Skip to main content
Glama
nexargio

nexargio-mcp

by nexargio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NEXARGIO_API_KEYYesEnterprise API key provisioned from the Nexargio Portal. (Required)
NEXARGIO_RETRIESNoBounded retries for transient gateway network interruptions.2
NEXARGIO_TIMEOUTNoGateway request timeout in seconds.30.0
NEXARGIO_LOG_LEVELNoClient log verbosity (emitted exclusively to stderr to preserve MCP protocol).INFO
NEXARGIO_GATEWAY_URLNoTarget endpoint (defaults to Sovereign Mumbai Gateway / Production Cloud Gateway).
NEXARGIO_MAX_IMAGE_MBNoMaximum allowed size in MB for remote QR code image fetches.5

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
nexargio_scanA
Scans a web URL, bare domain, or QR code image for phishing, credential
harvesting, brand impersonation, and weaponized infrastructure.

Accepts:
  - Full URL (e.g. 'https://login.microsoftonline.portal-security-check.com/auth')
  - Bare Domain (e.g. 'portal-security-check.com')
  - Local QR Code Image Path (e.g. 'C:/downloads/invoice_qr.png')
  - Remote QR Code Image URL (e.g. 'https://example.com/assets/invoice_qr.png')
  - Base64-encoded QR Image String

Scan Modes (Both 100% AI-Powered):
  - 'fast' (Default): Nexargio Autonomous AI Brain (Deep Cognitive System-Two reasoning).
    Returns deep contextual reasoning, brand impersonation detection, and plain-language explanation.
  - 'ultra_fast': Nexargio Normal Engine (Fast Neural System-One LPU).
    Returns instantaneous wire-speed score (0-100), verdict, and action policy (wire-speed execution).

Returns:
  - Verdict (WEAPONIZED_ATTACK, BENIGN_AMBIENT, etc.)
  - Threat Score (0-100) and Action Policy (HARD_BLOCK, ALLOW)
  - Targeted Brand impersonation attribution
  - Plain-language forensic explanation
  - RFC 3161 NIST SHA-256 evidence seal

If a scan cannot be completed, the result's verdict is SCAN_INCOMPLETE with
action_policy ERROR_REVIEW_REQUIRED -- it must NOT be treated as safe.

Args:
    target: The URL, domain, or QR image file path / remote URL to scan.
    scan_mode: Execution mode ('fast' for Deep Cognitive AI analysis, 'ultra_fast' for Wire-Speed Neural LPU triage).
nexargio_disarm_carrierA
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.
nexargio_audit_actionA
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.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
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

TDQS

A4.1/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a clearly different security stage: nexargio_scan inspects external URLs/domains/QR codes, nexargio_disarm_carrier sanitizes local content or prompts, and nexargio_audit_action evaluates proposed agent actions before execution. Their input domains and outputs are distinct enough that an agent can select the right tool without confusion.

Naming Consistency5/5

All tools use the same nexargio_ snake_case prefix and readable action-oriented names. nexargio_scan is slightly less noun-structured than the others, but the overall convention remains predictable and consistent.

Tool Count5/5

Three tools is lean but appropriate for a focused security pipeline, with each tool covering a substantial distinct operation. There are no filler or duplicate tools.

Completeness4/5

The core workflow is covered: scan external threats, disarm carrier content, and audit proposed actions. Minor gaps exist around batch scanning, saved reports/history, and configuration, but agents can still complete the main security tasks.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources