{"data":{"name":"io.github.Foresee-Tech/foresee","title":"Foresee","description":"Let AI assistants shop for home and auto insurance: compare quote estimates across every carrier.","version":"4.0.0","websiteUrl":"https://go-foresee.com","repositoryUrl":"https://github.com/Foresee-Tech/foresee","remotes":[{"url":"https://agents.go-foresee.com/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-10-02T02:09:45.845Z","updatedAt":"2026-10-02T02:09:45.845Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"Foresee","source":"official-registry","sourceId":"io.github.Foresee-Tech/foresee","updatedAt":"2026-10-02T02:09:45.845Z","confidence":100,"websiteUrl":"https://go-foresee.com","description":"Let AI assistants shop for home and auto insurance: compare quote estimates across every carrier.","verification":"official","repositoryUrl":"https://github.com/Foresee-Tech/foresee"}],"toolIndex":{"tools":[{"serverName":"io.github.Foresee-Tech/foresee","endpointFingerprint":"87ec36de830549ecc392fc6b1f1fa3f0c7321fa837fedf71947154ec1d0f3af7","name":"live_carrier_quotes","title":"Live carrier quotes","description":"Purpose: confirm quote estimates on the carriers' own quote sites, via Foresee agents completing their real quote flows.\n\n        IDEMPOTENT, keyed on the profile: the first call commissions the\n        walks; calling again with the same profile collects progress and\n        results instead of re-submitting anything — whatever the ask. A\n        profile that has already been walked returns those results (the\n        carriers are never asked twice): the envelope's\n        ``coverage_selection`` names the ask the walk typed, and each quote\n        carries the carrier's other recorded coverage options as\n        ``variants``, so a new ask reads the same run. So call once to\n        start, then re-call after a few minutes to collect; agents still\n        working report their stage.\n\n        Ask ONCE, before the first call: the consent disclosure below, the\n        identity fields, and the questions listed at the end of this\n        description under EVERY LINE and under the line being walked — all\n        in one message, so the first commissioning call walks every carrier. A call made before\n        consent submits nothing and answers ``authorization_required`` with\n        the profile's ``needs``, for when you have not asked yet.\n\n        No sign-in is required. The one hard requirement is the user's own\n        consent, captured in-band: BEFORE the commissioning call, you MUST\n        tell the user, plainly: Foresee will submit their details to the\n        named carriers; the carriers may obtain their credit-based insurance\n        score (a soft pull, with no impact on your credit score); and the\n        carriers may contact them by email or phone. Then get their explicit\n        go-ahead and pass their affirmation VERBATIM as ``user_authorization``\n        (e.g. \"yes, go ahead\"). The affirmation is stored as the durable\n        consent record for the dispatch; without one the call is refused with\n        ``authorization_required``. Foresee only collects quotes; it does\n        not take payment or bind insurance.\n\n        Collect the ``identity`` fields in chat. Nothing is filled in from\n        anywhere else: what the walks type is what the call states.\n\n        A ``missing_facts`` response is normal: carrier forms insist on facts\n        (body style, purchase date, age first licensed…) that Foresee will not\n        invent. Each ``needs`` entry carries the carrier (``scope``), the\n        facts in the walk's own words (``need``), and ``fields[]`` — per\n        fact, the ``ask`` beside the exact schema path to pass the answer\n        under (``field``, e.g. ``auto.vehicles[].purchase_date``;\n        ``identity.…`` paths go on ``identity``). Ask the user for exactly\n        those facts, then call again with the answers merged in at those\n        paths. A fact with no ``field`` has no profile home yet — relay\n        that carrier's ask as unavailable rather than guessing a key. While\n        any carrier waits on a fact the user can answer, nothing is\n        submitted: the carriers already able to go are listed under\n        ``ready`` and held, so every carrier is walked together. Only when\n        the user cannot or will not answer, re-call with\n        ``dispatch_ready_only=true`` to walk the ready ones now; that\n        receipt is PARTIAL — follow its ``recover`` block: re-call with the\n        new facts merged AND ``carriers`` set to exactly\n        ``recover.carriers`` — a changed profile is a new dispatch, and an\n        unscoped re-call would re-submit the already-walked carriers too.\n\n        Unasserted MINOR facts are not asked: a form field that is really a\n        claim nobody made (an anti-theft device, a defensive-driving course,\n        a licence held abroad) is answered with the declared no-claim value —\n        never a discount claim — and every one comes back in ``assumptions``\n        (``field`` + the ``assumed`` value submitted). Relay them with the\n        results; if the user corrects one, re-call with the real value at\n        that path.\n\n        ``carriers``: OMIT it to walk every carrier walked for the line in\n        the user's state — that is the default and the goal. Pass it only\n        when the user asks to limit the walk: most carriers with an estimate\n        have no walk, so a shortlist copied from quote_insurance results is\n        refused with ``carriers_not_walked`` naming the ``walkable`` set to\n        choose from. Those\n        carriers keep their estimates; the live run adds real quotes from\n        every walked carrier.\n\n        ``lines`` names WHICH line to walk, exactly one per call (a fan-out\n        drives one form family): ``{\"auto\": {...the ask...}}``,\n        ``{\"home\": null}``, or ``{\"renters\": {\"coverage_c\": 30000,\n        \"coverage_e\": 100000, \"coverage_f\": 1000, \"deductible\": 500}}``. An\n        AUTO walk's ask is REQUIRED — the limits and deductibles the agents\n        ask the carriers for, as actual numbers (`bi` \"100/300\", `pd` 100,\n        `coll_deductible` 500, `comp_deductible` 500, the same four axes as\n        quote_insurance); without it the tool answers with the\n        selection-required message; ask the user, then call again. A HOME\n        walk takes NO ask — the carrier's own form prices its package\n        (dwelling amount from its replacement-cost estimate) and the agents\n        report what it chose. A RENTERS walk requires its four axes as\n        actual dollars — ``coverage_c`` (personal-property/contents),\n        ``coverage_e`` (personal liability), ``coverage_f`` (guest medical)\n        and ``deductible`` — the agents type the user's numbers on the form\n        instead of accepting its defaults, and Foresee never invents them.\n\n        Quotes come back with evidence. ``quote.premium`` is VERBATIM as\n        the carrier's page printed it, and ``term_months`` says what it\n        covers — a 6-month figure is not a monthly one. When term_months\n        is known, present the monthly equivalent (premium ÷ term_months)\n        so carriers compare on one basis, the page's own figure beside it;\n        without it, relay the printed premium and say the monthly\n        equivalent is unknown. A carrier may\n        also decline the risk — a real answer to relay, not an error. Every\n        carrier without a quote says why in ``detail``: ``declined`` is the\n        carrier's own answer; ``missing_facts`` lists under ``fields`` (each\n        an ``ask`` and its ``field`` path) what its form wanted — ask the\n        user, then re-call with the answers merged and ``carriers`` set to\n        that carrier; ``failed`` and ``not_quoted`` mean Foresee couldn't get\n        that quote — say so, never that the carrier turned the user down.\n        ``not_dispatched`` names each carrier with an instant estimate that\n        this run won't quote live, with a ``by`` and a ``detail``: ``by:\n        carrier`` is the carrier's own answer (e.g. it doesn't quote that\n        line online there), to relay as written; ``by: foresee`` means\n        Foresee couldn't get a live quote — say exactly that, and never\n        guess or add why. ``skipped`` names carriers whose form needs facts\n        the profile lacks. A carrier never silently vanishes.\n\nWhat the carriers' forms ask. In ONE message, together with the consent disclosure and BEFORE the first call, ask the user the EVERY LINE questions plus the questions for each line they want priced, then omit `carriers` to walk every carrier in the user's state. Each fact names the path its answer goes under.\n\nEVERY LINE:\n- identity: legal name, date of birth, street address, email and phone (identity)\n\nAUTO ONLY:\n- household: gender (gender); marital status (marital_status); the spouse of a married applicant (auto.drivers[])\n- work: occupation (occupation)\n- residence: whether the home is owned or rented (home_ownership_status); how long at this address (resident_since)\n- each car: whether the vehicle is owned, financed or leased (auto.vehicles[].ownership); when the vehicle","inputSchema":null,"annotations":{"title":"Live carrier quotes","readOnlyHint":false,"destructiveHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"cf453f1416e1dfe04da0fbca30b41afe8b45210a7520ccdfe8d06a6e4f6bf8ba","schemaStatus":"too-large","origin":"official-registry","observedAt":"2026-11-19T12:46:52.908Z","metadataTrust":"untrusted"},{"serverName":"io.github.Foresee-Tech/foresee","endpointFingerprint":"87ec36de830549ecc392fc6b1f1fa3f0c7321fa837fedf71947154ec1d0f3af7","name":"quote_insurance","title":"Instant insurance quote estimates","description":"Purpose: generate instant, itemized quote estimates from the carriers\n    Foresee supports, across the lines and states Foresee currently serves,\n    in one call — the LIVE TODAY line at the end of this description names\n    today's set.\n\n    `lines` is REQUIRED and is ONE map: each key names a line to price (e.g.\n    \"auto\", \"renters\", \"home\" — plain words are fine), each value is that\n    line's coverage ask as actual numbers. A line Foresee doesn't quote in\n    the user's state comes back under `skipped`: `lines` names each one and\n    `message` is one sentence, written to be relayed to the user as-is,\n    naming what Foresee does quote in that state. For auto\n    the ask has four axes — `bi` (bodily-injury liability, per-person/\n    per-accident in $000s, e.g. \"100/300\"), `pd` (property-damage liability in\n    $000s, e.g. 100), `coll_deductible` (collision deductible in dollars, e.g.\n    500) and `comp_deductible` (comprehensive deductible in dollars, e.g.\n    500); `um` and `medpay` are optional. A renters ask has four axes —\n    `coverage_c` (personal-property/contents limit in dollars, e.g. 30000),\n    `coverage_e` (personal liability in dollars, e.g. 100000), `coverage_f`\n    (guest medical in dollars, e.g. 1000) and `deductible` (all-perils, in\n    dollars, e.g. 500); `coverage_d` is optional. A home ask: `coverage_a`\n    (the dwelling's replacement cost in dollars), `coverage_e` (e.g. 300000),\n    `coverage_f` (e.g. 1000) and `aop_deductible` (all-other-perils\n    deductible in dollars, e.g. 1000). There are no named coverage levels:\n    pass exact numbers, the same ask in every state. An omitted OPTIONAL\n    axis (`um`, `medpay`, `coverage_d`) keeps each carrier's own\n    default — the quote's per-coverage lines show what was rated. Where the\n    user's state puts more on every auto policy (its personal injury\n    protection, a lawsuit option) and the ask doesn't name it, the quote\n    prices the state's own and says so. Each line's `state_notes` is what\n    the user's state means for these quotes — that, its legal minimum, the\n    facts its law bars insurers from pricing on, a carrier that doesn't sell\n    there — each note's `text` written to be relayed. Any\n    numbers at or above the state's legal minimum work as the ask (an auto\n    `bi`/`pd` below it prices nothing — no carrier may sell that policy — and\n    comes back under `coverage_required` naming the minimum); each carrier's\n    `price_ladder` prices every other rung, so a starting\n    selection is easy to refine after the fact. An incomplete ask on a\n    live line prices nothing and answers with `coverage_required` naming that\n    line's own axes; an axis supplied with a value no carrier offers (`bi`\n    \"banana\", a negative deductible) is refused the same way, naming the bad\n    value and the format the axis takes. Each supported carrier is priced at\n    the selection given; a carrier that doesn't offer an asked rung is priced\n    at its nearest offered one and says so: its entry carries\n    `rated_vs_asked` (per axis: `asked`, `rated`, and `coverage` \"less\"/\"more\"\n    than asked; the dense text puts it on the `C` row as `rated`). That price is NOT\n    like-for-like — state the rated limits next to it every time you show it\n    (e.g. \"$255/mo — 30/60 BI / $25k PD, the most this carrier offers, not\n    the 100/300 / $100k you asked for\"), and never let it headline or anchor\n    a cheapest/spread claim without saying so. A carrier without a price\n    appears in `failures`, on every line it was asked on — a carrier never\n    silently vanishes from a line's results. Each entry's `by` says whose\n    answer it is: `carrier` is the carrier's own (it doesn't sell the line\n    in the state, isn't taking new customers, only quotes military families)\n    — relay its `error` as written; `foresee` means Foresee couldn't get\n    that quote — say exactly that, and never guess or add why. Priced\n    results come back per line under `by_line`.\n\n    Profile requirements: ZIP code, age (or dob) and — for auto — each\n    vehicle's year/make/model are REQUIRED; they have no server-side\n    fallback. A missing or mistyped one errors at the schema with guidance;\n    a value that fits the schema but cannot rate (\"not-a-zip\", a negative\n    age) comes back in `profile_required` naming it, with guidance on what\n    the field takes. Use the profile schema's exact field names: a key the\n    schema doesn't name is carried but never rated. A complete call — a\n    25-year-old in Oakland with a 2021 Civic, a January 2025 speeding ticket\n    and a 2023 at-fault accident, asking for 100/300 BI, $100k PD and $500\n    collision/comprehensive deductibles:\n    {\"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}}}\n    Every violation needs `kind` and `on`, every accident `on`; an\n    incomplete entry is refused naming its path, never assumed away.\n\n    Each carrier returns a **point estimate**\n    (`monthly`) plus a `confidence_interval` that reflects only what's genuinely\n    unresolvable (irreducible), NOT missing profile fields. A field the caller\n    omits is filled with ONE declared value and reported in `assumptions` /\n    `tighten_by` (the reducible \"tell us X and we sharpen\" gap) — the response\n    is built to be presented early and refined, never widened into\n    a vague range. Each entry's `field` is the exact profile path to send\n    the user's real answer under (e.g. `auto.drivers[].violations`), and\n    `tighten_by` lists those same paths. The one exception is\n    `incident_details`: it is answered by completing the incident entries\n    already sent (dates, fault, BI split), not under a fresh key.\n\n    Each carrier's `quote` carries every sub-coverage line (BI/PD/collision/\n    comprehensive/UM…) with its monthly price, at the selection you passed (echoed\n    as `coverage_selection`). Most carriers also carry a `price_ladder`: for each\n    coverage lever of the line (auto: BI limit, PD limit, collision/comprehensive\n    deductible; renters: deductible and the C/E/F limits; home: AOP deductible\n    and the A/E/F limits) the exact\n    price at every rung, one lever moved at a time with everything else\n    held at the user's selection — the ladder is anchored at the selection you\n    passed, so its `anchor.monthly` is the carrier's `monthly`. It answers\n    limit/deductible what-ifs with real marginal prices.\n    Every ladder number IS an exact re-rate; a combined change or an unlisted\n    rung has no derivable price (rating is not linear), so those price only\n    through a re-call with the new `coverage_selection`. A profile what-if\n    (a cleaner record, another vehicle, a different ZIP) prices the same way:\n    re-call with the changed profile.\n    \n\nRESULT FORMAT: compact machine text on `dense`, one section per line. Each section opens Q <state> <line> sel=<the coverage_selection priced, as JSON>. state_notes: <sentences> is the line's `state_notes`, to relay. assumptions:, tighten_by:, input_flags: and not_rated: carry those fields; each entry's `field` (and each tighten_by item) is the profile path to send the user's answer under, and `incident_details` is answered by completing the incident entries already sent. not_priced: <carrier>,…:<error> ; … is the line's `failures`, grouped by their `error` sentence. skipped <line>,…: <message> names the lines not quoted in this state. Row types — C: carrier|entity|monthly|ci lo-hi, then |rated <axis>=<rung>(asked <X>,less|more);… when the price is for a rung other than the ask (`rated_vs_asked`). W: a warning on the carrier above. L: monthly $ per coverage line (already monthly, every carrier), under codes that mean the same coverage at every carrier: BI ","inputSchema":null,"annotations":{"title":"Instant insurance quote estimates","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"1a3b1cf55f5e8cbf1355f84e8a3c3d767cfa193ab09faf88276c24918da84659","schemaStatus":"too-large","origin":"official-registry","observedAt":"2026-11-19T12:46:52.908Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"87ec36de830549ecc392fc6b1f1fa3f0c7321fa837fedf71947154ec1d0f3af7","protocol":"streamable-http","status":"indexed","toolCount":2,"observedAt":"2026-11-19T12:46:52.908Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.github.Foresee-Tech/foresee":{"url":"https://agents.go-foresee.com/mcp"}}},"Cursor":{"mcpServers":{"io.github.Foresee-Tech/foresee":{"url":"https://agents.go-foresee.com/mcp"}}},"VS Code":{"servers":{"io.github.Foresee-Tech/foresee":{"type":"http","url":"https://agents.go-foresee.com/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://agents.go-foresee.com/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.github.Foresee-Tech%2Fforesee","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.github.Foresee-Tech%2Fforesee","name":"io.github.Foresee-Tech/foresee","description":"Let AI assistants shop for home and auto insurance: compare quote estimates across every carrier.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://agents.go-foresee.com/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://go-foresee.com","repositoryUrl":"https://github.com/Foresee-Tech/foresee","version":"4.0.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.github.Foresee-Tech/foresee","status":"online","lastCheckedAt":"2026-11-20T04:16:43.670Z","lastSuccessfulCheck":"2026-11-20T04:16:43.670Z","latencyMs":73,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T04:16:43.670Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T04:16:43.670Z"},"security":null,"timestamps":{"createdAt":"2026-10-02T02:09:45.845Z","updatedAt":"2026-10-02T02:09:45.845Z","observedAt":"2026-11-20T04:16:43.670Z"},"compatibility":{"serverVersion":"4.0.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}