Skip to main content
Glama

VerditNxtGen MCP Suite

Add cryptographic compliance logging to any MCP server in one line.

VerditNxtGen runs a daily Ghost Swarm that sandbox-tests 190+ open-source MCP tools in Docker, scores them for deployment reliability, detects OWASP vulnerabilities at runtime, and generates HMAC-SHA256 signed manifests for SOC2 compliance.

This repository contains the client-side SDKs and proxy that connect your MCP infrastructure to the VerditNxtGen compliance ledger.


Packages

Package

Language

Install

verditnxtgen-mcp-middleware

TypeScript

npm install verditnxtgen-mcp-middleware

verditnxtgen-mcp

Python

pip install verditnxtgen-mcp

Sidecar Proxy

Docker

docker pull ghcr.io/shopfarnow/verditnxtgen-sidecar

Get an API key at verditnxtgen.com/connect-mcp — free tier, no credit card.


Related MCP server: Proofpane

TypeScript — one line

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { withVerditLedger } from "verditnxtgen-mcp-middleware";

const server = withVerditLedger(
  new McpServer({ name: "my-server", version: "1.0" }),
  { apiKey: process.env.VERDIT_API_KEY }
);
// Every tool call is now HMAC-signed and logged to the compliance ledger.
// Zero latency impact — telemetry posts fire-and-forget in the background.

Python — one decorator

from mcp.server.fastmcp import FastMCP
from verditnxtgen_mcp import verdit_ledger

mcp = FastMCP("my-server")

@mcp.tool()
@verdit_ledger(api_key="YOUR_VERDIT_API_KEY")
async def query_database(sql: str) -> str:
    ...

Docker Sidecar — zero code changes

services:
  verdit-sidecar:
    image: ghcr.io/shopfarnow/verditnxtgen-sidecar:latest
    environment:
      VERDIT_API_KEY: "${VERDIT_API_KEY}"
      DOWNSTREAM_URL: "http://your-mcp-tool:3000"
    ports:
      - "8080:8080"
  # Point your gateway at verdit-sidecar:8080 instead of your tool directly

What you get

After logging starts, the VerditNxtGen Intelligence Dashboard shows:

  • Compliance Ledger: HMAC-SHA256 signed manifest for every tool — chain-of-custody proof for SOC2 Type II audits

  • OWASP scan results: LLM01 prompt injection, LLM06 PII boundary, LLM08 vector weakness detection from live sandbox runs

  • pass@k curves: Statistical deployment reliability (pass@1, pass@3, pass@5) across 700+ sandbox runs

  • Cost intelligence: Compute cost per run across resource profiles



License

MIT — see individual package directories.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    A
    maintenance
    Open-source MCP proxy that enforces security policies, content scanning, and audit logging between AI agents and tool servers
    25
    AGPL 3.0
  • A
    license
    B
    quality
    A
    maintenance
    A governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.
    13
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A security MCP proxy that monitors and blocks data exfiltration between AI agents and their tools by detecting toxic flows (untrusted → sensitive → egress) deterministically with zero LLM calls in the decision path.
    1
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Enables sub-millisecond pre-execution safety filtering for AI agent tool calls, blocking destructive shell commands, dangerous SQL mutations, credential access, SSRF, and scope-creep or prompt-injection patterns before they execute, with optional fail-closed transparent proxy wrapping for any MCP server.
    6
    32 npm
    12
    Apache 2.0