"Understanding Proxies or Proxy Servers" matching MCP servers:

A zero-dependency Node.js playground for debugging how MCP clients authenticate to an MCP server over HTTP.

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.

Enables connecting multiple accounts to remote MCP servers like Slack, Sentry, and Trello through a single OAuth-fronted proxy, with per-account URLs and token handling.

It's a safety middleware that can detect and intercept self-harm and criminal intent at 3 stages. It allows developers of chat-based platforms to configure webhook notifications and store encrypted information for prior mitigation of any such cases.

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

Enables running a FastMCP server behind a Caddy reverse proxy that enforces bearer-token authentication, so MCP clients can access tools over HTTP only with a valid token.

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

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.

Acts as a secure OAuth 2.0/2.1 proxy gateway for MCP servers, enabling integration with Claude and ChatGPT platforms.

Enables secure MCP traffic by filtering threats with a 3-stage detection pipeline, applying RBAC policies, and redacting sensitive data in real-time via an SSE-inspecting proxy.

MCP proxy server for SAP ABAP ADT that adds JWT authentication and forwards requests to target MCP servers.

A self-hosted proxy that enables per-user credential injection for upstream MCP servers, allowing users to securely connect services like GitHub and Confluence via one-time links without exposing credentials to the LLM.

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

Provides tools for DeepTempo AI SOC including findings and case management, investigation workflow orchestration, action approval workflows, and MITRE ATT&CK layer generation.

OpenAI-compatible proxy with PII scrubbing, audit logging, and model routing. Drop-in replacement — set OPENAI_BASE_URL to point to this server. Supports GPT-4o, Claude, Gemini, and Llama via single endpoint.

A generic single-upstream MCP authentication proxy that wraps remote Streamable HTTP MCP servers behind Horizon OAuth, enabling clients to connect securely without carrying upstream API keys. It adds a fixed authentication header to upstream requests and supports bearer tokens, API keys, and custom headers.

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.

Enables Claude Code to use remote MCP servers already authenticated in Codex by reusing Codex OAuth tokens and forwarding JSON-RPC messages without requiring a second OAuth flow.

Manages an authorized proxy pool for security testing, providing MCP tools to select the best available proxy, report status, switch proxies, view pool health, and register nodes, backed by health checks and audit logging.