"Using an MCP server to generate structured ADK agents" matching MCP servers:

Enables AI agents to discover each other and communicate through cryptographically verified messaging and secure inbox management via the Agents Registry. It provides tools for Ed25519-based identity authentication, message signing, and agent discovery across domains.

Secure MCP server that enforces allowlist-based policies, read-only access, input validation, and human-in-the-loop for sensitive actions, enabling safe vulnerability analysis.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Validates AGENTS.md files against the cross-vendor coding-agent spec, detecting security smells and consistency issues.

Connect your database to your AI agent, read-only, without sharing your password. Maplith Bridge serves a folder of data files over MCP behind a token you create, and fills it from PostgreSQL under a role that can only read.

Provides 14 MCP tools for AI agent infrastructure, enabling knowledge base queries, skill search, handoffs, blueprint validation, trust scoring, identity verification, SLA validation, and compliance checks.

This server enables AI agents to interact with Microsoft 365 tenants using restricted, temporary sessions without ever being given direct credentials. It enforces strict operational policies and ensures every action and proposal is recorded in an immutable audit trail for a human user to review.

Enables Claude AI to access and run over 150 integrated cybersecurity tools through a public ngrok tunnel, supporting agentic security workflows via MCP.

An MCP server that provides authorization middleware for AI agents using private data, enabling consent management on Aleo and local private inference with persistent policy storage.

A secure MCP proxy server with JWT authentication, SQL guardrails, rate limiting, and Kafka audit logging, enabling enterprise-grade access control for MCP clients like Cursor and Claude Desktop.

Enables Terraform HCL plan generation, drift detection, and strict human confirmation approval barriers for cloud infrastructure management.

Persistent identities, email, saved accounts and scoped credentials for AI agents. Remote Streamable HTTP or local stdio, with permission and revocation checks. Password and TOTP outputs are withheld remotely unless explicitly enabled. Requires ActAs Pro (US$12/month or US$120/year). Setup: https://actas.dev/docs?utm_source=glama&utm_medium=directory&utm_campaign=launch

Enables agents to use secrets without exposing them, by injecting values into commands and redacting them from all outputs and transcripts.

Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.

Enables agents to browse the web anonymously over Tor, host hidden onion services, communicate through encrypted groups, and discover peers without exposing their identity or infrastructure.

Provides a three-layer payment firewall for AI agents, enabling identity verification, risk screening, and execution authorization with on-chain policy enforcement for secure and auditable transactions.

Enables LLM coding agents to sign in with Nostr by generating NIP-07 signatures and exposing public keys, without requiring a wallet or browser extension.

Enables agents to serve interactive Auth0 Forms as MCP Apps in a sandboxed iframe, letting users complete sign-up, consent, profile, or payment flows while the agent only receives completion status.

Fast PDF tools for AI agents: 31 tools in one Rust binary. CLI, MCP server and library.

Input/output safety gate for AI agents: detect prompt-injection/jailbreak, leaked secrets/PII, and URL/IP reputation. Deterministic, no LLM.