Security

Official Model Context Protocol (MCP) Server for DotI (.i) Web3 Identity & Multichain Domain Resolution

Security scanner for AI agent skills, configs, and MCP tools. Vet before you trust.

Write the rules for your AI agent once, in plain English. Deterministic code checks every tool call, and a Claude Code hook blocks the ones your rules forbid.

BaseMail MCP server — give AI agents their own @basemail.ai email (SIWE auth, ERC-8004 identity, $ATTN attention economy) on Base

Opt-in UUAID adapter for @e-sig/core — stamp the acting agent's UUAID into the audit log and anchor the audit hash-chain head to UUAID's Polygon-anchored ledger (encrypted, hash-only).

One source of truth for your MCP servers — fold one config out to every client.

Local MCP credential broker for coding agents (Claude Code, Codex, Gemini, and any other MCP-stdio client). Values never enter the AI transcript — the agent requests secrets through a schema, a localhost form lets you type them, and they land in Vault, .e

Universal AI API Orchestrator — 1554 tools, 96 services, portable AI Brain bundles + machine-bound vault encryption + Application Engine. The most comprehensive MCP server available. Free and open source from 0nORK.

MCP contracts for governed AI agent tools, OAuth scopes, and the Praxa agentic harness.

A multi-domain, auth-first MCP server giving AI agents access to financial markets, Web3/DeFi, developer tools, and healthcare (FHIR). Production-grade, typed, and installable in minutes.

MCP server for safe shell, file, database, git, and HTTP access. Every operation validated against per-agent permission rules. Powered by AgentsID.

SonarQube CLI integration for pi: sonar_* tools, a pre-commit secrets guard and agent context for the `sonar` CLI.

MCP stdio server for Ripple's local authorization gate for AI coding agents.

iota embedded policy engine as a pi coding-agent extension: hash-pinned bless, agents.yaml enforcement for read/write/edit/bash, JSONL decision log

Bind LangGraph Agent Inbox human responses to exact, one-time EMILIA authority. Accept uses the frozen interrupt, edit requires fresh authority for the edited action, and response or ignore never authorize tool execution.

VerifID integration skill for AI coding agents (Claude Code): install with `npx @verifid/skill install` and ask your agent to integrate identity verification.

Authorized, local-first application security assessment run by the coding agent you already use

AWS IAM MCP Server – user/role inspection, policy analysis, access key audit, and privilege simulation for security investigations

Node.js/TypeScript MCP server for AWS Single Sign-On (SSO). Enables AI systems (LLMs) with tools to initiate SSO login (device auth flow), list accounts/roles, and securely execute AWS CLI commands using temporary credentials. Streamlines AI interaction w

VirusTotal MCP Server – security analysis for URLs, files, IPs and domains