"Unofficial Minecraft Proxy (MCP) Server" matching MCP servers:

Enables fetching web URLs through authenticated residential egress with provider, country, and session controls. It also exposes tools for checking the exit IP, account status, and masked connection URL.

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.

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.

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.

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.

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.

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 MCP clients to access Notion through a permission-checking proxy that restricts operations to a configured root page and its subtree, while blocking unauthorized tools. It also handles Notion OAuth and validates signed permission settings.

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.

A transparent proxy and execution firewall that intercepts and audits AI agent tool calls against configurable security policies before forwarding them to downstream MCP servers. It provides safe execution environments with features like data redaction, anti-loop protection, and unified alert dispatching.

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 MCP clients to discover and call Danske Bank public APIs through a hosted MCP server, adding OAuth/mTLS authentication and endpoint URL validation via a local call_endpoint tool.

MCP server for Nginx Proxy Manager: manage proxy hosts, redirections, streams, Let's Encrypt certificates, and access lists, with dry-run previews on every change and a one-shot HTTPS host workflow.

Enables Claude to read and modify an Nginx Proxy Manager instance through its API, covering proxy, redirection, and 404 hosts, streams, certificates, access lists, audit logs, and any other API endpoint. Changes are merged into existing objects and guarded by read, change, and destructive safety levels that require user confirmation before anything is altered.

Enables MCP clients to authenticate through OIDC and call protected tools while rejecting unauthenticated requests.

Enables managing Nginx Proxy Manager resources like proxy hosts, redirection hosts, streams, access lists, certificates, users, and settings through MCP, with automatic JWT refresh and configurable transport modes.

Enables transparent security for any MCP server by intercepting tool calls, blocking prompt injection attempts, masking PII in responses, and writing immutable audit logs.

Publishes a shared MCP endpoint where API-key users in different groups see and call only the tools their policies permit, mixing remote upstream tools with local ones. Tool discovery and execution are both filtered, hidden-tool calls are denied before their handlers run, and every action is tagged with subject and group in structured JSON logs.

Aggregates multiple backend MCP servers (Stdio, SSE, and Streamable HTTP) into a single hub, exposing their combined tools and resources through unified SSE or Streamable HTTP endpoints, or as a Stdio server, while routing requests to the correct backend. Adds API-key/bearer-token endpoint security, per-tool enable/disable and renaming, and an optional web admin UI with live config reload, install monitoring, and a web terminal.

Enables AI clients to connect to remote OAuth 2.0-protected MCP servers through a zero-config stdio-to-Streamable HTTP bridge with automatic discovery, PKCE login, and silent token refresh.

Enables OAuth-only clients such as claude.ai to use Trilium Notes' built-in MCP tools by handling browser login and forwarding requests to Trilium with each client's ETAPI token.

Enables AI agents to safely query Kingdee Cloud Galaxy ERP with read-only mode, write confirmation gates, and full audit logging.

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

Enables multi-user, network-reachable MCP interaction with Redmine, with per-user impersonation and identity-based access control.