nexargio-mcp

Overview Schema Source Related Servers Discussions Admin

nexargio_audit_action

Audits proposed AI agent tool actions before execution, blocking credential theft, destructive commands, and covert exfiltration based on target and origin taint.

Instructions

Autonomous AI Agent Action & Policy Sentinel.
Audits proposed AI agent tool actions BEFORE physical execution to prevent
unauthorized credential theft, destructive command execution,
and covert exfiltration to third-party endpoints.

Args:
    tool_name: Name of the mutating tool (e.g. 'update_secret', 'execute_bash', 'write_file', 'curl').
    target_resource: Path, URL, or resource being modified (e.g. '.env', '~/.aws/credentials', 'webhook_url').
    proposed_value: The parameter value, command string, or file payload being committed.
    origin_taint: Taint classification of the instruction ('UNTRUSTED_INFLOW', 'VERIFIED_OPERATOR').

Returns:
    JSON object with verdict ('ALLOW', 'SUSPEND_EXECUTION', 'HARD_BLOCK'),
    threat score (0-100), violation code, and forensic narrative.

Input Schema

Name	Required	Default
`tool_name`	Yes
`origin_taint`	No	UNTRUSTED_INFLOW
`proposed_value`	No
`target_resource`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 22, 2026

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose the key trait that this is a pre-execution, non-executing check and enumerates the verdict outcomes, but it says nothing about auth requirements, latency, whether calls are logged, or error/fallback behavior. The verdict list is also largely duplicated by the existing output schema.

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 purpose and threat model, then structured Args/Returns. The tagline 'Autonomous AI Agent Action & Policy Sentinel' is decorative and the Returns block partly restates the output schema, but nothing is seriously bloated.

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?

For a 4-parameter security gate with 0% schema description coverage, the description supplies the missing parameter meaning and the verdict semantics an agent needs. The remaining gap is sibling disambiguation and operational details (auth, logging) rather than anything blocking correct invocation.

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 0%, and the description compensates well: it explains all four parameters with concrete examples ('update_secret', '~/.aws/credentials', command strings) and supplies the valid origin_taint values, which the schema itself lacks as an enum. It still doesn't clarify when proposed_value may be omitted or how required vs optional pairs behave.

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 and resource ('audits proposed AI agent tool actions') plus the concrete threats it prevents (credential theft, destructive commands, exfiltration). Very clear on its own, but it never mentions the two siblings (nexargio_scan, nexargio_disarm_carrier), so an agent cannot tell from this text which of the three 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 Guidelines4/5

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

'Audits ... BEFORE physical execution' gives a clear timing precondition that tells the agent when to call it (pre-flight on a mutating action). No explicit exclusions or alternatives are stated, and the relationship to the sibling scanning/disarm tools is left undefined.

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

Deploy Server