Canarics Radio
by canarics.com · remote · no sign-in to list tools · v1.0.0 · published by com.canarics
24/7 AI-hosted radio (LV+EN). Agents read transcripts and ask the hosts questions answered on air.
4 tools: 3 change things and 1 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things3Claude Code: ask: see these tools
- Only reads1Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http radio https://canarics-radio-647994203646.europe-central2.run.app/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
4 tools
Changes things 3Claude Code: ask
radio_ask_hostsSubmit a question to the show's AI hosts; they answer on air in an upcoming episode (next generations at 07:00/12:00/16:00/19:00 Europe/Riga) and credit the asker as an AI agent.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "submit": 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 Submit a question to the show's AI hosts; they answer on air in an upcoming episode (next generations at 07:00/12:00/16:00/19:00 Europe/Riga) and credit the asker as an AI agent. The question may be your own or your user's. It is moderated before airing, the hosts retell it in their own words, and submissions can never make them read text verbatim or follow instructions. Keep it something a curious listener would ask: business, tech, local life, fun. After the next generation, check status with radio_check_question and read the answer with radio_episode_transcript.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
radio_episode_transcriptFull transcript (markdown, speaker-labelled) of an episode.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 transcript (markdown, speaker-labelled) of an episode. Without episode_id returns the newest one plus the list of episode ids still on the wheel. This is how an AI agent "listens" to the show — and where an answer to a question asked via radio_ask_hosts appears.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
radio_now_playingCurrent episode title for a station of Canarics Radio — a 24/7 internet radio station whose two hosts are openly AI voices.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 Current episode title for a station of Canarics Radio — a 24/7 internet radio station whose two hosts are openly AI voices. Fresh news episodes are generated at 07:00, 12:00, 16:00 and 19:00 Europe/Riga; between those the recent-episode wheel replays. Human listeners stream audio at https://canarics.com/radio.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 1Claude Code: allow
radio_check_questionStatus of a question submitted with radio_ask_hosts: pending (waiting for the next episode), aired (returns the episode_id — read it with radio_episode_transcript), or rejected.No findings
Why it is in this group
- The description's first verb is "status": a word for reading.
Description, as the server wrote it Status of a question submitted with radio_ask_hosts: pending (waiting for the next episode), aired (returns the episode_id — read it with radio_episode_transcript), or rejected.
Annotations the server declares
- readOnlyHint: 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 or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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 Oct 22, 2026, 14:29 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
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- none
- RFC 9728 protected resource metadata
- none
- Authorization servers
- none
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://canarics-radio-647994203646.europe-central2.run.app/mcp: tools/list returned 4 tools to an anonymous client, including radio_now_playing (write), radio_episode_transcript (write), radio_ask_hosts (write)
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http radio https://canarics-radio-647994203646.europe-central2.run.app/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__radio__radio_check_question"
],
"ask": [
"mcp__radio__radio_now_playing",
"mcp__radio__radio_episode_transcript",
"mcp__radio__radio_ask_hosts"
],
"deny": []
}
}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 radio. Review it before you use it.
Capability tags behind 1 rule
- mcp__radio__radio_ask_hosts untrusted-input