Other · Local MCP server
Agentsafe
Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.andyscott88/agentsafe- Version
- 1.0.1
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-05-25
- Updated
- 2026-05-25
- Publisher
- andyscott88 (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/andyscott88) · how
- Repository
- github.com/andyscott88/AgentSafe
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | agentsafe-mcp-server | 1.0.1 | stdio |
How to connect Agentsafe
Agentsafe runs locally from a Node.js package published to the npm registry: agentsafe-mcp-server version 1.0.1. 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 agentsafe-mcp-server@1.0.1. It reads the environment variable AGENTSAFE_API_KEY (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": {
"agentsafe": {
"command": "npx",
"args": [
"-y",
"agentsafe-mcp-server@1.0.1"
],
"env": {
"AGENTSAFE_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 other servers
| Server | Runs |
|---|---|
| Agentresources MCPMCP server for Agent Resources: Trust Cards, signed telemetry, ERC-8004 identity, x402. | Local · stdio |
| AgentriskPre-trade token risk scoring API for Base tokens, paid via x402. | Remote · HTTPLive check: ✓ handshake |
| AgentsPay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust. | Remote · HTTPLive check: ✓ handshake |
| Agents Get Paid Kit - x402 MCP + Unlock ($49)Call get_quote, then buy_kit (49 USDC Base x402). Humans keep #pay. | Remote · HTTPLive check: ✓ handshake |
| AgentsbestfriendMCP that provides fast, token-efficient tools for navigating, searching, and understanding codebases. | Local · stdio |
| Agentschat MCPShared live rooms for AI agents to chat, vote, run OKRs, hand off to humans - join, don't rebuild. | Local · stdio |
| AgentsKit RegistryDiscover open-source AI agents and get source-owned installation instructions through MCP. | Remote · HTTPLive check: ✓ handshake |
| AgentsoukMarketplace for AI agents: hire, sell, get paid in USDC on Base. Identity, jobs, reputation. | Remote · HTTPLive check: ✓ handshake |