"Exposing an MCP server via a public tunnel with mcp-proxy" matching MCP servers:

Enhances Microsoft Work IQ with broader MCP client compatibility, structured search tools, an interactive REPL, and an OpenAI-compatible HTTP API.

Enables MCP clients to securely connect to Kerberos-protected upstream MCP servers using the current macOS user's Kerberos ticket cache via SPNEGO authentication over a local HTTP proxy.

Lets a model use hundreds or thousands of MCP tools without loading them: it puts five tools in front of a large MCP server or gateway, so the model searches for the tool it needs and calls it. Search combines BM25 with a multilingual embedding model that runs inside the proxy.

Enables MCP-compatible agents to interact with the Kenwea marketplace through a public HTTP endpoint, supporting authentication, session management, and tools for marketplace search, publishing, and onboarding.

Local-first MCP proxy with BM25 tool discovery, quarantine security, Docker isolation, OAuth support, activity logging, and web UI. Routes multiple upstream MCP servers through a single endpoint.

Enables LLMs to interact with embedded devices by reading and writing Segger RTT data through a J-Link debugger.

Enables AI assistants to explore a PostgreSQL database, run bounded read-only SQL, inspect query plans, test hypothetical indexes, find slow queries, and check database health with compact CSV output.

Self-hosted webhook relay and tunnel with Noise NK encryption. Inspect requests, replay webhooks, trace AI pipelines, connect/disconnect tunnels — 13 MCP tools. No tokens or passwords needed.

Transparent Go proxy that intercepts, signs, rate-limits, redacts, and audits all MCP JSON-RPC tool calls without modifying client or server. Stores to JSONL or SQLite with HMAC-SHA256 signatures.

Gives AI assistants real-time access to web data with the ability to scrape any website, bypass anti-bot systems, extract structured data, and capture screenshots through enterprise-grade infrastructure.

HTTP(S) and WebSocket debugging proxy, like Proxyman or Charles, that AI agents drive over MCP: summarize captured traffic, read requests with secrets masked, diff a working request against a failing one, mock responses, set breakpoints and throttle the network.

MCP production gateway — Streamable HTTP proxy to stdio/HTTP backends with API-key auth, per-key rate limiting, TTL cache, per-backend circuit breaker, Prometheus metrics.

An MCP orchestration layer that aggregates multiple MCP servers while exposing only 8 meta-tools, dramatically reducing context window usage, and provides SLOP scripting, event monitoring, and tool customization.

Open-source MCP proxy that enforces security policies, content scanning, and audit logging between AI agents and tool servers

Enables agents to discover and execute a catalog of AI models and APIs through a remote Streamable HTTP server using one API key and prepaid balance, with per-call pricing and public tool discovery.

Control-plane proxy that sits in front of MCP servers, enforcing per-identity policy (YAML/OPA/Cedar), budget limits, and an audit trail on every call. Includes real-time anomaly detection that auto-blocks a compromised agent without a human in the loop.

Security proxy that wraps any MCP server with bidirectional scanning for credential leaks, prompt injection, and tool description poisoning. Also provides an HTTP fetch proxy with a 9-layer scanner pipeline for capability-separated agent deployments.

An MCP server for the Last.fm API, exposing artist, album, track, chart, and user data as read-only tools. Supports optional writes, auth, and experimental methods over stdio or HTTP.

Debug your Container and Kubernetes workloads with an AI interface powered by eBPF

Enables users to check a site, e-mail, phone number, IBAN, or SIREN against public sources and receive sourced anti-scam signals in French. The same checks are available remotely over MCP and locally via stdio, sharing the HTTP API's key and quota.

Zero-dependency local proxy that wraps any MCP server to redact secrets, strip hidden-Unicode prompt injection, and block writes to protected paths like ~/.ssh and .env.

Enables AI agents to securely use API keys by storing them in an encrypted vault and injecting them on demand with user approval, without exposing the key values to the model.

An unofficial MCP server that brings your Fileee documents to AI clients, with secure authentication via OAuth or static tokens and capabilities for reading, writing, sharing, and more.

Connect any AI client to the CaBrain memory system via MCP, exposing tools for memory recall, retain, and brain management.

MCP proxy that wraps any MCP server and transparently converts JSON responses in tools/call to TOON format — a token-efficient alternative to JSON optimized for LLMs (~40% fewer tokens).

Enables Garmin Connect IQ developers to inspect store versions, listings, reviews, and installs, run SDK builds and simulator workflows, and optionally access Garmin Connect data through an agent, with read-only defaults and confirmation before public actions.

Read and post to Clanksquare, an agent social network of public channels where every post is signed by its author's key; runs as a stdio server (node clank.mjs mcp) with all tools. Built by Zach Lowden (ZacxDev), with most of the code written by AI coding agents.

This server enables Temporal Workflows and other MCP clients to call tools implemented as Temporal Nexus operations, and to proxy upstream MCP servers so every upstream call runs in a standalone Temporal activity.

Enables administering Ubuntu hosts through MCP over stdio, currently exposing a read-only get_system_info tool that reports OS release, hostname, kernel, architecture, memory, and root filesystem capacity.

Enables an AI agent to read and change macOS VPN split-tunnel routing through the VPN Bypass app's local control socket.