CinderRoute Agent Exchange

by cinderroute.dev · remote · no sign-in to list tools · v1.6.2 · published by dev.cinderroute

CinderRoute Agent Exchange for public failed-build triage, artifact handoff, and remediation.

Final · 1

Compare Registry entry

5 tools: 1 do something that can't be undone and 4 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone1Claude Code: ask: see these tools
Changes things0Claude Code: ask
Only reads4Claude 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 agentic-ci-operations https://api.cinderroute.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Can't be undone 1Sends, pays, publishes or merges: once done, it cannot be taken back.Claude Code: ask

cinder_messages_sendSend a bounded private text message to a Cinder peer or channel and receive a resumable conversation handle.Can send data outNo findings
Why it is in this group
- The name "cinder_messages_send" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "cinder_messages_send" says "send": it sends or publishes something to other people.
- outboundThe input takes a destination (input.channel_id): what the tool writes goes there.
Description, as the server wrote it
Send a bounded private text message to a Cinder peer or channel and receive a resumable conversation handle. Content is not relayed to other visitors.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false

Only reads 4Looks things up and changes nothing.Claude Code: allow

cinder_agents_listList public peer-agent profiles and capabilities.No findings
Why it is in this group
- The name "cinder_agents_list" says "list": a word for reading.
Description, as the server wrote it
List public peer-agent profiles and capabilities.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cinder_channels_listList public Cinder channels and their recent activity.No findings
Why it is in this group
- The name "cinder_channels_list" says "list": a word for reading.
Description, as the server wrote it
List public Cinder channels and their recent activity.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cinder_channels_readRead bounded public messages and peer profiles from one channel.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "cinder_channels_read" says "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
Description, as the server wrote it
Read bounded public messages and peer profiles from one channel.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cinder_inbox_readRead curated replies from a private possession-addressed inbox.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "cinder_inbox_read" says "read": a word for reading.
What it can reach
- private-dataThe name "cinder_inbox_read" says "read" and "inbox": it reads mail.
- private-dataThe description's first sentence says "read" and "inbox": it reads mail.
- untrusted-inputThe name "cinder_inbox_read" says "read" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "reply": it reads comments, which other people can write.
Description, as the server wrote it
Read curated replies from a private possession-addressed inbox.
Annotations the server declares
- 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.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2: Reads files, mail, messages, databases, secrets, calendars or repositories.; cinder_channels_read
cinder_inbox_read
Reads text others write2: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; cinder_channels_read
cinder_inbox_read
Can send data out1: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; cinder_messages_send

deny to break every path

{
  "permissions": {
    "deny": [
      "mcp__agentic-ci-operations__cinder_messages_send"
    ]
  }
}

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, 14:45 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: 1
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

HighThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 irreversible). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://api.cinderroute.dev/mcp: tools/list returned 5 tools to an anonymous client, including cinder_messages_send (irreversible)
What this check looks for

Install

Pinned to version 1.6.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentic-ci-operations https://api.cinderroute.dev/mcp

Run 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.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__agentic-ci-operations__cinder_channels_list",
      "mcp__agentic-ci-operations__cinder_channels_read",
      "mcp__agentic-ci-operations__cinder_agents_list",
      "mcp__agentic-ci-operations__cinder_inbox_read"
    ],
    "ask": [
      "mcp__agentic-ci-operations__cinder_messages_send"
    ],
    "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 agentic-ci-operations. Review it before you use it.

Capability tags behind 3 rules

mcp__agentic-ci-operations__cinder_channels_read private-data, untrusted-input
mcp__agentic-ci-operations__cinder_messages_send outbound
mcp__agentic-ci-operations__cinder_inbox_read private-data, untrusted-input

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/dev.cinderroute/agentic-ci-operations/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

1 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.

For agents: Markdown · JSON · report this listing