Skip to main content
Glama
Sign In

Knocklog

by io.github.leonlesenechal
OverviewDiscussionsAdmin

Identify and verify one HTTP request

classify_request
Read-only

Identifies whether a request comes from an AI agent, which one, what kind (training, AI search, user-triggered, agentic browser…) and whether its identity is verified or spoofed, using what each operator publishes (IP lists, reverse DNS, Web Bot Auth signatures; see https://knocklog.ai/agents). Pass the client IP, the full request URL and all request headers for the most complete check.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "classify_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
ipNoClient IP as seen by the server
urlNoFull request URL
methodNoHTTP method of the request (default GET)
headersNoRequest headers
user_agentNoThe User-Agent header of the request, exactly as received

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / method / description
      Added value: +"HTTP method of the request (default GET)"
    • addedInput schema / properties / user_agent / description
      Added value: +"The User-Agent header of the request, exactly as received"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds real value by naming the underlying evidence sources (operator-published IP lists, reverse DNS, Web Bot Auth signatures) and pointing to an external reference URL. It also discloses the verification dimension (verified vs. spoofed), which is behavior an agent could not infer from annotations alone. It stops short of stating rate limits, latency, or confidence handling.

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

Conciseness5/5

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

Two sentences: the first front-loads the purpose with a compact parenthetical enumeration, the second gives actionable input guidance. No filler, no restatement of the title, and the external link is placed where it supports rather than interrupts.

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

Completeness4/5

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

There is no output schema, so the description carries the burden of describing results, and it does so conceptually (agent identity, agent category, verification status). For a 5-parameter read-only classification call that is close to sufficient; the only gap is that the concrete response shape or confidence levels are not described.

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 the baseline is 3, but the description adds meaning beyond the schema by explaining that the IP, full URL, and all headers are what drive the completeness of the check. That signals relative parameter importance and the cost of omitting headers, which the flat schema does not convey.

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 ('Identifies whether a request comes from an AI agent') and enumerates the exact determinations returned: which agent, what kind (training, AI search, user-triggered, agentic browser), and verified vs. spoofed. This is far more specific than the title and lets an agent distinguish it from list_known_agents or scan_site without opening the schema.

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?

The second sentence gives invocation guidance ('Pass the client IP, the full request URL and all request headers for the most complete check'), implying partial inputs yield a weaker result. However, it never states when to choose this tool over the sibling tools or what preconditions exist (e.g., single request vs. bulk/site-wide analysis), so usage is only implied.

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

All Knocklog toolsInspect
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.

Resources