RelayShield Security Intelligence MCP Server

by nzdsf2-gif Your server? Claim it

local only

RelayShield Security Intelligence runs on your own machine — the client starts it, so there is no endpoint to ping. 451 installs a week from pypi. Last commit 7 Sep 2026.

Breach, SIM swap, infostealer, domain lookalikes, MCP registry risk, prompt-injection detection.

Installs per day peak 312 · avg 45 · +132% w/w

a month agotoday

451

Installs / week

pypi · relayshield-mcp

Stars

0 open issues

7 Sep 2026

Last commit

0 releases in 90 days

—

License

Python

What the code does

We read the source, 19 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Secret passed into the image build Dockerfile:5, .actor/Dockerfile:31

ENV RELAYSHIELD_API_KEY=""

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add relayshield-mcp -- uvx relayshield-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "relayshield-mcp": {
      "args": [
        "relayshield-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.relayshield-mcp]
command = "uvx"
args = ["relayshield-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "relayshield-mcp": {
      "args": [
        "relayshield-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "relayshield-mcp": {
      "args": [
        "relayshield-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: RELAYSHIELD_API_URL (RelayShield API base URL — https://api.relayshield.net), RELAYSHIELD_API_KEY (RelayShield API key for subscription access (all tools available) — get one at api.relayshield.net/developers), RELAYSHIELD_X_PAYMENT (x402 payment proof — USDC on Base (pay-as-you-go mode, no API key needed)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to RelayShield Security Intelligence

same job, measured the same way

AI Firewall MCP

by akhilucky

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

89 installs/wk local only

npm Registry MCP Server

by yawlabs

npm registry MCP server — package intelligence, security audits, dependency analysis

1 290 installs/wk local only

AIShield Security Scanner

by lm203688

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

46 installs/wk 9 tools local only

GuardianShield

by sparkvibe-io

AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs

82 installs/wk local only

Domain Intelligence

by dataleadspro

Domain overviews for security and sales: registration, infrastructure, and risk signals.

1 tools answering

Sentinel Scan

by ventrova

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

74 installs/wk local only

MCP Safeguard

by cognivators

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

125 installs/wk local only

Agent Security Scanner MCP

by sinewaveai

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

728 installs/wk local only

RelayShield Security Intelligence — questions

Answers built from our own checks of this server.

Why is there no uptime for RelayShield Security Intelligence?

RelayShield Security Intelligence runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package relayshield-mcp was installed 451 times last week.

How do I connect RelayShield Security Intelligence?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls relayshield-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use RelayShield Security Intelligence?

The pypi package relayshield-mcp was installed 451 times in the last week. Week over week that is +132%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is RelayShield Security Intelligence open source?

We cannot say either way: written in Python and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.