AI Agent Liability Insurance MCP server
com.johalinsurancebrokers/ai-liability-insurancejohalinsurancebrokers.comstreamable-httpv1.1.0Scanned
Quote AI agent liability insurance (Tech E&O + AI coverage) from a licensed US insurance broker.
7 tools: 3 can delete or cancel things and 4 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things. 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 AI Agent Liability Insurance MCP server can do
The AI Agent Liability Insurance MCP server is published by johalinsurancebrokers.com, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (3 tools: submit_commercial_insurance_submission, send_submission_documents and request_ai_liability_quote). 4 tools only read.
1 tool reads private data (get_submission_requirements); 4 tools bring in text other people can write (get_premium_estimate_options, submit_commercial_insurance_submission, send_submission_documents and 1 more); 1 tool can send data out of your system (send_submission_documents). 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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.1.0.
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.
7 tools
Deletes or cancels 3Claude Code: deny
request_ai_liability_quoteSubmits a quote request for AI agent liability insurance (Tech E&O + AI coverage) for a US company headquartered in CA, TX, IL, WI, LA.Reads text others writeNo findings
Why it is in this group
- The name "request_ai_liability_quote" says "request": a word for a change.
- The server marks it destructive (destructiveHint: true).
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 Submits a quote request for AI agent liability insurance (Tech E&O + AI coverage) for a US company headquartered in CA, TX, IL, WI, LA. A licensed broker rates it and emails the quote to the company contact, usually the same business day. Free. Each call creates a real quote request that a human broker works on, using the company details provided. It does not bind coverage.
Annotations the server declares
- title: Request an AI agent liability insurance quote
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
send_submission_documentsDelivers base64 documents (loss runs, declarations page, SOV spreadsheet, rent roll, photos, leases) to the broker working a submission, by its CQ- reference.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_submission_documents" says "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "send_submission_documents" says "send": it sends or publishes something to other people.
Description, as the server wrote it Delivers base64 documents (loss runs, declarations page, SOV spreadsheet, rent roll, photos, leases) to the broker working a submission, by its CQ- reference. Up to 4 MB per call.
Annotations the server declares
- title: Send submission documents
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
submit_commercial_insurance_submissionSends a commercial property and/or general liability submission for a risk in CA, TX, IL, MO, WI, LA to a licensed broker at Johal Insurance Brokers, who shops it with 20+ carriers…Reads text others writeNo findings
Why it is in this group
- The name "submit_commercial_insurance_submission" 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.
- The server marks it destructive (destructiveHint: true).
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 Sends a commercial property and/or general liability submission for a risk in CA, TX, IL, MO, WI, LA to a licensed broker at Johal Insurance Brokers, who shops it with 20+ carriers and contacts the owner, usually the same business day. Accepted only when the owner authorized it, an effective date is given, and core facts are present (per building: year built, construction, stories, square feet, building value; 5-year loss history). Requests marked price_check_only are not submitted and get the premium calculator link instead. Each accepted call creates a real submission a human works on. It does not bind coverage. Optional base64 attachments (loss runs, dec page, SOV, rent roll, photos) up to 4 MB.
Annotations the server declares
- title: Submit commercial insurance submission
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Only reads 4Show 4 read-only tools
get_ai_liability_coverage_infoDescribes the AI agent liability insurance Johal Insurance Brokers (licensed US broker) can quote: Technology E&O with affirmative AI coverage for companies that build or deploy AI…No findings
Why it is in this group
- The name "get_ai_liability_coverage_info" says "get": a word for reading.
Description, as the server wrote it Describes the AI agent liability insurance Johal Insurance Brokers (licensed US broker) can quote: Technology E&O with affirmative AI coverage for companies that build or deploy AI agents. Returns coverages, limits, eligible states, required quote fields and how binding works. Free, no side effects.
Annotations the server declares
- title: AI agent liability insurance — what's covered
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_commercial_insurance_guideReturns Johal Insurance Brokers' commercial insurance knowledge base: lines and property classes placed (commercial property $500K–$50M+, general liability, contractor GL) in CA, T…No findings
Why it is in this group
- The name "get_commercial_insurance_guide" says "get": a word for reading.
Description, as the server wrote it Returns Johal Insurance Brokers' commercial insurance knowledge base: lines and property classes placed (commercial property $500K–$50M+, general liability, contractor GL) in CA, TX, IL, MO, WI, LA, how quoting and binding work, what a complete submission needs, and the tool list. Free, no side effects.
Annotations the server declares
- title: Commercial insurance guide
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_submission_requirementsReturns the full question list a carrier needs, grouped by form: ACORD 125 (applicant), ACORD 140 (property, per building), statement of values columns (3+ buildings), ACORD 126 (g…Reads private dataNo findings
Why it is in this group
- The name "get_submission_requirements" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "document": it reads documents.
Description, as the server wrote it Returns the full question list a carrier needs, grouped by form: ACORD 125 (applicant), ACORD 140 (property, per building), statement of values columns (3+ buildings), ACORD 126 (general liability), the class-specific supplemental for the property type, and the document list (5-year loss runs, dec page, rent roll, SOV, photos). Free, no side effects.
Annotations the server declares
- title: Submission requirements
- readOnlyHint: true
- destructiveHint: false
- 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 data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- 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.
{
"permissions": {
"deny": [
"mcp__ai-liability-insurance__send_submission_documents"
]
}
}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 15, 2026, 13:21 UTC, unchanged since Nov 15, 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
- 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 3 tools that change things (3 destructive). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://johalinsurancebrokers.com/mcp: tools/list returned 7 tools to an anonymous client, including submit_commercial_insurance_submission (destructive), send_submission_documents (destructive), request_ai_liability_quote (destructive)
Posture changes
- Nov 15, 2026
- Tools that change things, listed without credentials: 1 to 3
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.
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 3.View diff
- Tools that change things, listed without credentials: 1 to 3
Tools5 added, 2 changed.+5 added~2 changedView diff
- Added:get_commercial_insurance_guideOnly reads
- Added:get_premium_estimate_optionsOnly reads
- Added:get_submission_requirementsOnly reads
- Added:send_submission_documentsDeletes or cancels
- Added:submit_commercial_insurance_submissionDeletes or cancels
- Changed:get_ai_liability_coverage_infoOnly readsannotations
- Changed:request_ai_liability_quoteDeletes or cancelsannotations
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http ai-liability-insurance https://johalinsurancebrokers.com/mcpclaude mcp add --transport http ai-liability-insurance https://johalinsurancebrokers.com/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__ai-liability-insurance__get_commercial_insurance_guide",
"mcp__ai-liability-insurance__get_submission_requirements",
"mcp__ai-liability-insurance__get_premium_estimate_options",
"mcp__ai-liability-insurance__get_ai_liability_coverage_info"
],
"ask": [],
"deny": [
"mcp__ai-liability-insurance__submit_commercial_insurance_submission",
"mcp__ai-liability-insurance__send_submission_documents",
"mcp__ai-liability-insurance__request_ai_liability_quote"
]
}
}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 ai-liability-insurance. Review it before you use it.
Capability tags behind 5 rules
- mcp__ai-liability-insurance__get_submission_requirements private-data
- mcp__ai-liability-insurance__get_premium_estimate_options untrusted-input
- mcp__ai-liability-insurance__submit_commercial_insurance_submission untrusted-input
- mcp__ai-liability-insurance__send_submission_documents untrusted-input, outbound
- mcp__ai-liability-insurance__request_ai_liability_quote untrusted-input
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.johalinsurancebrokers/ai-liability-insurance/verify?hash=745d115e1e40c838cead3af4ba927c5ad257956f40ad602807c31ec50a8b60d1" | jq -e '.changed == false'Pinned hash 745d115e1e40, from Nov 11, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.johalinsurancebrokers/ai-liability-insurance/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.johalinsurancebrokers/ai-liability-insurance)Source: MCP Registry. Synced Nov 11, 2026, 23:17 UTC.
AI Agent Liability Insurance MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Agent Liability Insurance MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 3 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 AI Agent Liability Insurance MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: submit_commercial_insurance_submission, send_submission_documents and request_ai_liability_quote.
Can the AI Agent Liability Insurance 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 AI Agent Liability Insurance MCP server have?
- 7 tools: 3 destructive, 4 read. submit_commercial_insurance_submission, send_submission_documents, request_ai_liability_quote, get_commercial_insurance_guide, get_submission_requirements, get_premium_estimate_options and get_ai_liability_coverage_info.
Does the AI Agent Liability Insurance MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Agent Liability 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): send_submission_documents.
Has the AI Agent Liability Insurance 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.