Flautoquotes MCP server
com.flautoquotes/quote-exchangeflautoquotes.comstreamable-httpv0.5.0Scanned
Indicative US auto insurance prices for agents: rating facts only, no PII, consented path to agents.
8 tools: 6 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 3
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change 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 Flautoquotes MCP server can do
The Flautoquotes MCP server is published by flautoquotes.com, a domain the MCP Registry verified. It has 8 tools. It can create or change data (6 tools: check_eligibility, pull_requests, data_use_terms, request_agent_contact and 2 more), but cannot delete data. 2 tools only read.
2 tools bring in text other people can write (request_agent_contact and register_agency); 3 tools can send data out of your system (pull_requests, request_agent_contact and register_agency).
The fixed checks matched 2 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 0.5.0.
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.
8 tools
Changes things 6Claude Code: ask
check_eligibilityCheck whether we can return quotes for a state before any personal details are collected.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 Check whether we can return quotes for a state before any personal details are collected. Call this first. Returns the states we are licensed in, what we can do in each, and how many licensed agents can take a request there.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
data_use_termsWhat happens to anything you send us: who receives it, for what purpose, how long it is kept, how your human revokes it, and the exact consent wording to present before request_age…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 What happens to anything you send us: who receives it, for what purpose, how long it is kept, how your human revokes it, and the exact consent wording to present before request_agent_contact. Machine readable so you can evaluate the exchange before making it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
market_dataThe qualified demand dataset contains only requests backed by a cryptographically or IP-verified agent, or a phone-verified consumer outcome.1 finding
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.
Findings
- Info
The input schema at properties.credential.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.description: "MPP credential"
Description, as the server wrote it The qualified demand dataset contains only requests backed by a cryptographically or IP-verified agent, or a phone-verified consumer outcome. User-agent claims, legacy rows, probes and impostors are quarantined and unavailable for sale. Qualified rows are de-identified (age band, ZIP3, vehicle, coverage, mileage band, prices shown, door, verified agent identity and outcome). Never a name, phone, email, date of birth or five-digit ZIP. Filter by state, since, until, door, vendor; limit and offset. Priced per record with a minimum per pull; pay with a prepaid buyer key, x402, MPP or AP2. Without payment the result is a 402 with the price and a preview count. A free sample and the schema are at /data.json.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
pull_requestsDrain the queue of pool records routed to you.Can send data out1 finding
Why it is in this group
- The name "pull_requests" says "request": a word for a change.
What it can reach
- outboundThe name "pull_requests" says "request" and "pull request": it writes something other people read.
Findings
- Info
The input schema at properties.credential.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.description: "MPP credential (the base64url JSON that would follow "..."
Description, as the server wrote it Drain the queue of pool records routed to you. Requires your buyer key. Metered buyers receive an x402 payment requirement (status 402, accepts[]) until a payment is supplied. Records are projected to the scope the consumer granted — never wider.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
register_agencyFor an AI working for a licensed insurance agency: register the agency to receive consented consumer requests in its states.Reads text others writeCan send data outNo 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.
- outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it For an AI working for a licensed insurance agency: register the agency to receive consented consumer requests in its states. Needs the agency name, the producer NPN (National Producer Number) and its state, the states it is appointed in, the licensed contact's name, email and mobile, and how leads should arrive (email, webhook, or pull by key). The licensed contact confirms by a link sent to their email; nothing is delivered before that. The first agencies in a state receive leads free for a founding period, then prepaid credits by card. Read /join for the terms.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
request_agent_contactConnect the consumer with licensed insurance agents who can quote firm and bind.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "request_agent_contact" says "request": 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.
- outboundThe input takes a destination (input.phone_number): what the tool writes goes there.
Description, as the server wrote it Connect the consumer with licensed insurance agents who can quote firm and bind. Needs the quote_id from get_quotes, the consumer's name and phone, and the consumer's explicit consent to be contacted — granted by the human, presented by you, or confirmed by the human directly at the consent URL the elicitation returns. Under scope contact_consumer up to 4 licensed agents receive the request and contact details; sell_identity additionally permits sharing with marketing partners. Nothing leaves without the consent. Every delivery and refusal is receipted, and POST /forget revokes.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
agency_statusFor a registered agency: its states, rail, terms, founding period, queued and delivered counts, credit balance, and whether the licence was verified.No findings
Why it is in this group
- The name "agency_status" says "status": a word for reading.
Description, as the server wrote it For a registered agency: its states, rail, terms, founding period, queued and delivered counts, credit balance, and whether the licence was verified. Requires the buyer key issued at confirmation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_quotesReturn indicative auto insurance prices from multiple carriers, where this entity is licensed to show them.No findings
Why it is in this group
- The name "get_quotes" says "get": a word for reading.
Description, as the server wrote it Return indicative auto insurance prices from multiple carriers, where this entity is licensed to show them. Takes rating facts only — no name, phone, email, SSN or licence number is required for an indicative price. Where we are not licensed to show prices, the request is still registered and a quote_id returned so licensed agents can quote it. If facts are missing the server asks for exactly what it needs and nothing more.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: 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.
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 write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- 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, 18:38 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
- 6
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://flautoquotes.com/: tools/list returned 8 tools to an anonymous client, including check_eligibility (write), pull_requests (write), data_use_terms (write), request_agent_contact (write), register_agency (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
- Infopull_requests
The input schema at properties.credential.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.description: "MPP credential (the base64url JSON that would follow "..."
- Infomarket_data
The input schema at properties.credential.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.description: "MPP credential"
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 0.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http quote-exchange https://flautoquotes.com/claude mcp add --transport http quote-exchange https://flautoquotes.com/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.
{
"permissions": {
"allow": [
"mcp__quote-exchange__get_quotes",
"mcp__quote-exchange__agency_status"
],
"ask": [
"mcp__quote-exchange__check_eligibility",
"mcp__quote-exchange__pull_requests",
"mcp__quote-exchange__data_use_terms",
"mcp__quote-exchange__request_agent_contact",
"mcp__quote-exchange__register_agency",
"mcp__quote-exchange__market_data"
],
"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 quote-exchange. Review it before you use it.
Capability tags behind 3 rules
- mcp__quote-exchange__pull_requests outbound
- mcp__quote-exchange__request_agent_contact untrusted-input, outbound
- mcp__quote-exchange__register_agency 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.flautoquotes/quote-exchange/verify?hash=d31a897dca7a353673bf6b954d1784ebfd94e4f9cc65b977075df747fc97e860" | jq -e '.changed == false'Pinned hash d31a897dca7a, from Nov 13, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.flautoquotes/quote-exchange/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.flautoquotes/quote-exchange)Source: MCP Registry. Synced Oct 21, 2026, 17:55 UTC.
Flautoquotes MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Flautoquotes MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 6 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 Flautoquotes MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Flautoquotes 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 Flautoquotes MCP server have?
- 8 tools: 6 write, 2 read. check_eligibility, pull_requests, data_use_terms, request_agent_contact, register_agency, market_data, get_quotes and agency_status.
Does the Flautoquotes MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Flautoquotes MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): pull_requests, request_agent_contact and register_agency.
Has the Flautoquotes MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.