Skip to content

Foresee MCP server

io.github.Foresee-Tech/foreseeForesee-Techstreamable-httpv4.0.0Scanned

Let AI assistants shop for home and auto insurance: compare quote estimates across every carrier.

2 tools: 1 can delete or cancel things and 1 change things.

Tools: 1 delete, 0 irreversible, 1 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. 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 Foresee MCP server can do

The Foresee MCP server is published by the GitHub account Foresee-Tech. It has 2 tools. It can delete or cancel things (1 tool: live_carrier_quotes) and create or change data (1 tool: quote_insurance). None of its tools only reads.

1 tool brings in text other people can write (live_carrier_quotes).

The fixed checks matched 2 findings (long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 15, 2026, version 4.0.0.

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.

2 tools

Deletes or cancels 1Claude Code: deny
  • live_carrier_quotesPurpose: confirm quote estimates on the carriers' own quote sites, via Foresee agents completing their real quote flows.Reads text others write1 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 destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description is 8,972 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...is used for (property.occupancy); how many people live there (property.household)"

      What this check looks for
    Description, as the server wrote it
    Purpose: confirm quote estimates on the carriers' own quote sites, via Foresee agents completing their real quote flows. IDEMPOTENT, keyed on the profile: the first call commissions the walks; calling again with the same profile collects progress and results instead of re-submitting anything — whatever the ask. A profile that has already been walked returns those results (the carriers are never asked twice): the envelope's ``coverage_selection`` names the ask the walk typed, and each quote carries the carrier's other recorded coverage options as ``variants``, so a new ask reads the same run. So call once to start, then re-call after a few minutes to collect; agents still working report their stage. Ask ONCE, before the first call: the consent disclosure below, the identity fields, and the questions listed at the end of this description under EVERY LINE and under the line being walked — all in one message, so the first commissioning call walks every carrier. A call made before consent submits nothing and answers ``authorization_required`` with the profile's ``needs``, for when you have not asked yet. No sign-in is required. The one hard requirement is the user's own consent, captured in-band: BEFORE the commissioning call, you MUST tell the user, plainly: Foresee will submit their details to the named carriers; the carriers may obtain their credit-based insurance score (a soft pull, with no impact on your credit score); and the carriers may contact them by email or phone. Then get their explicit go-ahead and pass their affirmation VERBATIM as ``user_authorization`` (e.g. "yes, go ahead"). The affirmation is stored as the durable consent record for the dispatch; without one the call is refused with ``authorization_required``. Foresee only collects quotes; it does not take payment or bind insurance. Collect the ``identity`` fields in chat. Nothing is filled in from anywhere else: what the walks type is what the call states. A ``missing_facts`` response is normal: carrier forms insist on facts (body style, purchase date, age first licensed…) that Foresee will not invent. Each ``needs`` entry carries the carrier (``scope``), the facts in the walk's own words (``need``), and ``fields[]`` — per fact, the ``ask`` beside the exact schema path to pass the answer under (``field``, e.g. ``auto.vehicles[].purchase_date``; ``identity.…`` paths go on ``identity``). Ask the user for exactly those facts, then call again with the answers merged in at those paths. A fact with no ``field`` has no profile home yet — relay that carrier's ask as unavailable rather than guessing a key. While any carrier waits on a fact the user can answer, nothing is submitted: the carriers already able to go are listed under ``ready`` and held, so every carrier is walked together. Only when the user cannot or will not answer, re-call with ``dispatch_ready_only=true`` to walk the ready ones now; that receipt is PARTIAL — follow its ``recover`` block: re-call with the new facts merged AND ``carriers`` set to exactly ``recover.carriers`` — a changed profile is a new dispatch, and an unscoped re-call would re-submit the already-walked carriers too. Unasserted MINOR facts are not asked: a form field that is really a claim nobody made (an anti-theft device, a defensive-driving course, a licence held abroad) is answered with the declared no-claim value — never a discount claim — and every one comes back in ``assumptions`` (``field`` + the ``assumed`` value submitted). Relay them with the results; if the user corrects one, re-call with the real value at that path. ``carriers``: OMIT it to walk every carrier walked for the line in the user's state — that is the default and the goal. Pass it only when the user asks to limit the walk: most carriers with an estimate have no walk, so a shortlist copied from quote_insurance results is refused with ``carriers_not_walked`` naming the ``walkable`` set to choose from. Those carriers keep their estimates; the live run adds real quotes from every walked carrier. ``lines`` names WHICH line to walk, exactly one per call (a fan-out drives one form family): ``{"auto": {...the ask...}}``, ``{"home": null}``, or ``{"renters": {"coverage_c": 30000, "coverage_e": 100000, "coverage_f": 1000, "deductible": 500}}``. An AUTO walk's ask is REQUIRED — the limits and deductibles the agents ask the carriers for, as actual numbers (`bi` "100/300", `pd` 100, `coll_deductible` 500, `comp_deductible` 500, the same four axes as quote_insurance); without it the tool answers with the selection-required message; ask the user, then call again. A HOME walk takes NO ask — the carrier's own form prices its package (dwelling amount from its replacement-cost estimate) and the agents report what it chose. A RENTERS walk requires its four axes as actual dollars — ``coverage_c`` (personal-property/contents), ``coverage_e`` (personal liability), ``coverage_f`` (guest medical) and ``deductible`` — the agents type the user's numbers on the form instead of accepting its defaults, and Foresee never invents them. Quotes come back with evidence. ``quote.premium`` is VERBATIM as the carrier's page printed it, and ``term_months`` says what it covers — a 6-month figure is not a monthly one. When term_months is known, present the monthly equivalent (premium ÷ term_months) … [2972 more characters not shown]

    Annotations the server declares

    • title: Live carrier quotes
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
Changes things 1Claude Code: ask
  • quote_insurancePurpose: generate instant, itemized quote estimates from the carriers Foresee supports, across the lines and states Foresee currently serves, in one call — the LIVE TODAY line at t…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 description is 9,038 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...wer; live quotes are the follow-up. LIVE TODAY: Foresee quotes auto in CA today."

      What this check looks for
    Description, as the server wrote it
    Purpose: generate instant, itemized quote estimates from the carriers Foresee supports, across the lines and states Foresee currently serves, in one call — the LIVE TODAY line at the end of this description names today's set. `lines` is REQUIRED and is ONE map: each key names a line to price (e.g. "auto", "renters", "home" — plain words are fine), each value is that line's coverage ask as actual numbers. A line Foresee doesn't quote in the user's state comes back under `skipped`: `lines` names each one and `message` is one sentence, written to be relayed to the user as-is, naming what Foresee does quote in that state. For auto the ask has four axes — `bi` (bodily-injury liability, per-person/ per-accident in $000s, e.g. "100/300"), `pd` (property-damage liability in $000s, e.g. 100), `coll_deductible` (collision deductible in dollars, e.g. 500) and `comp_deductible` (comprehensive deductible in dollars, e.g. 500); `um` and `medpay` are optional. A renters ask has four axes — `coverage_c` (personal-property/contents limit in dollars, e.g. 30000), `coverage_e` (personal liability in dollars, e.g. 100000), `coverage_f` (guest medical in dollars, e.g. 1000) and `deductible` (all-perils, in dollars, e.g. 500); `coverage_d` is optional. A home ask: `coverage_a` (the dwelling's replacement cost in dollars), `coverage_e` (e.g. 300000), `coverage_f` (e.g. 1000) and `aop_deductible` (all-other-perils deductible in dollars, e.g. 1000). There are no named coverage levels: pass exact numbers, the same ask in every state. An omitted OPTIONAL axis (`um`, `medpay`, `coverage_d`) keeps each carrier's own default — the quote's per-coverage lines show what was rated. Where the user's state puts more on every auto policy (its personal injury protection, a lawsuit option) and the ask doesn't name it, the quote prices the state's own and says so. Each line's `state_notes` is what the user's state means for these quotes — that, its legal minimum, the facts its law bars insurers from pricing on, a carrier that doesn't sell there — each note's `text` written to be relayed. Any numbers at or above the state's legal minimum work as the ask (an auto `bi`/`pd` below it prices nothing — no carrier may sell that policy — and comes back under `coverage_required` naming the minimum); each carrier's `price_ladder` prices every other rung, so a starting selection is easy to refine after the fact. An incomplete ask on a live line prices nothing and answers with `coverage_required` naming that line's own axes; an axis supplied with a value no carrier offers (`bi` "banana", a negative deductible) is refused the same way, naming the bad value and the format the axis takes. Each supported carrier is priced at the selection given; a carrier that doesn't offer an asked rung is priced at its nearest offered one and says so: its entry carries `rated_vs_asked` (per axis: `asked`, `rated`, and `coverage` "less"/"more" than asked; the dense text puts it on the `C` row as `rated`). That price is NOT like-for-like — state the rated limits next to it every time you show it (e.g. "$255/mo — 30/60 BI / $25k PD, the most this carrier offers, not the 100/300 / $100k you asked for"), and never let it headline or anchor a cheapest/spread claim without saying so. A carrier without a price appears in `failures`, on every line it was asked on — a carrier never silently vanishes from a line's results. Each entry's `by` says whose answer it is: `carrier` is the carrier's own (it doesn't sell the line in the state, isn't taking new customers, only quotes military families) — relay its `error` as written; `foresee` means Foresee couldn't get that quote — say exactly that, and never guess or add why. Priced results come back per line under `by_line`. Profile requirements: ZIP code, age (or dob) and — for auto — each vehicle's year/make/model are REQUIRED; they have no server-side fallback. A missing or mistyped one errors at the schema with guidance; a value that fits the schema but cannot rate ("not-a-zip", a negative age) comes back in `profile_required` naming it, with guidance on what the field takes. Use the profile schema's exact field names: a key the schema doesn't name is carried but never rated. A complete call — a 25-year-old in Oakland with a 2021 Civic, a January 2025 speeding ticket and a 2023 at-fault accident, asking for 100/300 BI, $100k PD and $500 collision/comprehensive deductibles: {"profile": {"zip_code": "94621", "age": 25, "auto": {"drivers": [{"violations": [{"on": "2025-01", "kind": "speeding"}], "accidents": [{"on": "2023-06-15", "at_fault": true, "amount": 4200}]}], "vehicles": [{"year": 2021, "make": "Honda", "model": "Civic"}]}}, "lines": {"auto": {"bi": "100/300", "pd": 100, "coll_deductible": 500, "comp_deductible": 500}}} Every violation needs `kind` and `on`, every accident `on`; an incomplete entry is refused naming its path, never assumed away. Each carrier returns a **point estimate** (`monthly`) plus a `confidence_interval` that reflects only what's genuinely unresolvable (irreducible), NOT missing profile fields. A field the caller omits is filled with ONE declared value and reported in `assumptions` / `tighten_by` (the reducible "tell us X and we sharpen" gap) — the response is built to be presented early and refined, never widened into a vague range. Each entry's `field` is the exact profile path to send the user's real answer under (e.g. `auto.drivers[].violations`), and `tighten_by` lists those same paths. The one exception is `incident_details`: it is answered by completing the incident entries already sent (dates, fault, BI split), not under a fresh key. Each carrier's `quote` carries every s… [3038 more characters not shown]

    Annotations the server declares

    • title: Instant insurance quote estimates
    • 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.

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:58 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
2
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 2 tools that change things (1 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agents.go-foresee.com/mcp: tools/list returned 2 tools to an anonymous client, including live_carrier_quotes (destructive), quote_insurance (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 info
  • The description is 9,038 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...wer; live quotes are the follow-up. LIVE TODAY: Foresee quotes auto in CA today."

    What this check looks for
  • The description is 8,972 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...is used for (property.occupancy); how many people live there (property.household)"

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 4.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http foresee https://agents.go-foresee.com/mcp
claude mcp add --transport http foresee https://agents.go-foresee.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": [],
    "ask": [
      "mcp__foresee__quote_insurance"
    ],
    "deny": [
      "mcp__foresee__live_carrier_quotes"
    ]
  }
}

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 foresee. Review it before you use it.

Capability tags behind 1 rule
  • mcp__foresee__live_carrier_quotes 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/io.github.Foresee-Tech/foresee/verify?hash=05c7e7e7679def8d9e4d754437e015d7cc6641f1a189ad1fa2da3e0e34ab0e96" | jq -e '.changed == false'

Pinned hash 05c7e7e7679d, from Nov 15, 2026, 20:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.Foresee-Tech/foresee/changes.xml

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

Badge

Anlyon Radar badge for io.github.Foresee-Tech/foresee
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Foresee-Tech/foresee.svg)](https://radar.anlyon.com/servers/io.github.Foresee-Tech/foresee)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:16 UTC.

Foresee MCP server: questions and answers

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

Is the Foresee MCP server safe?

No scan can promise that. What its definitions show: 2 tools, 2 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 Foresee MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: live_carrier_quotes.

Can the Foresee 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 Foresee MCP server have?

2 tools: 1 destructive, 1 write. live_carrier_quotes and quote_insurance.

Does the Foresee MCP server need sign-in or OAuth?

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

Does the Foresee MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Foresee MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.