TLS Radar MCP server
com.tlsradar/tlsradartlsradar.comstreamable-httpv0.5.1Scanned
SSL/TLS scanning, free Let's Encrypt issuance, and certificate-expiry monitoring.
16 tools: 1 can delete or cancel things, 2 do something that can't be undone, 8 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 2 do 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 TLS Radar MCP server can do
The TLS Radar MCP server is published by tlsradar.com, a domain the MCP Registry verified. It has 16 tools. It can delete or cancel things (1 tool: remove_monitor), do things that cannot be undone, such as sending, paying or publishing (finalize_certificate and invite_team_member) and create or change data (8 tools: scan_domain, create_certificate, check_certificate_propagation, renew_certificate and 4 more). 5 tools only read.
6 tools bring in text other people can write (scan_domain, create_certificate, check_certificate_propagation and 3 more); 1 tool can send data out of your system (invite_team_member).
The fixed checks matched 2 findings (annotation-conflict and tool-shadowing). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 0.5.1.
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.
16 tools
Deletes or cancels 1Claude Code: deny
remove_monitorStop monitoring a domain.No findings
Why it is in this group
- The name "remove_monitor" says "remove": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Stop monitoring a domain. Accepts the domain name or the host_id returned by list_monitors.
Annotations the server declares
- title: Stop Monitoring a Domain
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 2Claude Code: ask
finalize_certificateFinalize and issue a certificate order in one call: validates the DNS challenges, waits for Let's Encrypt, and returns the issued cert.Reads text others writeNo findings
Why it is in this group
- The name "finalize_certificate" says "finalize": a word for a change that another call does not undo.
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 Finalize and issue a certificate order in one call: validates the DNS challenges, waits for Let's Encrypt, and returns the issued cert. Step 3 of issuance - call after check_certificate_propagation reports all_found. STRONGLY PREFER passing csr_pem (generate the key + CSR locally with openssl so the private key never leaves the machine). Returns leaf_pem/chain_pem/fullchain_pem. If you must, pass a passphrase instead to get a PKCS#12 bundle - but a CSR is safer. If it replies "still validating", DNS hasn't fully propagated: re-check check_certificate_propagation and call again. Needs a locally-generated CSR (csr_pem) - requires a local shell with openssl. On a surface without one (e.g. a Claude.ai custom connector) this can't complete; it returns guidance to finish in Claude Code/Cowork or the web form. Scanning and monitoring work everywhere. On success the structuredContent carries a `handoff` object - relay `handoff.message` to the user and do NOT separately call add_monitor; the cert→monitoring handoff is automatic and server-side.
Annotations the server declares
- title: Finalize Certificate
- readOnlyHint: false
- idempotentHint: true
- openWorldHint: true
invite_team_memberInvite a user to a team by email.Can send data outNo findings
Why it is in this group
- The name "invite_team_member" says "invite": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "invite_team_member" says "invite": it sends or publishes something to other people.
Description, as the server wrote it Invite a user to a team by email. Defaults to the user's current team. Honors the plan's seat limit (returns the same upgrade payload as add_monitor when the cap is hit).
Annotations the server declares
- title: Invite Teammate
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 8Claude Code: ask
add_monitorAdd a domain to ongoing certificate monitoring with expiry alerts.No findings
Why it is in this group
- The name "add_monitor" says "add": a word for a change.
Description, as the server wrote it Add a domain to ongoing certificate monitoring with expiry alerts. Requires authentication (the user runs /mcp once). If the plan's monitor limit is reached, the response's structuredContent carries a limit-reached payload - when relaying it, LEAD with `recommended_upgrade` (it carries the plan name and price), mention `also_available` tiers in a single closing line, and offer removing an existing monitor as the free alternative. Don't dump a full tier comparison; that's choice paralysis at the moment of action.
Annotations the server declares
- title: Add Domain to Monitoring
- readOnlyHint: false
- idempotentHint: true
- openWorldHint: false
add_monitorsAdd multiple domains to monitoring in one call.No findings
Why it is in this group
- The name "add_monitors" says "add": a word for a change.
Description, as the server wrote it Add multiple domains to monitoring in one call. Returns a per-domain status so the caller can show partial-success outcomes. Honors the same plan-limit checks as add_monitor.
Annotations the server declares
- title: Add Multiple Domains
- readOnlyHint: false
- idempotentHint: true
- openWorldHint: false
check_certificate_propagationCheck whether the DNS TXT records for a certificate order have propagated (Cloudflare/Google/Quad9).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 whether the DNS TXT records for a certificate order have propagated (Cloudflare/Google/Quad9). Step 2 of issuance - poll until all_found is true, then call finalize_certificate. Returns per-record resolver results.
Annotations the server declares
- title: Check Challenge Propagation
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
create_certificateStart issuing a FREE Let's Encrypt certificate for a domain (no account required).Reads text others writeNo findings
Why it is in this group
- The name "create_certificate" 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 Start issuing a FREE Let's Encrypt certificate for a domain (no account required). Step 1 of 3. Lifetime is Let's Encrypt's default: 90 days today, 64 days from 2027-02-10; read the real expiry from the issued certificate. Pick a validation method with `challenge`: "dns-01" (default; publish a TXT record; covers apex + www) or "http-01" (serve a file over HTTP on port 80; issues the exact domain only). dns-01 with a DNS-provider API token is the most automatable; http-01 suits a server you control on port 80. Returns an order_id plus either dns_records (dns-01) or http_files (http-01) to put in place. Next: poll `check_certificate_propagation` until all_found, then call `finalize_certificate`. Strongly prefer the CSR path at finalize (the private key never leaves the user's machine). Issuing automatically offers the user ongoing monitoring by email once it completes - don't add a monitor manually afterward.
Annotations the server declares
- title: Start Certificate Issuance
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
export_monitorsDump the user's monitors as a JSON structure suitable for backup, migration, or infrastructure-as-code workflows.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 Dump the user's monitors as a JSON structure suitable for backup, migration, or infrastructure-as-code workflows. Tokens and PII are NEVER included - only domain configuration.
Annotations the server declares
- title: Export Monitors
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
import_monitorsCreate monitors from a JSON structure (typically produced by `export`).1 finding
Why it is in this group
- The name "import_monitors" says "import": a word for a change.
Findings
- Warn
The input schema at properties.payload.description names a tool "export" that this server does not list.
What this check looks forMatched text
inputSchema.properties.payload.description: "Export payload, version 1.0. Use the `export` tool to generate one."
Description, as the server wrote it Create monitors from a JSON structure (typically produced by `export`). Skips domains the user is already monitoring; honors the plan's domain limit. Returns a per-domain status.
Annotations the server declares
- title: Import Monitors
- readOnlyHint: false
- idempotentHint: true
- openWorldHint: false
renew_certificateRenew a certificate by cloning a recent order (requires the original order_id; Beacon purges orders after ~24h).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 Renew a certificate by cloning a recent order (requires the original order_id; Beacon purges orders after ~24h). Returns a new order_id and fresh DNS TXT records - then poll check_certificate_propagation and call finalize_certificate. If you don't have an order_id (the usual case at renewal time), call create_certificate for the domain instead; that IS the renewal.
Annotations the server declares
- title: Renew Certificate
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
scan_domainRun a free, anonymous SSL/TLS scan against a hostname and return certificate details.Reads text others write1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "scan_domain" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run a free, anonymous SSL/TLS scan against a hostname and return certificate details. No account required.
Annotations the server declares
- title: SSL/TLS Scan
- readOnlyHint: true
- openWorldHint: true
Only reads 5Show 5 read-only tools
get_accountReturn the current user's plan, limits, and usage so the client can render upgrade nudges proactively.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it Return the current user's plan, limits, and usage so the client can render upgrade nudges proactively.
Annotations the server declares
- title: Account & Plan Info
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_certificate_statusReturn the current state of a certificate order (dns_pending, validating, ready, completed, failed) and per-authorization Let's Encrypt statuses.Reads text others writeNo findings
Why it is in this group
- The name "get_certificate_status" says "get": a word for reading.
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 Return the current state of a certificate order (dns_pending, validating, ready, completed, failed) and per-authorization Let's Encrypt statuses. Use it to resume an interrupted issuance.
Annotations the server declares
- title: Certificate Order Status
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
get_scan_historyReturn recent scan results for a domain the user monitors.No findings
Why it is in this group
- The name "get_scan_history" says "get": a word for reading.
Description, as the server wrote it Return recent scan results for a domain the user monitors. Useful for spotting issuer changes, grade drops, or vulnerability appearances over time.
Annotations the server declares
- title: Scan History
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
list_expiring_certificatesReturn monitored certificates expiring within N days.No findings
Why it is in this group
- The name "list_expiring_certificates" says "list": a word for reading.
Description, as the server wrote it Return monitored certificates expiring within N days. Defaults to 30. If the response's structuredContent includes a `nudge` object, the user is watching enough soon-to-expire certs to benefit from a higher tier - mention it casually ONCE (lead with `nudge.recommended_upgrade`); skip it if it doesn't fit.
Annotations the server declares
- title: Expiring Certificates
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
list_monitorsList all certificates currently being monitored across the user's teams.No findings
Why it is in this group
- The name "list_monitors" says "list": a word for reading.
Description, as the server wrote it List all certificates currently being monitored across the user's teams. If the response's structuredContent includes a `nudge` object, the user is at their monitor cap - surface it casually ONCE (lead with `nudge.recommended_upgrade`, mention `nudge.also_available` in one closing line); don't force it if it doesn't fit the conversation.
Annotations the server declares
- title: List Monitored Domains
- readOnlyHint: true
- 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 out1
- 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, 18:48 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
- 11
- Protocol version
- 2024-11-05
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://tlsradar.com/.well-known/oauth-protected-resource/api/v1/mcp
- Authorization servers
- https://tlsradar.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (1 destructive, 2 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://tlsradar.com/api/v1/mcp: tools/list returned 16 tools to an anonymous client, including remove_monitor (destructive), finalize_certificate (irreversible), invite_team_member (irreversible), scan_domain (write), create_certificate (write) and 6 more
Findings
Matches of fixed checks, with the text they matched.
- Warnscan_domain
The server marks "scan_domain" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
- Warnimport_monitors
The input schema at properties.payload.description names a tool "export" that this server does not list.
What this check looks forMatched text
inputSchema.properties.payload.description: "Export payload, version 1.0. Use the `export` tool to generate one."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:add_monitorChanges thingsdescription
Install
Pinned to version 0.5.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http tlsradar https://tlsradar.com/api/v1/mcpclaude mcp add --transport http tlsradar https://tlsradar.com/api/v1/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__tlsradar__get_certificate_status",
"mcp__tlsradar__get_account",
"mcp__tlsradar__list_monitors",
"mcp__tlsradar__list_expiring_certificates",
"mcp__tlsradar__get_scan_history"
],
"ask": [
"mcp__tlsradar__scan_domain",
"mcp__tlsradar__create_certificate",
"mcp__tlsradar__check_certificate_propagation",
"mcp__tlsradar__finalize_certificate",
"mcp__tlsradar__renew_certificate",
"mcp__tlsradar__add_monitor",
"mcp__tlsradar__add_monitors",
"mcp__tlsradar__export_monitors",
"mcp__tlsradar__import_monitors",
"mcp__tlsradar__invite_team_member"
],
"deny": [
"mcp__tlsradar__remove_monitor"
]
}
}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 tlsradar. Review it before you use it.
Capability tags behind 7 rules
- mcp__tlsradar__scan_domain untrusted-input
- mcp__tlsradar__create_certificate untrusted-input
- mcp__tlsradar__check_certificate_propagation untrusted-input
- mcp__tlsradar__finalize_certificate untrusted-input
- mcp__tlsradar__get_certificate_status untrusted-input
- mcp__tlsradar__renew_certificate untrusted-input
- mcp__tlsradar__invite_team_member 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/com.tlsradar/tlsradar/verify?hash=cabe9e87387a0140bee898eae7f37e11e58cadfce9a222c648484911926836ed" | jq -e '.changed == false'Pinned hash cabe9e87387a, from Nov 11, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.tlsradar/tlsradar/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.tlsradar/tlsradar)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:07 UTC.
TLS Radar MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TLS Radar MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 11 of which can change, send or delete something, and 2 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 TLS Radar MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: remove_monitor.
Can the TLS Radar MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: finalize_certificate and invite_team_member.
What tools does the TLS Radar MCP server have?
- 16 tools: 1 destructive, 2 irreversible, 8 write, 5 read. remove_monitor, finalize_certificate, invite_team_member, scan_domain, create_certificate, check_certificate_propagation, renew_certificate, add_monitor and 8 more.
Does the TLS Radar MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TLS Radar MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): invite_team_member.
Has the TLS Radar MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.