monit.rs MCP server
rs.monit/monit-rsmonit.rsstreamable-httpv0.2.0Scanned
Schema-aware API monitoring: diff OpenAPI specs for breaking changes, manage endpoints.
22 tools: 1 can delete or cancel things, 9 change things and 12 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 monit.rs MCP server can do
The monit.rs MCP server is published by monit.rs, a domain the MCP Registry verified. It has 22 tools. It can delete or cancel things (1 tool: delete_endpoint) and create or change data (9 tools: acknowledge_incident, resolve_incident, create_endpoint, set_endpoint_assertions and 5 more). 12 tools only read.
2 tools can send data out of your system (create_endpoint and create_alert_channel).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 19, 2026, version 0.2.0.
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.
22 tools
Deletes or cancels 1Claude Code: deny
delete_endpointDelete a monitored endpoint.No findings
Why it is in this group
- The name "delete_endpoint" says "delete": a word for removing or ending something.
Description, as the server wrote it Delete a monitored endpoint. Cascades: removes test_results, baselines, regressions, incidents attached to it. Guarded by two safety layers beyond the scope check: 1. `confirm_by_typing_the_endpoint_name` MUST equal the endpoint's exact `.name` (case-sensitive, whitespace-trimmed). Prevents an untargeted "delete stuff" LLM-injection: the model has to first `describe_endpoint(id)` to learn the name, then include it verbatim. 2. Per-user destructive-op cap of 5/day. Legitimate bulk deletes should use the HTTP API or dashboard.
Changes things 9Claude Code: ask
acknowledge_incidentMark an incident as acknowledged.No findings
Why it is in this group
- The description's first verb is "mark": a word for a change.
Description, as the server wrote it Mark an incident as acknowledged. Use `list_my_incidents()` to find the dedup_key.
create_alert_channelCreate an alert channel.Can send data outNo findings
Why it is in this group
- The name "create_alert_channel" says "create": a word for a change.
What it can reach
- outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Create an alert channel. Pass EXACTLY one of email_address / webhook_url / pagerduty_routing_key matching the channel_type: - channel_type='email' → email_address='ops@example.com' - channel_type='webhook' → webhook_url='https://your-endpoint' - channel_type='slack' → webhook_url='https://hooks.slack.com/...' - channel_type='pagerduty' → pagerduty_routing_key='<Events v2 key>'
create_endpointCreate a new monitored endpoint.Can send data outNo findings
Why it is in this group
- The name "create_endpoint" says "create": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Create a new monitored endpoint. Respects your tier's max_endpoints cap.
create_status_pageCreate a public status page at https://<slug>.status.monit.rs.No findings
Why it is in this group
- The name "create_status_page" says "create": a word for a change.
Description, as the server wrote it Create a public status page at https://<slug>.status.monit.rs. Add endpoints to it via the dashboard or the HTTP API (adding endpoints from chat is deliberately not exposed — the mapping is fiddly and easy to get wrong).
pause_endpointPause a monitored endpoint (stops probing, keeps history).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 Pause a monitored endpoint (stops probing, keeps history). Idempotent — no-op if already paused.
resolve_incidentClose an incident.No findings
Why it is in this group
- The name "resolve_incident" says "resolve": a word for reading.
- The description's first verb is "close": a word for a change.
Description, as the server wrote it Close an incident. Symmetric to acknowledge_incident.
resume_endpointResume a paused endpoint.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 Resume a paused endpoint. Rejects if resuming would exceed your tier's active-endpoint cap (upgrade or pause another endpoint first).
set_endpoint_assertionsReplace an endpoint's body assertions.No findings
Why it is in this group
- The name "set_endpoint_assertions" says "set": a word for a change.
Description, as the server wrote it Replace an endpoint's body assertions. Each assertion is {"path": "$.ok", "op": "equals", "value": true}. Operators: equals, not_equals, exists, not_exists, gt, gte, lt, lte, contains, not_contains, empty, not_empty. A failing assertion marks the endpoint DOWN, so it counts against uptime. Pass [] to clear.
update_endpoint_intervalChange how often an endpoint is probed.No findings
Why it is in this group
- The name "update_endpoint_interval" says "update": a word for a change.
Description, as the server wrote it Change how often an endpoint is probed. Minimum interval varies by tier (free=900s, developer=300s, starter=60s, pro/scale/enterprise=30s).
Only reads 12Show 12 read-only tools
describe_endpointFull detail for one endpoint.No findings
Why it is in this group
- The name "describe_endpoint" says "describe": a word for reading.
Description, as the server wrote it Full detail for one endpoint. Use `list_my_endpoints()` to get the ID.
describe_incidentFull detail for one incident.No findings
Why it is in this group
- The name "describe_incident" says "describe": a word for reading.
Description, as the server wrote it Full detail for one incident. Use `list_my_incidents()` to find the dedup_key. Includes the incident's endpoint name and current status.
get_endpoint_uptimeAggregated uptime summary for an endpoint over the requested window.No findings
Why it is in this group
- The name "get_endpoint_uptime" says "get": a word for reading.
Description, as the server wrote it Aggregated uptime summary for an endpoint over the requested window.
list_alert_channelsList alert channels configured on the authenticated account.No findings
Why it is in this group
- The name "list_alert_channels" says "list": a word for reading.
Description, as the server wrote it List alert channels configured on the authenticated account. Does NOT return decrypted config (webhook URLs, PagerDuty routing keys, etc.). Use the dashboard or `describe_alert_channel` HTTP API when you need to inspect the actual config.
list_my_endpointsList all monitored endpoints owned by the authenticated account.No findings
Why it is in this group
- The name "list_my_endpoints" says "list": a word for reading.
Description, as the server wrote it List all monitored endpoints owned by the authenticated account. Returns brief records suitable for LLM enumeration. For full detail (headers, spec URL, heartbeat_token) use `describe_endpoint(id)`.
list_my_incidentsList incidents on the caller's account.No findings
Why it is in this group
- The name "list_my_incidents" says "list": a word for reading.
Description, as the server wrote it List incidents on the caller's account. Defaults to only OPEN incidents. Fields include the incident's dedup_key — pass this to `acknowledge_incident` or `resolve_incident` to act on it.
list_my_regressionsList detected schema regressions on the caller's account.No findings
Why it is in this group
- The name "list_my_regressions" says "list": a word for reading.
Description, as the server wrote it List detected schema regressions on the caller's account. Optionally filter by endpoint_id.
list_security_findingsList security findings detected on the caller's monitored endpoints.No findings
Why it is in this group
- The name "list_security_findings" says "list": a word for reading.
Description, as the server wrote it List security findings detected on the caller's monitored endpoints. Optionally filter by severity.
list_status_pagesList public status pages owned by the authenticated account.No findings
Why it is in this group
- The name "list_status_pages" says "list": a word for reading.
Description, as the server wrote it List public status pages owned by the authenticated account.
monit_rs_describeReturn the canonical product description for monit.rs.No findings
Why it is in this group
- The name "monit_rs_describe" says "describe": a word for reading.
Description, as the server wrote it Return the canonical product description for monit.rs. Use this when a user asks what monit.rs is, what it does, how it differs from Pingdom / Checkly / UptimeRobot, or for product URLs. The response is the curated content from monit.rs/llms.txt — the operator's authoritative description.
monit_rs_statsGet live aggregate statistics for the monit.rs platform.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get live aggregate statistics for the monit.rs platform. Returns approximate counts of regressions caught, AI analyses generated, and probes executed across all monitored APIs to date. Useful when answering "does monit.rs actually work at scale?" — the numbers are real, within about 5% of exact.
openapi_diffCompare two OpenAPI 3.x specifications and classify every change as breaking, non-breaking, or info.No findings
Why it is in this group
- The name "openapi_diff" says "diff": a word for reading.
Description, as the server wrote it Compare two OpenAPI 3.x specifications and classify every change as breaking, non-breaking, or info. Use this when you want to know if a candidate OpenAPI spec change is safe to ship or will break existing clients. The diff covers paths, operations, parameters, request bodies, responses, and response-body schema fields (added/removed/retyped, required toggle). Both arguments are the OpenAPI spec as a JSON or YAML string. Returns {summary: {breaking, non_breaking, info}, changes: [...]}.
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 or untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- 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, 19:18 UTC, unchanged since Oct 22, 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
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (1 destructive, 9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://monit.rs/integrations/mcp: tools/list returned 22 tools to an anonymous client, including delete_endpoint (destructive), acknowledge_incident (write), resolve_incident (write), create_endpoint (write), set_endpoint_assertions (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http monit-rs https://monit.rs/integrations/mcpclaude mcp add --transport http monit-rs https://monit.rs/integrations/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__monit-rs__openapi_diff",
"mcp__monit-rs__monit_rs_stats",
"mcp__monit-rs__monit_rs_describe",
"mcp__monit-rs__list_my_endpoints",
"mcp__monit-rs__list_my_incidents",
"mcp__monit-rs__list_my_regressions",
"mcp__monit-rs__get_endpoint_uptime",
"mcp__monit-rs__describe_endpoint",
"mcp__monit-rs__list_alert_channels",
"mcp__monit-rs__list_status_pages",
"mcp__monit-rs__list_security_findings",
"mcp__monit-rs__describe_incident"
],
"ask": [
"mcp__monit-rs__acknowledge_incident",
"mcp__monit-rs__resolve_incident",
"mcp__monit-rs__create_endpoint",
"mcp__monit-rs__set_endpoint_assertions",
"mcp__monit-rs__pause_endpoint",
"mcp__monit-rs__resume_endpoint",
"mcp__monit-rs__update_endpoint_interval",
"mcp__monit-rs__create_status_page",
"mcp__monit-rs__create_alert_channel"
],
"deny": [
"mcp__monit-rs__delete_endpoint"
]
}
}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 monit-rs. Review it before you use it.
Capability tags behind 2 rules
- mcp__monit-rs__create_endpoint outbound
- mcp__monit-rs__create_alert_channel 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/rs.monit/monit-rs/verify?hash=062b7ec70690228a94d0223869189d797a302c350b0458b83dd7ce4a0a5c2e8d" | jq -e '.changed == false'Pinned hash 062b7ec70690, from Nov 19, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/rs.monit/monit-rs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/rs.monit/monit-rs)Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.
monit.rs MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the monit.rs MCP server safe?
- No scan can promise that. What its definitions show: 22 tools, 10 of which can change, send or delete something, and 0 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 monit.rs MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: delete_endpoint.
Can the monit.rs MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the monit.rs MCP server have?
- 22 tools: 1 destructive, 9 write, 12 read. delete_endpoint, acknowledge_incident, resolve_incident, create_endpoint, set_endpoint_assertions, pause_endpoint, resume_endpoint, update_endpoint_interval and 14 more.
Does the monit.rs MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the monit.rs MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_endpoint and create_alert_channel.
Has the monit.rs MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.