Skip to main content
Glama
@caelaralabs/mcp

@caelaralabs/mcp

caelara_agent_prompt_injection_scanner

Score text for prompt-injection patterns to detect malicious inputs and protect AI agents from manipulation.

Instructions

[Agent Safety] Score text for prompt-injection patterns Measured p50 11 ms, p95 15 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://agent.caelaralabs.com.

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": {
      "text": "<text>"
    },
    "name": "caelara_agent_prompt_injection_scanner"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to scan

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3/5.0
Behavior2/5

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

With no annotations supplied, the description carries the full behavioral burden, and it discloses only that the call goes to an external host and how fast it is. It says nothing about whether the operation is read-only, whether submitted text is logged or retained on the vendor side, whether auth/rate limits apply, or what the score looks like (range, thresholds).

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 description is short and front-loads the purpose, which is good. However, the benchmark timestamp, p50/p95 latency figures, and bare endpoint URL consume roughly half the text without helping an agent decide or invoke, which dilutes an otherwise tight definition.

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

Completeness3/5

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

For a one-parameter tool this covers the input adequately, but with no output schema the description should explain what the score represents and how to interpret it. An agent calling this has no idea whether the result is a boolean, a probability, or a pattern list.

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?

There is a single parameter with full schema coverage ('Text to scan'), so the schema already does the work and the description adds no syntax the agent is missing. Baseline of 4 applies for a one-parameter tool where the schema is self-explanatory.

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

Purpose4/5

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

The description states a specific verb and resource: 'Score text for prompt-injection patterns', which tells an agent exactly what goes in and what class of analysis comes out. It does not distinguish itself from nearby siblings such as caelara_agent_agent_input_firewall or caelara_api_prompt_firewall_structurer, so the agent must infer which to pick.

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?

There is no guidance on when to use this scanner versus the firewall/structurer siblings, and no prerequisites or exclusions are stated. The only contextual cue is the '[Agent Safety]' tag, which is implied usage at best.

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

Deploy Server

Other Tools