Loading…
Anchor AI agent tool calls, file hashes, and events to the Bitcoin blockchain via OpenTimestamps for tamper-evident, court-admissible audit records.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 27 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 knox-anchor MCP server exposes 7 tools, focused primarily on general-purpose capabilities. Its published description reads: "Anchor AI agent tool calls, file hashes, and events to the Bitcoin blockchain via OpenTimestamps for tamper-evident, court-admissible audit records". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates knox-anchor D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". 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 knox-anchor's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add knox-anchor to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://bonissystems.com/api/knox/mcpStreamable 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.
Return the Knox MCP server self-description: operator, USPTO patent reference, jurisdiction, available tools, and links to the public AAM (Agent Audit and Management) documentation surface.
Return Knox service health: process uptime, database latency, total anchors written, latest anchor timestamp, and the Bitcoin anchor SLA target (OpenTimestamps interval, 1-6 hour confirmation window).
Return the canonical Knox event-type taxonomy. Each event type is a citation token for federal-grade audit; the registry expands monotonically and is itself anchored on every expansion.
Given a SHA-256 anchor hash (64 hex chars), return the anchor record, chain link validity (predecessor present and matched), event type, sequence number, and verify URL. Public — no authentication req
Anchor a generic agent action to the Knox chain. Accepts any event_type from the canonical taxonomy plus a payload object. Returns the anchor sequence, payload hash, predecessor hash, timestamp, and v
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: anchor_event
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
s a Knox Bearer API key on the Authorization header — unauthenticated cRecommendationRemove side-channel parameters; constrain tool inputs.
tool: anchor_mcp_tool_call
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "server_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
AI agents. Call get_descriptor for full server metadata, list_event_types 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.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.
Access Vonage API documentation, code snippets, tutorials, and troubleshooting resources.
Decode SSTV audio recordings and anchor their fingerprint and image hash to the Knox event chain.
Read-only public-registry routing map by entity kind for reference, not determination.
Screen a name against the U.S. Treasury OFAC SDN list as an informational reference, not a compliance determination.
Anchor a content-creation event to the Knox chain, returning a C2PA-aligned, FRE 902-shaped provenance bundle.
Check whether a NAICS code aligns with a vertical as a routing-for-review signal, not a determination.
Generate a self-authenticating booking-request receipt anchored to the Knox chain that never represents a person.
Convenience anchor for the AAM Model Context Protocol theater. Records an `agent_mcp_tool_call` event with structured tool-call metadata (server URL, tool name, argument digest, agent identity, respon
Anchor a SHA-256 file digest to Knox and return an affidavit architected for FRE 902(13)/(14) self-authentication. The file itself is not transmitted — the caller computes the hash and only the digest