Loading…
Linux kernel CVE analyzer: upload a .config, get a CycloneDX VEX report of affecting CVEs.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days 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 KernelScan MCP server exposes 10 tools, focused primarily on developer capabilities. Its published description reads: "Linux kernel CVE analyzer: upload a .config, get a CycloneDX VEX report of affecting CVEs". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates KernelScan F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Unguarded destructive tools". 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 KernelScan's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add KernelScan to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://kernelscan.io/mcp/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.
Search Linux kernel CVEs. No API key required: keyless callers get the free public tier — recent high-severity Linux kernel CVEs (capped at 25 results). Free *keyed* callers see only CVEs published in
Fetch a single Linux kernel CVE by ID (e.g. ``CVE-2024-12345``). No API key required: keyless callers get the public representation of a CVE, but only for CVEs in the public set (recent high-severity)
List the calling user's products with denormalized analysis stats. Paid plans only (basic / pro / enterprise). Free callers get a clear upgrade message.
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: get_product_vex
A tool description tries to alter the model’s use of another tool.
next call to ``get_product`` (or the REST endpoint) will regenerate it.RecommendationDescriptions must describe only their own tool.
tool: create_product
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
t: ``curl -H "Authorization: Bearer ks_live_..." \RecommendationAnnotate destructive tools and require human approval.
tool: create_product
A tool description tries to alter the model’s use of another tool.
instead of retrying. Check ``whoami`` before a batch of creates.RecommendationDescriptions must describe only their own tool.
tool: update_product
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
oduct`` for the curl recipe) and pass the returned ``config_RecommendationAnnotate destructive tools and require human approval.
tool: update_product
A tool description tries to alter the model’s use of another tool.
ploads`` (see ``create_product`` for the curl recipe) and pass the retRecommendationDescriptions must describe only their own tool.
tool: request_access
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
inside MCP (no API key needed). Use this when a keyless calleRecommendationRemove side-channel parameters; constrain tool inputs.
tool: submit_support_report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
caller's API-key user is attached automatically (id, email, planRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
X) over MCP. No API key required to get started: keyless callers get aRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
browse it with search_cves and get_cve, and use request_access to ask forRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: get_cve
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "get_cve"RecommendationScope tools to the minimum needed.
tool: create_product
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_product"RecommendationScope tools to the minimum needed.
tool: update_product
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "update_product"RecommendationScope tools to the minimum needed.
tool: request_access
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "request_access"RecommendationScope tools to the minimum needed.
tool: submit_support_report
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "submit_support_report"RecommendationScope tools to the minimum needed.
tool: (server instructions)
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.
enAPI schema at https://kernelscan.io/openapi.json (no separate spec to discover).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.
Fetch one product owned by the caller, including the CVE breakdown. Returns 404 (not 403) if the product belongs to another user, so product existence isn't leaked across accounts.
Return the CycloneDX 1.6 VEX document for one of the caller's products. Reads from the 24h ProductVexCache; if the cache is empty/expired the next call to ``get_product`` (or the REST endpoint) will r
Create a new product, run analysis, and return its initial stats. ``config_upload_id`` references a previously-staged .config that the caller POSTed to ``/api/configs/uploads`` over plain HTTP — the L
Update a product owned by the caller. Re-runs analysis if the kernel_version, arch, or referenced .config changed. To change the .config, first POST the new file to ``/api/configs/uploads`` (see ``cre
Return the caller's identity, plan, and quota state. Works without an API key: keyless callers get a lightweight public-tier payload (no account) describing how to request access.
Request an invitation to KernelScan from inside MCP (no API key needed). Use this when a keyless caller wants the full service. It records an invitation request and emails a confirmation; an admin rev
Send a support / dispute report to KernelScan staff. Use this when an automated CVE or factor assessment looks wrong, or when you need to hand human-needed context back to the team. The caller's API-k