Skip to main content
Glama
Sign In

Whisper

by io.github.whisper-sec
OverviewDiscussionsAdmin

agents: firewall

whisper_agents_firewall

The firewall operation on the Whisper control plane, served as CALL whisper.agents({op:'firewall', args:{...}}). Requires your Whisper API key. The identifier in the example is a placeholder for one of YOUR agents: list them with the "agents.list" skill and {"kind":"agents"}. Example call: {"skill":"agents.firewall","input":{"agent":"agent-a1f4c0b2d3e4f5a67"}} Needs a linked Whisper account (OAuth) or your API key in the X-API-Key header.

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": {
      "input": "<input>"
    },
    "name": "whisper_agents_firewall"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesArguments for this operation, as an object. The example passes {"agent":"agent-a1f4c0b2d3e4f5a67"}.

Output Schema

NameRequiredDescriptionDefault
rowsYesThe answers, one object per row, keyed by the column names above. An empty array means the question was understood and nothing matched, which is an answer and not a failure.
columnsYesThe column names, in order. Every row object has exactly these keys, so this is the row shape and reading it is cheaper than inspecting a row.
statisticsNoWhat the query cost.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.3/5.0
Behavior2/5

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

The annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the safety profile is partly covered. The description usefully adds the auth requirement (OAuth-linked account or X-API-Key). However, for a non-read mutation it never states what is changed, whether the change is reversible, or what side effects occur — the most important behavioral fact is absent.

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?

The auth and placeholder guidance is useful, but the invocation syntax is stated twice (the CALL form and the JSON example), and the agent-ID warning is split across two sentences. Tightening would improve front-loading, since the operation's actual effect — the most important thing — never appears.

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

Completeness2/5

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

An output schema exists, so return values need not be explained. But this is a mutating, open-world operation on an agent, and the definition omits what it does, its effect, and its reversibility. Auth coverage does not compensate for that missing core.

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?

The input schema is a single generic "input" object, so the description's example — {"agent":"agent-a1f4c0b2d3e4f5a67"} — is what reveals the actual argument key and its value format. It also correctly warns the ID is a placeholder. That is real added value, though nothing is said about other possible keys or validation.

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

Purpose2/5

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

"The firewall operation on the Whisper control plane" essentially restates the tool name as a noun phrase. It never says what the operation does to an agent's firewall — read rules, add rules, enable/disable, or apply policy — so an agent cannot distinguish it from siblings like whisper_agents_policy or whisper_agents_alert on purpose alone.

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

Usage Guidelines2/5

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

The description gives prerequisite guidance (obtain the agent ID via the agents.list skill) but no when-to-use or when-not-to-use guidance. There is no indication of how this differs from policy, alert, or other agent-ops siblings, leaving selection to guesswork.

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

All Whisper 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