Dechonet-MCP

Report a Page

report_page

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. This call only records the report and returns at once; it opens nothing. A report changes no verdict by itself: later, DechoNet's own hourly check visits the reported host (an outside site) with the same rules as phishing_link_check (mcp_server_check for malicious_mcp, dns_lookup and ssl_check for network_anomaly), and only what that check observes counts; hosts reported by several independent sources are checked first. Not read-only (it records the report); rate-limited.

Input 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

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.

Changed2 schema fields changedOct 15, 2026

changedInput schema / properties / kind / enum

Previous value: -[
-  "phishing",
-  "fake_payment",
-  "hidden_instructions",
-  "malicious_download",
-  "false_positive",
-  "missed"
-]New value: +[
+  "phishing",
+  "fake_payment",
+  "hidden_instructions",
+  "malicious_download",
+  "false_positive",
+  "missed",
+  "malicious_mcp",
+  "network_anomaly"
+]

addedInput schema / properties / observed

Added value: +{
+  "description": "network_anomaly only: the certificate serial (hex) and issuer, and the addresses, you saw for the host",
+  "properties": {
+    "ips": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "issuer": {
+      "type": "string"
+    },
+    "serial": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedOct 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the annotations: it discloses 90-day retention, exactly which fields persist (host, kind, anonymous reporter hash; endpoint path for malicious_mcp; observed values plus connection country for network_anomaly), what is NOT stored (query, page text, free text), and that the call returns immediately without opening the page. It also notes rate-limiting and prioritization of multiply-reported hosts, and its 'not read-only' framing is consistent with readOnlyHint=false.

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

Conciseness4/5

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

Dense but front-loaded, with the kinds enumerated first and the retention/workflow consequences after; nearly every clause carries information an agent needs. However, it is delivered as one long paragraph with semicolon-chained clauses, which makes it harder to scan than it needs to be.

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 non-idempotent, open-world write tool, the description covers retention, anonymity, side effects, the follow-up verification workflow, and rate-limiting, and an output schema exists to carry return-value detail. Nothing an agent needs in order to decide and call correctly is missing.

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 already 100%, so baseline would be 3; the description adds real meaning on top by specifying that url is the MCP endpoint for malicious_mcp and by explaining what belongs in 'observed' for network_anomaly (certificate serial/issuer, addresses seen). There is a slight tension with the schema note 'only its host is kept' versus the description's 'for malicious_mcp the endpoint path', which costs it a point.

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 and resource ('Report a page to DechoNet') and immediately enumerates the eight reportable conditions, so an agent knows exactly what qualifies. It also names the downstream check tools (phishing_link_check, mcp_server_check, dns_lookup, ssl_check), which separates this reporting call from the sibling tools that actually perform checks.

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?

Gives clear per-kind conditions for use (phishing, fake_payment, false_positive, missed, malicious_mcp, network_anomaly) and clarifies that a report does not by itself change a verdict, which prevents an agent from expecting immediate action. It stops short of explicitly routing an agent to phishing_link_check / mcp_server_check when a direct check rather than a report is wanted.

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

All Dechonet-MCP tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?