Jerry Insurance
REMOTE · MCP.JERRY.AI
Compare US car, home and renters insurance quotes with Jerry. Sign-in required; buy in the app.
Available components
Last scanned (29 minutes ago)
Scores higher than 54% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security66
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 403, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability55
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 3721 tokens (~465/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 92% of tool parameters carry a description.Partial
- Structured output schemas are declared (13% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
- Stability: unverified → 0.03 ▲ functional
- 25 Oct 26 64
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://mcp.jerry.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.jerry.ai | CN=Amazon RSA 2048 M04,O=Amazon,C=US | 26 Sept 2026 | 11 Apr 2027 | RSA 2048 | SHA256-RSA | 1b2b80ed7ed53017a88e36f224e32c5 |
| SANs: *.jerry.ai, *.stage.jerry.ai, *.ing.getjerry.com, *.stage.getjerry.com, *.prod.getjerry.com, *.getjerry.com, *.prod.jerry.ai | ||||||
| CN=Amazon RSA 2048 M04,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 773124f2a952e3ed18a58bdb85d1bc0ce5f27 |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of mcp.jerry.ai. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 1814, 3799 | 8, 8 | Verified |
| jerry.ai. | present | 64251 | 13 | Verified |
| mcp.jerry.ai. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.jerry.ai/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.jerry.ai/mcp | Inconclusive | 403 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
jerry_get_account Account details ~41
Read the name, email and phone on the customer's Jerry account, and whether the phone is verified. It doesn't verify an email or change any insurance information.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | – | Customer account contact profile |
| message | string | – | – |
No examples provided.
jerry_get_quotes View quotes ~135
List every quote for a shopping intent, cheapest first by monthly price (in USD cents); each policy has a coverageSummary. Pass up to 4 bundleIds to also get their coverages, discounts and payment plans, for example to compare them. Prices are estimates until priceStatus is final. Declined quotes are left out and counted in declinedCount. It doesn't request quotes.
| Name | Type | Req | Description |
|---|---|---|---|
| bundleIds | array | – | Up to 4 bundle ids to return with coverages, discounts and payment plans. Omit to list every quote. |
| intentId | string | yes | The shopping intent id returned by an earlier shopping tool. |
No output schema declared.
No examples provided.
jerry_get_status Shopping status ~119
Read where the customer's insurance shopping stands: the stage, what the current goal still needs (by application path), a summary of the application, what Jerry found that isn't on the application yet (suggested) and, when a request is ready, the confirmation to show. It doesn't change anything.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | Include every typed application fact by application path, with sensitive values masked. |
| intentId | string | – | The shopping intent id returned by an earlier shopping tool. Omit it to read the customer's most recent open intent. |
No output schema declared.
No examples provided.
jerry_request_final_price Request final price ~158
Get the final price of the quote the customer chose. Call it first with bundleId only: that selects the quote and returns the status, which may list what the final price still needs, then a confirmation. After the customer says yes to that confirmation, call again with its token and the customer's exact reply. Nothing is requested unless requested comes back true.
| Name | Type | Req | Description |
|---|---|---|---|
| bundleId | string | yes | The bundleId of the chosen quote. |
| confirmation | object | – | Omit on the first call, which selects the quote and returns the confirmation to show. |
| idempotencyKey | string | yes | Unique key for safely retrying this customer action |
| intentId | string | yes | The shopping intent id returned by an earlier shopping tool. |
No output schema declared.
No examples provided.
jerry_request_quotes Request quotes ~123
Request quotes. Every request needs the confirmation from the status: show its summary, get the customer's explicit yes, then pass its token and their exact reply. Nothing is requested unless requested comes back true; reason says why not, and status is the intent after the call. On stale_confirmation the facts changed: show the new confirmation and ask again.
| Name | Type | Req | Description |
|---|---|---|---|
| confirmation | object | yes | – |
| idempotencyKey | string | yes | Unique key for safely retrying this customer action |
| intentId | string | yes | The shopping intent id returned by an earlier shopping tool. |
No output schema declared.
No examples provided.
jerry_start_shopping Start shopping ~212
Start shopping for the insurance products the customer asked for. If a shopping intent for exactly these products is already open, it resumes that one. Pass the main facts you already know in application, so the status asks only for the rest. application takes the main fields only: send any other fact with jerry_update_application right after. Returns the status, with rejected and clarify. When a fact comes from anything other than the customer, sources says where, and permission holds the customer's reply allowing it.
| Name | Type | Req | Description |
|---|---|---|---|
| application | object | – | The main facts the agent already knows, saved in the same call so the first status asks only for the rest. Send other facts with updateShoppingIntentApplication. |
| idempotencyKey | string | yes | Unique key for safely retrying this customer action |
| permission | object | – | Required once when sources include anything but customer. |
| policyTypes | array | yes | Products to shop for. |
| sources | array | – | Where these facts come from; defaults to ['customer']. |
No output schema declared.
No examples provided.
jerry_update_application Update application ~345
Save application facts the customer gave, in their own words. Every field is optional and merges into what's saved, so send only facts that are new or changed. - Items with an id update that driver, car or home; items without one are added. included puts an item on the quote or leaves it off. - Add a car by vin, by licensePlate and licensePlateState, or by year, make and model. Send year, make and model only when there's no VIN or plate, since those set them. A final price needs the VIN. - Answer any other requirement in answers, by its path. A fact that has its own field here comes back rejected as typed_field if it's sent in answers. - coverage and history.currentMonthlyPremiumCents are optional and never block quotes. Send them only when the customer asks for a coverage level or specific coverages, or says what they pay now. - Drivers and cars Jerry found are in the status's suggested list, each with an id that starts with suggested:. Once the customer confirms one, send that id in drivers or vehicles with included: true. Returns the status, with suggested. rejected lists values to correct with the customer, and clarify lists values to choose from. The rest of the write is saved either way.
| Name | Type | Req | Description |
|---|---|---|---|
| application | object | yes | – |
| idempotencyKey | string | yes | Unique key for safely retrying this customer action |
| intentId | string | yes | The shopping intent id returned by an earlier shopping tool. |
| permission | object | – | Required once when sources include anything but customer. |
| sources | array | – | Where these facts come from; defaults to ['customer']. |
No output schema declared.
No examples provided.
jerry_wait Wait for results ~179
Wait for quotes or a final price after requesting them. Returns as soon as they're ready, or after timeoutSeconds with the status so far; call again while they're still running. When quotes are ready, it returns the quote list too. A final price is ready once it's resolved. If a Jerry agent takes it over (manual) or it's taking longer than usual (delayed), the wait stops with that reason, and the status's nextStep says what happens next. Calling again on a delayed price keeps waiting.
| Name | Type | Req | Description |
|---|---|---|---|
| for | string | yes | quotes after jerry_request_quotes; final_price after jerry_request_final_price requested it. |
| intentId | string | yes | The shopping intent id returned by an earlier shopping tool. |
| timeoutSeconds | integer | – | Longest time to wait, in seconds; default 20, at most 20. |
No output schema declared.
No examples provided.
How do I install the Jerry Insurance MCP server?
Jerry Insurance is a hosted endpoint at https://mcp.jerry.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.jerry.ai
claude mcp add --transport http ai-jerry-insurance 'https://mcp.jerry.ai/mcp'
What is the Jerry Insurance MCP server?
Jerry Insurance is an MCP server listed in the public MCP registry as ai.jerry/insurance. Compare US car, home and renters insurance quotes with Jerry. Sign-in required; buy in the app. This page covers its hosted endpoint (https://mcp.jerry.ai/mcp).
Is the Jerry Insurance MCP server safe to use?
Jerry Insurance scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Jerry Insurance MCP server expose?
Jerry Insurance exposes 8 tools: jerry_get_account, jerry_start_shopping, jerry_update_application, jerry_request_quotes, jerry_request_final_price, and 3 more. Their descriptions and schemas cost roughly 1,312 tokens of context every time the server is loaded.
Does the Jerry Insurance MCP server require authentication?
No. We connected to Jerry Insurance without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Jerry Insurance MCP server still maintained?
Jerry Insurance is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.