Skip to main content
Glama
Sign In
nexargio-mcp

nexargio-mcp

by nexargio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

nexargio_disarm_carrier

Sanitizes prompts and documents before AI ingestion by neutralizing hidden injection payloads, weaponized PDF actions, and exfiltration URLs, then returns clean content with an audit proof.

Instructions

Carrier-Grade Content Disarm & Reconstruction (AI-CDR).
Neutralizes weaponized prompts, documents, and carrier files before AI ingestion.

Neutralizes:
  - Covert prompt injection steganography and hidden instruction tags.
  - Non-rendering invisible zero-width character sequences.
  - Hidden HTML/Markdown comment injection payloads.
  - Weaponized PDF action streams and execution triggers.
  - Concealed exfiltration URLs and unauthorized network destinations.

Args:
    carrier_target: Raw text prompt string OR absolute file path to a local document (.txt, .md, .pdf).

Returns:
    JSON object containing sanitization status, threats neutralized, sanitized clean content,
    and RFC 3161 cryptographic audit proof.

Input Schema

NameRequiredDescriptionDefault
carrier_targetYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden; it does disclose the output shape (sanitization status, threats neutralized, sanitized content, RFC 3161 audit proof) and that it processes rather than merely inspects. However it never says whether a file-path target is modified in place or left untouched, nor whether the operation is safe/idempotent, which matters for a 'disarm' tool.

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?

Front-loaded with the one-line definition, then a scannable threat list, then args and returns. The five-item bullet list is slightly verbose but each item is a distinct, decision-relevant payload class rather than filler.

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?

With an output schema present, the return values need not be re-explained, yet the description summarizes them anyway, and it covers the single input fully. The remaining gap is behavioral: whether local files are mutated in place is unspecified.

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 description coverage is 0%, so the description must compensate, and it does: carrier_target is defined as either a raw text prompt string or an absolute file path, with the accepted extensions (.txt, .md, .pdf) spelled out. That is the essential disambiguation for a single required string parameter.

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?

States a specific verb+resource ('Content Disarm & Reconstruction') and enumerates exactly what classes of payload it neutralizes, so the action is unmistakable. It does not explicitly contrast itself with sibling nexargio_scan, leaving the scan-vs-disarm boundary to inference.

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?

'before AI ingestion' implies the when, but only implicitly. No explicit when-not-to-use, no prerequisites, and no named alternative such as nexargio_scan even though it is a plausible sibling choice.

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