site untrusted-input, outbound
- mcp__hookpulse__check_site untrusted-input
- mcp__hookpulse__signal_slug outbound
- mcp__hookpulse__status_feed_url untrusted-input
- mcp__hookpulse__status_feed_rotate untrusted-input
- mcp__hookpulse__get_api_x402_check untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/net.hookpulse/hookpulse/verify?hash=15e25269bd70c94bdf2c7ed480251c28366b97a51d7f0ced03bb56fde96d595e" | jq -e '.changed == false'Pinned hash 15e25269bd70, from Nov 10, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/net.hookpulse/hookpulse/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/net.hookpulse/hookpulse)Source: MCP Registry · repository. Synced Nov 10, 2026, 17:18 UTC.
hookpulse MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the hookpulse MCP server safe?
- No scan can promise that. What its definitions show: 29 tools, 18 of which can change, send or delete something, and 10 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the hookpulse MCP server delete data?
- Yes. 4 tools can delete, cancel or revoke something: cancel_plan, delete_endpoint, ingest_key_rotate and status_feed_rotate.
Can the hookpulse MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: signal_slug.
What tools does the hookpulse MCP server have?
- 29 tools: 4 destructive, 1 irreversible, 13 write, 11 read. cancel_plan, delete_endpoint, ingest_key_rotate, status_feed_rotate, signal_slug, buy_plan, api_index, create_guest and 21 more.
Does the hookpulse MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the hookpulse MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_site, signal_slug and get_api_x402_check.
Has the hookpulse MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.