BlackVeil DNS & Email Security Scanner

check_llms_txt

Read-onlyIdempotent

Inspect a domain's /llms.txt and /llms-full.txt for links and install commands an AI agent could inherit. Sweeps external link hosts for dangling CNAMEs and deprovisioned-service fingerprints (evidence, not proof it is claimable) and checks npm/PyPI install package names for unregistered names and OSV malicious-package advisories. Detection only, not scored; notAssessed lists unmeasured items.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domain": "<domain>"
    },
    "name": "check_llms_txt"
  }
}

Input Schema

Name	Required	Description
`domain`	Yes	Domain, e.g. example.com
`format`	No	Output verbosity.
`force_refresh`	No	Bypass the cache.

Output Schema

Name	Required	Description	Default
`score`	Yes
`passed`	Yes
`partial`	No
`category`	Yes
`findings`	Yes
`checkStatus`	No
`verdictWithheld`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 12, 2026

changedInput schema / properties / domain / description

Previous value: -"Domain to check (e.g., example.com)"New value: +"Domain, e.g. example.com"

changedInput schema / properties / force_refresh / description

Previous value: -"Bypass cache and run a fresh check. Useful after DNS changes."New value: +"Bypass the cache."

changedInput schema / properties / format / description

Previous value: -"Output verbosity. Auto-detected if omitted."New value: +"Output verbosity."

Changed1 schema field changedOct 25, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
Changed1 schema field changedOct 5, 2026
- addedOutput schema / properties / verdictWithheld
```
Added value: +{
+  "type": "boolean"
+}
```
AddedSep 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the description is not obligated to restate safety. It adds genuinely new behavioral context: results are 'evidence, not proof it is claimable', the tool performs external link-host sweeping and third-party OSV lookups, and unmeasured items surface in a notAssessed list. Missing only things like rate-limit or latency expectations for the outbound sweeps.

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?

Two sentences, front-loaded with the core inspection target before the secondary sweeps and the confidence caveat. It is dense and jargon-heavy ('deprovisioned-service fingerprints', 'notAssessed') but no sentence is filler.

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?

With an output schema present and rich annotations, the description need only cover scope and caveats, and it does: what is inspected, what external checks fire, how confident the findings are, and that the tool does not score. An agent has enough to call it correctly and interpret results without opening the schema.

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

Parameters3/5

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

Schema coverage is 100% and all three parameters carry their own descriptions (domain example, format verbosity, force_refresh cache bypass). The description adds nothing about parameter behavior — notably it does not explain what compact vs full yields or when a cache bypass is warranted — so the baseline 3 applies.

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?

The description names a specific verb and resource ('Inspect a domain's /llms.txt and /llms-full.txt') and then enumerates the concrete artifacts it hunts for: external link hosts, dangling CNAMEs, deprovisioned-service fingerprints, and npm/PyPI package names. This is far more specific than the sibling names alone (check_txt_hygiene, check_agent_discovery) and lets an agent tell which file set and which failure modes are in scope.

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

Usage Guidelines3/5

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

Usage context is implied rather than stated — an agent can infer this is the tool for AI-agent-readable manifest files, but there is no explicit 'use this instead of check_agent_discovery' routing and no stated prerequisites or exclusions. The line 'Detection only, not scored' tells the agent how to interpret results but not when to reach for this tool over a sibling.

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

All BlackVeil DNS & Email Security Scanner tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.