"Relay" matching MCP servers:

Enables developers to expose any dev tool as a safe, audited MCP server with permission tiers, audit logging, and automatic argument validation.

Enables managing Firefox Relay masks (random and domain) via MCP tools, including listing, creating, updating, and disabling masks.

Security-enhanced MCP Relay/Proxy server providing real-time AI threat protection for MCP Clients, scanning tool descriptions, call parameters, and responses for threats like prompt injections and malicious URLs.

A Docker-based relay service that simplifies authentication and provides audit logging for AI agents accessing IBM Guardium Cryptography Manager's MCP server.

Enables a standard authenticated MCP client to dispatch three controlled operations — command execution and scoped file reads/writes — to a remote lightweight agent through Vercel, with encrypted relaying, atomic writes, and Redis-backed audit logging.

Broadcasts Article 73 incident reports simultaneously to EU AI Act, DORA, NIS2, GDPR, and ISO 42001 regulators, with escalation workflows and audit trails.

Security intelligence for AI agents — breach detection, SIM swap, domain lookalikes, OAuth watchlist, and malware scanning. Subscription or x402 PAYG.

Enables AI agents to explore licensed IP intelligence databases through four read-only tools: listing the databases an organization is licensed for, inspecting a database's columns, sample rows, row count and build date, fetching published checksums for verifying a local copy, and reviewing recent download attempts. It covers VPN, proxy, hosting, CDN and relay address space data without transferring the multi-gigabyte files themselves.

Enables CLI/agent sessions to join a Buzz relay, see channels, read the bus, post, and @mention agents, with custody-clean identity resolution.

Enables agents to price, send, and track encrypted file transfers, with files chunked, encrypted, and hashed locally before any network relay, and to retrieve signed collection receipts. It supports prepaid credit pools and gives agents a privacy-first transfer capability within their own trust domain.

Enables local, privacy-mode incident handoffs with four fixed questions, pattern-guarded redaction, human-review drafts, and optional in-memory data clearing.

Safe, reversible tool execution for AI agents. It sits between an agent and its tool servers, adding contracts, dry-run planning, policy, approvals, saga execution, and rewind.

Provides anonymous email management through Firefox Relay, enabling sending, receiving, and OTP extraction while maintaining privacy and security.

Enables ChatGPT and Codex to request public keys, prepare and sign exact Nostr events, encrypt or decrypt NIP-04/NIP-44 payloads, and publish with per-relay acknowledgement, while the private key stays in the user's Alby, nos2x, or remote NIP-46 signer. Every operation is queued for local browser approval, with one-use signing intents and verification before anything is broadcast.

A lightweight stdio-to-http relay that enables the GitHub MCP server to authenticate using a GitHub App instead of a Personal Access Token. It automatically manages fine-grained permissions and short-lived tokens for secure, organizational AI agent workflows.

Replay safety evals before agent releases move forward. A paid remote MCP for AI agent safety replay checks, policy gates, eval receipts, control-fix suggestions, and release evidence exports.

Enables autonomous agents to negotiate and collaborate through end-to-end encrypted sessions, ensuring confidentiality and non-repudiation without the relay reading plaintext.