Loading…
Access vehicle listings, market analysis, VIN decoding, safety recalls, and EV charging station data across Canada.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The Cardog Public MCP MCP server exposes 5 tools, focused primarily on general-purpose capabilities. Its published description reads: "Access vehicle listings, market analysis, VIN decoding, safety recalls, and EV charging station data across Canada". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Cardog Public MCP F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check Cardog Public MCP's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Cardog Public MCP to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.cardog.io/mcp?api_key={api_key}Streamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Turn free text into canonical Cardog entity refs — THE text entry point for every other tool. A ref is `{domain}:{key}`, lowercase, with `/` separating composite key segments: "make:tesla", "model:min
Decode a 17-character VIN into its full Cardog identity: canonical entity refs, the market grains (nano/squish), spec highlights, and links to adjacent resources. VIN ONLY — this tool never fuzzy-matc
Search live Canadian vehicle listings — ref-native. One call returns listings + facets + the total count. Filters take entity REFS from resolve_entity / identify_vehicle, never free-text names: makes:
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: resolve_entity
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: resolve_entity
A tool description tries to alter the model’s use of another tool.
`next` block): search_inventory with make/model refs; market_quote with a modelRecommendationDescriptions must describe only their own tool.
tool: resolve_entity
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: identify_vehicle
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: identify_vehicle
A tool description tries to alter the model’s use of another tool.
call this: call resolve_entity — free text enters the platform in exactly oneRecommendationDescriptions must describe only their own tool.
tool: identify_vehicle
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: search_inventory
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: search_inventory
A tool description tries to alter the model’s use of another tool.
ntity REFS from resolve_entity / identify_vehicle, never free-text names: makeRecommendationDescriptions must describe only their own tool.
tool: search_inventory
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: market_quote
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
s), a daily-bar history summary, and a bounded sample of the live listiRecommendationRemove side-channel parameters; constrain tool inputs.
tool: market_quote
A tool description tries to alter the model’s use of another tool.
ed; get it from resolve_entity (domain "model-year") or identify_vehicle's refRecommendationDescriptions must describe only their own tool.
tool: market_quote
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: check_recalls
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: check_recalls
A tool description tries to alter the model’s use of another tool.
) Get refs from resolve_entity or identify_vehicle — never construct them fromRecommendationDescriptions must describe only their own tool.
tool: check_recalls
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: check_recalls
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
mpliance guide: https://cardog.app/docs/compliance. Pass EXACTLY ONE of: - `vin` (17 characters) —RecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
The live market card for one instrument: quote (live listing count, best/p25/median/p75 price, average days-on-market, 30-day price cuts), a daily-bar history summary, and a bounded sample of the live
The authoritative "is this vehicle under recall?" check — Transport Canada + NHTSA recall campaigns, fused and ref-keyed. Compliance guide: https://cardog.app/docs/compliance. Pass EXACTLY ONE of: - `