CuffTracker
REMOTE · WWW.CUFFTRACKER.COM
Chicago and Milwaukee crime data: query incidents, stats, and map-linked MCP UI resources.
Available components
Last scanned (6 hours ago)
Scores higher than 66% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Maps and Location
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 Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability85
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1182 tokens (~98/item across 12 items; 5 tools + 7 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
- Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
- Supports UI / widget rendering.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 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 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 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 +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.
- 24 Oct 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “get_crime_stats” rewrote its description, which is the text the model reads security
- Tool “search_crimes” rewrote its description, which is the text the model reads security
- Tool “get_city_crimes” rewrote its description, which is the text the model reads security
- Schema quality: 59 → 98 ▼ functional
- New resource “Denver Crime Data” functional
- New resource “Minneapolis Crime Data” functional
- New resource “New York Crime Data” functional
- New tool “get_area_trends” functional
- New tool “resolve_place” functional
- “get_city_crimes” added an optional parameter “lon_min” cosmetic
- “get_city_crimes” added an optional parameter “place” cosmetic
- “get_city_crimes” added an optional parameter “lat_max” cosmetic
- “get_city_crimes” added an optional parameter “lat_min” cosmetic
- “get_city_crimes” added an optional parameter “lon_max” cosmetic
- “search_crimes” reworded the description of “city” cosmetic
- 22 Oct 26 +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.
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://www.cufftracker.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.cufftracker.com | CN=YR2,O=Let's Encrypt,C=US | 27 Sept 2026 | 26 Dec 2026 | RSA 2048 | SHA256-RSA | 53cf9828391c4c00ef1494c56e050171b95 |
| SANs: *.cufftracker.com, cufftracker.com | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.cufftracker.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| cufftracker.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
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 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.cufftracker.com/mcp | Verified | 200 | |
| http (plaintext) | http://www.cufftracker.com/mcp | HTTPS enforced | 308 | https://www.cufftracker.com/mcp |
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 →
get_area_trends ~219
Start here for any neighborhood or trend question. Pass city and place, such as Milwaukee and Harbor View. Returns counts by crime type versus the city, counts by month, noon-to-midnight share, top streets, and a few notable incidents. One call covers up to 450 days. A lat/lon box is optional. Do not download citywide incidents and filter them yourself.
| Name | Type | Req | Description |
|---|---|---|---|
| city | string | yes | City the area is in. |
| days | integer | – | Days ending at the newest incident in the city. Default 90. Use 400 for about 14 months. |
| lat_max | number | – | North edge of the box. Geographic filter. |
| lat_min | number | – | South edge of the box. Geographic filter. |
| lon_max | number | – | East edge of the box. Geographic filter. |
| lon_min | number | – | West edge of the box. Geographic filter. |
| place | string | – | Neighborhood or rough area, such as Harbor View or Logan Square. Omit if you pass a box. |
No output schema declared.
No examples provided.
get_city_crimes ~351
One page of individual incidents inside a lat/lon box. Counts, shares, months, and streets belong on get_area_trends. A window longer than 45 days without lat_min, lat_max, lon_min, and lon_max is refused. Chicago's portal withholds about the last seven days. New York publishes complaints after a quarter closes.
| Name | Type | Req | Description |
|---|---|---|---|
| city | string | – | City to query. |
| end_date | string | – | End date in YYYY-MM-DD format. |
| lat_max | number | – | North edge. Required geographic filter for a long window. |
| lat_min | number | – | South edge. Required geographic filter for a long window. |
| limit | integer | – | Max records to return (1-500). |
| location_descriptions | array | – | Filter by location descriptions (e.g., ['STREET', 'RESIDENCE']). Omit for all. |
| lon_max | number | – | East edge. Required geographic filter for a long window. |
| lon_min | number | – | West edge. Required geographic filter for a long window. |
| offset | integer | – | Records to skip for pagination. |
| place | string | – | Address text, such as a street name, matched against location, block, and community area. This is not a neighborhood boundary. Harbor View and other neighborhood names need the lat/lon box, or get_ar… |
| primary_types | array | – | Filter by crime types (e.g., ['THEFT', 'BATTERY', 'NARCOTICS']). Omit for all types. |
| search_text | string | – | Text search across primary_type and description fields. |
| start_date | string | – | Start date in YYYY-MM-DD format. |
No output schema declared.
No examples provided.
get_crime_stats ~77
Citywide counts, date range, and top crime types. There is no neighborhood or lat/lon filter. For a place, call get_area_trends.
| Name | Type | Req | Description |
|---|---|---|---|
| city | string | – | City to get stats for. Use 'all' for cross-city comparison. |
| top_n | integer | – | Number of top items to return. |
No output schema declared.
No examples provided.
resolve_place ~144
Return the lat/lon edges of a neighborhood or rough area. Call this only when you need those edges. For trends, call get_area_trends with the place name and skip this tool. The suggested query is a short incident list, not a trend summary.
| Name | Type | Req | Description |
|---|---|---|---|
| city | string | yes | City the place is in. |
| days | integer | – | Days for the suggested incident list. Omit for a short default. Year-long trend windows belong on get_area_trends. |
| place | string | yes | Neighborhood, street, borough, or a rough area such as downtown or north side. |
| primary_types | array | – | Optional crime types to carry into the suggested query. |
No output schema declared.
No examples provided.
search_crimes ~100
Text search of crime types and descriptions. There is no neighborhood box. A place name such as Harbor View is usually absent from the incident text. For a place, call get_area_trends.
| Name | Type | Req | Description |
|---|---|---|---|
| city | string | – | City to search. Use 'all' for every city. |
| limit | integer | – | Max results (1-200). |
| query | string | yes | Search text (e.g., 'armed robbery', 'domestic battery'). |
No output schema declared.
No examples provided.
How do I install the CuffTracker MCP server?
CuffTracker is a hosted endpoint at https://www.cufftracker.com/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 · www.cufftracker.com
claude mcp add --transport http andrewvg23-cufftracker 'https://www.cufftracker.com/mcp'
What is the CuffTracker MCP server?
CuffTracker is an MCP server listed in the public MCP registry as io.github.AndrewVG23/cufftracker. Chicago and Milwaukee crime data: query incidents, stats, and map-linked MCP UI resources. This page covers its hosted endpoint (https://www.cufftracker.com/mcp).
Is the CuffTracker MCP server safe to use?
CuffTracker scores 76 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 CuffTracker MCP server expose?
CuffTracker exposes 5 tools: resolve_place, get_area_trends, get_city_crimes, get_crime_stats, search_crimes. Their descriptions and schemas cost roughly 891 tokens of context every time the server is loaded.
Does the CuffTracker MCP server require authentication?
No. We connected to CuffTracker without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the CuffTracker MCP server still maintained?
CuffTracker 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.