Skip to content

Rayon Insurance MCP server

com.rayoninsure/mcprayoninsure.comstreamable-httpv1.0.0Scanned

Firm details, request forms, and contract review or quote requests with a robotics insurance broker.

4 tools: 1 do something that can't be undone and 3 only read.

Tools: 0 delete, 1 irreversible, 0 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Rayon Insurance MCP server can do

The Rayon Insurance MCP server is published by rayoninsure.com, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (submit_request), but cannot delete data. 3 tools only read.

1 tool reads private data (get_firm_details); 2 tools bring in text other people can write (list_request_forms and submit_request); 1 tool can send data out of your system (submit_request). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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 16, 2026, version 1.0.0.

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.

4 tools

Can't be undone 1Claude Code: ask
  • submit_requestSend a request to Rayon Insurance on the visitor's behalf: a contract review, quotes for a company running robots, a broker placement, an integrator checklist, a marketplace seller…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "submit_request" says "submit": a word for a change.
    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a destination (input.phone): what the tool writes goes there.
    Description, as the server wrote it
    Send a request to Rayon Insurance on the visitor's behalf: a contract review, quotes for a company running robots, a broker placement, an integrator checklist, a marketplace seller requirement, or Rayon Ops servicing. It files the same request as the form on the site and a person replies by email within two business days. It does not bind cover or produce a quote. Only call it after the visitor has seen what will be sent and asked you to send it. Documents cannot be attached here; the reply says where to email them.

    Annotations the server declares

    • title: Submit a request for the visitor
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_firm_detailsWho Rayon Insurance is, where it is licensed, what it does and does not do, and how to contact it.Reads private dataNo findings

    Why it is in this group

    • The name "get_firm_details" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "contact": it reads contacts.
    Description, as the server wrote it
    Who Rayon Insurance is, where it is licensed, what it does and does not do, and how to contact it. Call this before telling a visitor Rayon can help.

    Annotations the server declares

    • title: Get firm details
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_request_formsThe kinds of request Rayon takes and the web page where a visitor can fill in each one themselves.Reads text others writeNo findings

    Why it is in this group

    • The name "list_request_forms" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The kinds of request Rayon takes and the web page where a visitor can fill in each one themselves. Use it to pick the kind for submit_request, or to send the visitor to the form instead.

    Annotations the server declares

    • title: List request forms
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_insurance_guidesSearch Rayon's library of plain-English insurance guides: robot deployments, RaaS agreements, additional insured status, ISO generative AI exclusions (CG 40 47, CG 40 48, CG 35 08)…No findings

    Why it is in this group

    • The name "search_insurance_guides" says "search": a word for reading.
    Description, as the server wrote it
    Search Rayon's library of plain-English insurance guides: robot deployments, RaaS agreements, additional insured status, ISO generative AI exclusions (CG 40 47, CG 40 48, CG 35 08), marketplace seller requirements and certificates. Returns titles, one-line answers and links. An empty query lists every guide. General information, not advice on a specific policy.

    Annotations the server declares

    • title: Search insurance guides
    • 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.

2 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 data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__rayoninsure__submit_request"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 16, 2026, 14:19 UTC, unchanged since Nov 16, 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
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 1 tool that changes things (1 irreversible). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://rayoninsure.com/mcp: tools/list returned 4 tools to an anonymous client, including submit_request (irreversible)

    What this check looks for

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http rayoninsure https://rayoninsure.com/mcp
claude mcp add --transport http rayoninsure https://rayoninsure.com/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__rayoninsure__get_firm_details",
      "mcp__rayoninsure__list_request_forms",
      "mcp__rayoninsure__search_insurance_guides"
    ],
    "ask": [
      "mcp__rayoninsure__submit_request"
    ],
    "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 rayoninsure. Review it before you use it.

Capability tags behind 3 rules
  • mcp__rayoninsure__get_firm_details private-data
  • mcp__rayoninsure__list_request_forms untrusted-input
  • mcp__rayoninsure__submit_request 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/com.rayoninsure/mcp/verify?hash=71139ebc19f7a79f630ea87180b3d6ca667e6b5c736c059c231b28a6b1c264ee" | jq -e '.changed == false'

Pinned hash 71139ebc19f7, from Nov 16, 2026, 07:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.rayoninsure/mcp/changes.xml

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

Badge

Anlyon Radar badge for com.rayoninsure/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.rayoninsure/mcp.svg)](https://radar.anlyon.com/servers/com.rayoninsure/mcp)

Source: MCP Registry. Synced Nov 16, 2026, 07:17 UTC.

Rayon Insurance MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Rayon Insurance MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 1 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 Rayon Insurance MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Rayon Insurance MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: submit_request.

What tools does the Rayon Insurance MCP server have?

4 tools: 1 irreversible, 3 read. submit_request, get_firm_details, list_request_forms and search_insurance_guides.

Does the Rayon Insurance MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Rayon Insurance 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): submit_request.

Has the Rayon Insurance MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.