# Census EV (remote · censusev.com)

Every electric car for sale in the US, new and used. Search listings, look up a VIN, list models.

- Trust score: 77/100 (medium)
- Change this week: −1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `censusev.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-censusev-census/api-mcp.md), [page](https://verifymcp.io/servers/com-censusev-census/api-mcp)

## Channel facts

- Endpoint: `https://censusev.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2222 tokens (~317/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 73/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Census EV MCP server?

Census EV is a hosted endpoint at https://censusev.com/api/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.

### Claude

```bash
claude mcp add --transport http com-censusev-census 'https://censusev.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-censusev-census": {
      "url": "https://censusev.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-censusev-census": {
      "type": "http",
      "url": "https://censusev.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-censusev-census]
url = "https://censusev.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-censusev-census": {
      "type": "remote",
      "url": "https://censusev.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-censusev-census --url 'https://censusev.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-censusev-census:
    url: "https://censusev.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-censusev-census": {
      "Transport": "http",
      "Url": "https://censusev.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-censusev-census -t streamable-http -u 'https://censusev.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-censusev-census": {
      "type": "http",
      "url": "https://censusev.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 77, +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.

### 2026-11-19 (score 76, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_listing” rewrote its description, which is the text the model reads
- [security] Tool “search_listings” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 243 → 317
- [functional] Server version: 1.2.0 → 1.3.0
- [functional] New tool “compare_listings”
- [cosmetic] “search_listings” reworded the description of “detail”

### 2026-11-18 (score 75, −4)

- [security regression] Authorization: pass → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_listing” rewrote its description, which is the text the model reads
- [security] Tool “list_models” rewrote its description, which is the text the model reads
- [security] Tool “search_listings” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 760 → 1461
- [functional] The server now declares the “resources” capability
- [functional] First check of Capabilities: pass
- [functional] First check of Schema quality: 100
- [functional] New resource “cars”
- [functional] Server version: 1.1.0 → 1.2.0
- [functional] New tool “battery_warranty”
- [functional] New tool “market_snapshot”
- [cosmetic] “search_listings” added an optional parameter “detail”
- [cosmetic] “search_listings” reworded the description of “heat_pump”
- [cosmetic] “search_listings” reworded the description of “kind”

### 2026-11-16 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 77, +16)

- [security improvement] Authorization: unverified → pass
- [functional regression] Schema quality: 207 → 253
- [functional improvement] Tool coverage: 70% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0 → 1.1.0
- [cosmetic] “list_models” reworded the description of “make”
- [cosmetic] “search_listings” reworded the description of “heat_pump”
- [cosmetic] “search_listings” reworded the description of “limit”
- [cosmetic] “search_listings” reworded the description of “mileage_max”
- [cosmetic] “search_listings” reworded the description of “offset”
- [cosmetic] “search_listings” reworded the description of “price_max”
- [cosmetic] “search_listings” reworded the description of “price_min”
- [cosmetic] “search_listings” reworded the description of “radius_mi”
- [cosmetic] “search_listings” reworded the description of “sort”
- [cosmetic] “search_listings” reworded the description of “year_max”
- [cosmetic] “search_listings” reworded the description of “year_min”
- [cosmetic] Tool “get_listing” changed its title: Get one listing by VIN
- [cosmetic] Tool “list_models” changed its title: List makes and models
- [cosmetic] Tool “search_listings” changed its title: Search EV listings

### 2026-11-11 (score 61)

First indexed and scored.

## MCP tools (6)

### `search_listings` (~986 tokens)

Search EV listings

Search every electric and plug-in hybrid vehicle listed for sale in the United States that Census tracks — new, used and certified, from dealers' own sites and manufacturer inventory. Returns matching listings with price, mileage, location, the seller's name and website, a seller link that forwards through censusev.com to the dealer's own page for the car, and the EV facts the site stands behind (battery kWh, EPA range, charge port, heat pump, DC fast charging), each marked estimated when it is not the manufacturer's own figure. Also returns a breakdown of every matching car, not only the returned page: cars per model year, cars per trim (top 8, when every match is one model), and the lowest, median and highest asking price. Each record carries last_seen, the day the car was last seen for sale. asking_vs_similar ("below", "typical" or "above") compares the asking price with similar cars on Census EV: the same version and model year within 40,000 miles, adjusted for mileage, counting cars listed now and cars no longer listed in the last 30 days at their last asking price. It compares asking prices and is not an appraisal. "below" and "above" need a gap of at least $1,000 that is also wider than the usual spread of asking prices for that version: for most cars about 3 to 7% over for "above" and about 5 to 9% under for "below", more where few similar cars are known, and "below" must still hold with any one similar car left out. Otherwise it is "typical". Absent when the car could not be compared: new or under 2,000 miles, no asking price or mileage, a disclosed buyback or branded title, fewer than 3 similar cars, similar cars that are not all one version, or an asking price so far under them that the gap is more than 30% of it. Inventory is as of the `as_of` timestamp in the result.

Input parameters:

- `body` (string): Comma-separated: "suv", "sedan", "truck", "van", "hatchback".
- `charge_port` (string): Comma-separated: "NACS", "CCS1", "CHAdeMO".
- `condition` (string): Comma-separated: "new", "used", "certified".
- `detail` (string): How much of each record to return. Default "compact", which leaves out id (the VIN in lower case), image_url, location.zip, location.lat, location.lng, previous_price_usd, price_changed_at, listed_on…
- `drive` (string): Comma-separated: "AWD", "RWD", "FWD".
- `heat_pump` (string): Only cars known to have (yes) or not have (no) a heat pump. Cars where it is not established match neither, and are counted in not_established.heat_pump.
- `kind` (string): Battery-electric or plug-in hybrid. A car whose kind is not established matches neither; the result counts those in not_established.kind.
- `kwh_min` (integer): Minimum battery capacity in kWh.
- `limit` (integer): Results to return, 1 to 100. Default 25.
- `make` (string): Make, e.g. "Tesla", "Hyundai".
- `mileage_max` (integer): Maximum odometer reading in miles. Cars with no stated mileage are excluded when this is given.
- `model` (string): Model, e.g. "Model Y", "Ioniq 5". Punctuation and spacing are ignored.
- `offset` (integer): Results to skip, for paging. Default 0.
- `price_max` (integer): Maximum asking price in USD. Cars with no real asking price are excluded when a price bound is given.
- `price_min` (integer): Minimum asking price in USD.
- `radius_mi` (integer): Search radius around zip, in miles. Default 100.
- `range_min` (integer): Minimum EPA range in miles (electric-only for a plug-in hybrid).
- `sort` (string): Result order. distance needs a zip. Default: distance when a zip is given, otherwise price_asc.
- `state` (string): Comma-separated two-letter state codes, e.g. "CA,OR".
- `year_max` (integer): Latest model year to include.
- `year_min` (integer): Earliest model year to include, e.g. 2022.
- `zip` (string): 5-digit US ZIP; results are limited to radius_mi of it and sorted by distance unless sort is given.

### `get_listing` (~366 tokens)

Get one listing by VIN

One listing by VIN: every field of the search record plus its asking-price history on this seller, and battery_warranty, this car's high-voltage battery warranty as its Census EV page gives it: status (for example "Expired" or "In force · 38,200 mi or 3+ yr left"), in_force, and estimated when the term is not the manufacturer's own figure. battery_warranty is absent where the page gives no verdict for the car. asking_vs_similar ("below", "typical" or "above") compares the asking price with similar cars on Census EV: the same version and model year within 40,000 miles, adjusted for mileage, counting cars listed now and cars no longer listed in the last 30 days at their last asking price. It compares asking prices and is not an appraisal. "below" and "above" need a gap of at least $1,000 that is also wider than the usual spread of asking prices for that version: for most cars about 3 to 7% over for "above" and about 5 to 9% under for "below", more where few similar cars are known, and "below" must still hold with any one similar car left out. Otherwise it is "typical". Absent when the car could not be compared: new or under 2,000 miles, no asking price or mileage, a disclosed buyback or branded title, fewer than 3 similar cars, similar cars that are not all one version, or an asking price so far under them that the gap is more than 30% of it. The seller link forwards through censusev.com to the dealer's own page for the car.

Input parameters:

- `vin` (string, required): 17-character VIN.

### `compare_listings` (~93 tokens)

Compare listings

Two to five listings by VIN, side by side: for each, its full record with its asking-price history, battery_warranty and asking_vs_similar where they exist. VINs with no live listing are returned in not_found, and any that could not be read in time in unavailable. Results are as of the `as_of` timestamp.

Input parameters:

- `vins` (array, required): 2 to 5 VINs.

### `list_models` (~55 tokens)

List makes and models

Every make and model with live listings, with counts, in the exact spellings the listing search accepts.

Input parameters:

- `make` (string): Limit the list to one make, e.g. "Kia". Omit for every make.

### `battery_warranty` (~240 tokens)

Battery warranty by model year

The manufacturer's high-voltage battery warranty for a make, model and model year, as the Census EV warranty checker gives it: the term in years and miles (with the trims each term covers where the terms differ by trim), whether it is still in force at an odometer reading where that can be established, the battery capacity the warranty guarantees, and whether coverage transfers to a later owner. A term is marked estimated when it is not the manufacturer's own figure. Returns established: false and no term when the versions of that model year disagree or have not been researched. Includes the model's battery-warranty fact sheet on censusev.com where one exists.

Input parameters:

- `make` (string, required): Make, e.g. "Kia". Case, spacing and common short forms ("Chevy", "VW") are accepted.
- `mileage` (integer): Odometer reading in miles. With it, status says whether the warranty is in force where that can be established.
- `model` (string, required): Model, e.g. "EV6". Punctuation and spacing are ignored.
- `year` (integer, required): Model year, e.g. 2023.

### `market_snapshot` (~181 tokens)

Model market snapshot

Figures for one model as Census EV publishes them on its model page and its market page: how many are for sale and as of when; cars for sale and median asking price by model year; the mileage-adjusted asking price of a used one at 40,000 miles with its 30- and 60-day change; and the share of used ones no longer listed 30 days after they appeared, with the window it was measured over. A figure is null or absent where the site prints none, because too few cars stand behind it or it could not be read.

Input parameters:

- `make` (string, required): Make, e.g. "Hyundai". Case, spacing and common short forms ("Chevy", "VW") are accepted.
- `model` (string, required): Model, e.g. "Ioniq 5". Punctuation and spacing are ignored.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-censusev-census/api-mcp#diagnostics

## Score history

- 2026-11-21: 77
- 2026-11-20: 76
- 2026-11-19: 76
- 2026-11-18: 75
- 2026-11-17: 79
- 2026-11-16: 79
- 2026-11-15: 78
- 2026-11-14: 78
- 2026-11-13: 78
- 2026-11-12: 77
- 2026-11-11: 61

## Common questions

### What is the Census EV MCP server?

Census EV is an MCP server listed in the public MCP registry as com.censusev/census. Every electric car for sale in the US, new and used. Search listings, look up a VIN, list models. This page covers its hosted endpoint (https://censusev.com/api/mcp).

### Is the Census EV MCP server safe to use?

Census EV scores 77 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 Census EV MCP server expose?

Census EV exposes 6 tools: search_listings, get_listing, compare_listings, list_models, battery_warranty, market_snapshot. Their descriptions and schemas cost roughly 1,921 tokens of context every time the server is loaded.

### Does the Census EV MCP server require authentication?

No. We connected to Census EV without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Census EV MCP server still maintained?

Census EV is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Census EV MCP server?

VerifyMCP ran 14 checks on Census EV, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://censusev.com/api/mcp
- Website: https://censusev.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-censusev-census/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-censusev-census/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-censusev-census/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-censusev-census/api-mcp
