Find the right security-disclosure contact for any internet asset (domain, IP, package, repo, app).
Scored across 2 tools
Each tool has a distinct function: classify_asset identifies the asset type locally without network calls, while lookup_security_contact performs a network-backed search for disclosure contacts. There is no overlap in purpose or output.
Both tools follow a consistent verb_noun pattern in snake_case: classify_asset and lookup_security_contact. This makes the tool set predictable and easy for an agent to navigate.
With only two tools, the surface feels thin, but the server's scope is narrow and the two tools cover the primary workflow. This sits at the borderline lower end of acceptable tool count.
The workflow is complete for the stated purpose: classify an asset if needed, then look up security contacts. The lookup tool accepts all listed asset types, so there are no obvious dead ends or missing operations.
Classify an input as a domain, IP, package, repository, etc. No network calls — instant response. Useful for understanding what an asset is before performing a full lookup.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | The input to classify | |
| asset_type | No | Interpret as this asset type, preserving the same normalization as lookup. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, and the description adds a valuable behavioral trait: 'No network calls — instant response.' This extra context reassures the agent that classification is local and fast, going beyond what the annotations alone provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences deliver the core function, the key behavioral guarantee, and the usage context. Every clause earns its place, and the primary action appears immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only classifier with fully documented parameters, the description covers what the tool does, when to use it, and its performance characteristics. It does not describe the return payload, but the tool's simplicity and the lack of an output schema make this a modest rather than critical gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both input and asset_type already documented in the schema. The description adds a few examples of asset types but does not materially improve parameter understanding beyond the structured definitions, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource ('Classify an input') and enumerates the categories it can recognize ('domain, IP, package, repository, etc.'). This clearly distinguishes it from the lookup sibling by framing classification as a prerequisite step to a fuller operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use the tool: before performing a full lookup to understand what an asset is. It does not explicitly name alternatives or exclusions, but the intended positioning is unambiguous enough for an agent to select it appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find security reporting channels for responsible vulnerability disclosure. Takes a domain, IP, URL, package name, repository, container image, mobile app, hardware device, browser extension, desktop app, or organization name. Returns bug bounty programs, security.txt contacts, VDP links, abuse contacts, and national/global CERT fallbacks ordered by applicability to the queried owner and asset. This is informational only — not legal advice.
| Name | Required | Description | Default |
|---|---|---|---|
| asset | Yes | The asset to look up. Examples: "cloudflare.com", "8.8.8.8", "npm:express", "gh:facebook/react", "app:WhatsApp", "hw:Cisco ASA 5505" | |
| asset_type | No | Force a specific asset type. Auto-detected if omitted. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond the annotations by explaining that results are 'ordered by applicability to the queried owner and asset' and that the information is 'informational only — not legal advice.' This complements the readOnlyHint and openWorldHint annotations without contradicting them. It does not mention error handling or rate limits, but for a read-only lookup this is reasonably transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences long, front-loaded with the primary purpose, and each sentence adds distinct value: what it does, what inputs it accepts, what outputs it returns, and a caveat. There is no redundancy or filler, making it concise and well-structured for an AI agent to process quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Since there is no output schema, the description compensates by listing the return categories (bug bounty programs, security.txt contacts, VDP links, abuse contacts, CERT fallbacks) and the ordering rule, which gives the agent a good sense of what to expect. It does not detail the exact result structure or behavior on empty results, but for a simple lookup tool this is sufficient context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes both parameters thoroughly, including example values for 'asset' and the full enum for 'asset_type'. The description's list of supported asset types largely mirrors the schema's 'asset_type' enum and adds no new semantic meaning beyond what is already in the schema. With 100% schema description coverage, the description does not need to compensate, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Find') and resource ('security reporting channels for responsible vulnerability disclosure'). It also lists a wide range of supported asset types and output categories, distinguishing it from the sibling tool 'classify_asset' by its focus on contact lookup rather than classification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool through its clear purpose statement and asset type list, but it does not explicitly contrast it with sibling tools or provide exclusions (e.g., 'use classify_asset for asset classification'). There's no direct when-to-use/when-not-to-use guidance, making it adequate but not strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
classify_asset1 field changedInput schema / properties / asset_typeAdded value: +{
+ "description": "Interpret as this asset type, preserving the same normalization as lookup.",
+ "enum": [
+ "domain",
+ "ipv4",
+ "ipv6",
+ "url",
+ "email",
+ "cidr",
+ "asn",
+ "package",
+ "repository",
+ "container",
+ "cloud-resource",
+ "mobile-app",
+ "hardware",
+ "extension",
+ "desktop-app",
+ "organization"
+ ],
+ "type": "string"
+}classify_assetlookup_security_contactDiscover exposed assets, leaked secrets, APIs & client-side vulns across your attack surface
WHOIS/RDAP, DNS, SSL, live subdomains with IPs, and SPF/DMARC/DKIM for any domain.
Look up any domain, IP address or AS number: hosting, DNS, registration, email, TLS and headers.
Email security and AI discoverability scores for any domain, with the exact record or tag to fix.
Add one secure layer between your agents and this server.
