"A proxy MCP server for connecting to other MCP servers" matching MCP servers:

Universal MCP proxy server that discovers, searches, and executes tools across all configured MCP servers from a single entry point.

Look up what the official MCP Registry declares for a server and what Lowdown observed: daily reachability, HTTP status, tool names and tool-schema changes over the last 30 days, plus outcomes reported by agents. A public time-series record for a fixed sample of 5,000 Registry servers. Recorded facts only, no scores or rankings. Raw data: CC BY 4.0.

An MCP server that acts as a proxy to connect MCP clients to agent frameworks like Mastra and LangGraph, enabling agent discovery, dynamic server connections, and recursive agent networks.

Enables AI agents to route HTTP requests through millions of real residential IPs, bypassing anti-bot systems and geo-targeting by country or city.

Authenticating reverse proxy for MCP servers providing credential isolation, OAuth2 token management, and composite tool aggregation.

Enables connecting and managing multiple backend MCP resource servers of Stdio, SSE, and Streamable HTTP types, then exposing their aggregated tools and resources through unified SSE/HTTP endpoints or as a single Stdio server. It routes requests to the appropriate backend and supports optional web admin management, authentication, and concurrent client connections.

Enables connecting to and managing multiple backend MCP servers (Stdio, SSE, Streamable HTTP), aggregating their tools/resources, and exposing them through unified SSE, Streamable HTTP, or Stdio endpoints with routing, authentication, and optional web-based administration.

Enables connecting to and managing multiple backend MCP resource servers while routing tool and resource requests to the appropriate server and exposing their combined capabilities through a unified SSE, Streamable HTTP, or Stdio interface.

Enables per-profile tool filtering and enforcement for one or more upstream MCP servers, exposing only allowed tools and rejecting blocked calls, with Streamable HTTP serving and observability.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Enables connecting to and aggregating multiple backend Model Context Protocol servers, then exposing their combined tools and resources through unified SSE, Streamable HTTP, or Stdio interfaces. It also supports optional web-based management, tool control, authentication, and live configuration reloads.

Enables connecting and managing multiple backend MCP servers and exposing their aggregated tools and resources through unified SSE or Streamable HTTP endpoints, or as a Stdio server, with request routing and optional authentication.

Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.

An MCP server that acts as a governance proxy for AI agents, evaluating each tool call against policies before execution, enabling secure and controlled access to systems like Slack, GitHub, and AWS without exposing credentials to the agent.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Enables connecting, aggregating, and routing multiple backend Model Context Protocol servers (Stdio, SSE, and Streamable HTTP) by exposing their combined tools and resources through unified SSE/HTTP endpoints or a single Stdio interface, with optional authentication and web-based admin management.

Enables aggregation, filtering, transformation, and composition of tools from multiple MCP servers through a single proxy with tool views.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

A gateway server that enables agentic hosts to access multiple MCP servers through a single namespaced connection or proxy a specific server from MCP-Hive. It provides built-in discovery tools to list available servers, tools, and resources for seamless integration.

Enables connecting multiple remote HTTP MCP servers through a single local stdio endpoint, handling OAuth authentication, token refresh, and namespace-scoped tools.

A flexible proxy that enables discovery and execution of tools across multiple Model Context Protocol (MCP) servers and JavaScript functions, reducing context size even when dealing with hundreds of tools.

A self-hosted, OAuth-fronted MCP proxy that lets Claude custom connectors reach RapidAPI's MCP endpoints by injecting API credentials, with per-upstream tool filtering and rate limiting.

Enables connecting to and aggregating multiple backend MCP resource servers, exposing their combined tools and resources through unified SSE or Streamable HTTP endpoints, or as a single Stdio server. It handles request routing, optional authentication, and tool/resource management.

Enables Claude Code and Codex agents to message each other directly through a shared local room, with blocking send/wait calls, file claims, auto-wake hooks, and a turn cap so users no longer copy-paste between windows. A live browser board lets users watch the exchange and inject their own instructions at any time.

Aggregates multiple MCP servers into a single endpoint, enabling LLM clients to access tools, resources, and prompts from various backends through one connection.

A semantic proxy that reduces AI agent token usage by exposing only three core tools and using local vector embeddings to search for and execute hundreds of underlying MCP tools. It streamlines communication between agents and MCP Routers by identifying relevant tools through natural language queries.

Reverse proxy for the Tavily MCP endpoint that bypasses geo-blocking, rotates API keys based on quota, and authenticates clients via access keys.

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.

Authenticates with Databricks via OAuth and exposes remote MCP tools from Databricks applications, enabling interaction with Databricks-hosted tools through Claude.

Lets local MCP clients use one LightNow-managed MCP entry instead of storing every MCP server configuration and secret in every client.