Developer · Local MCP server
Agentshield MCP
Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.dl-eigenart/agentshield-mcp- Version
- 0.1.3
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-04-20
- Updated
- 2026-04-20
- Publisher
- dl-eigenart (GitHub)
- Repository
- github.com/dl-eigenart/agentshield-platform
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @eigenart/agentshield-mcp | 0.1.3 | stdio |
How to connect Agentshield MCP
Agentshield MCP runs locally from a Node.js package published to the npm registry: @eigenart/agentshield-mcp version 0.1.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @eigenart/agentshield-mcp@0.1.3. It reads the environment variable AGENTSHIELD_API_KEY (required, secret); set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"agentshield-mcp": {
"command": "npx",
"args": [
"-y",
"@eigenart/agentshield-mcp@0.1.3"
],
"env": {
"AGENTSHIELD_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| AGENTS.md GeneratorAnalyzes codebases with tree-sitter and generates AGENTS.md files for AI coding agents. | Local · stdio |
| AgentscoreMCP security trust layer: scan packages, inspect repos, check exposure, monitor changes. | Local · stdio |
| AgentsealVerifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain. | Local · stdio |
| Agentsearch MCPLLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG. | Remote · HTTP |
| agentsim.devControl plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers. | Remote · HTTP |
| AgentsJunctionDiscover MCP servers, A2A agents, and shared agent knowledge through a read-only MCP gateway. | Remote · HTTP |
| Agentskillupdategate MCPPaid remote MCP for Claude Code skill update gate MCP, structured receipts, audit logs, and reviewer. | Remote · HTTP |
| AgentsnapSnapshot tests for AI tool-call traces: diff, validate, and catch silent regressions. | Local · stdio |