Dechonet MCP

Report a Page

report_page

Report a URL to DechoNet to flag phishing, fake payments, hidden AI instructions, malicious downloads, wrong verdicts, malicious MCP servers, or network anomalies for review.

Instructions

Report a page to DechoNet: phishing or brand impersonation, a fake payment window (card fields where a payment provider should be), hidden instructions aimed at AI agents, a malicious download, a DechoNet verdict that looks wrong (false_positive) or a danger it missed (missed), an MCP server whose tool descriptions steer agents (malicious_mcp — url is the MCP endpoint), or a network anomaly (network_anomaly — the certificate serial/issuer or addresses you saw for the host, in observed). Kept for 90 days: the host and the kind, with an anonymous reporter hash used to count independent reports; for malicious_mcp the endpoint path, for network_anomaly the observed values and the country of the connection. No query, page text or free text. A report changes no verdict by itself: DechoNet opens the page itself and only what it observes counts; pages reported by several independent sources are looked at first. Not read-only (it records the report); rate-limited.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	Address of the page (only its host is kept)
`kind`	Yes	What is wrong with the page
`observed`	No	network_anomaly only: the certificate serial (hex) and issuer, and the addresses, you saw for the host

Output Schema

TableJSON Schema

Name	Required	Description
`host`	Yes
`kind`	Yes
`receipts`	No	Signed observation receipts behind this result, one per lookup: when, from where and under which rules version DechoNet observed it. Each url shows the record and checks its Ed25519 signature.
`received`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.5.14Oct 15, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond annotations: states the 90-day retention, exactly what data is kept (host+kind, anonymous reporter hash; endpoint path for malicious_mcp; observed values and country for network_anomaly), explicitly that no query/page text/free text is stored, that a report changes no verdict by itself, and that DechoNet re-opens the page. Also discloses rate limiting.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the verb and kind list well, but the first sentence is a very long run-on enumerating eight kinds with parenthetical definitions, and the retention/privacy sentences pack many clauses. Dense and information-rich but harder to scan than necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with an output schema, it covers privacy/retention, rate limits, what a report does and does not do, and the kind-specific data requirements. An agent has everything needed to call it correctly without reading the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so baseline is 3, but the description adds meaning the schema lacks: which kinds require observed data (network_anomaly), that url for malicious_mcp is the MCP endpoint, and that observed holds certificate serial/issuer or addresses. Useful layered detail beyond the enum descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (report) and resource (page) plus enumerates all eight report kinds with definitions, e.g. fake_payment means 'card fields where a payment provider should be'. This distinguishes it from every sibling, which are lookups/checks rather than reporting endpoints.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies when to use by enumerating the situations (phishing, fake payment window, hidden instructions, wrong verdict, missed danger, steering MCP server, network anomaly) and explains the false_positive/missed cases for reporting a bad DechoNet verdict. No explicit exclusions or named alternative tools, so not a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.