proxy
42 servers · 910★ total
Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.
Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
One endpoint in front of unlimited MCP servers and REST APIs. The agent sees a fixed ~15-tool surface however many you connect, so tool-list token cost stays flat (about 89% less on a 100-tool stack) and the savings climb as you add more. Single Rust binary.
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway. One YAML Lens wraps any MCP, 20 included (Postgres, MySQL, MongoDB, GitHub, Stripe, Snowflake, etc.). 84% fewer tokens, ~3x faster, holds PII leaks. AGPL or commercial.
ChatGPT app template using Pomerium, OpenAI Apps SDK and Model Context Protocol (MCP), with a Node.js server and React widgets.
🐕 Universal MCP Server Manager - Configure once, manage multiple MCP servers through a single interface. Perfect for Claude Desktop, Claude Code, Cursor, Gemini CLI & AI assistants. Web dashboard, auto-detection, unified proxy layer.
MCP that can proxy any GraphQL API and expose graphql operations as mcp tools.
Shared MCP gateway with schema deferral, response shielding, and HTTP daemon mode. Replaces 12+ MCP servers with 6 tools — saves ~99% context tokens and ~2.7GB RAM. npm: harshal-mcp-proxy
Self hosted secure gateway for AI agents. One token. Full control. Complete audit trail.
Open-source browser automation broker for AI agents: persistent Chrome profiles, proxy-aware identities, remote API, MCP tools, browser-use/OpenBrowser adapters, human auth handoff, telemetry, and audits.
Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server and persist traces to SQLite, Postgres or MySQL.
The Open-Source MCP Firewall & Security Gateway for AI Agents. Inspect, redact, and control tool calls. Proxy mode (universal) and Inline SDK mode (Go).
SSH MCP Server - AI manages remote servers via SSH. Multi-server, SFTP zero-token transfer, SOCKS5 proxy, jump host, 2FA, async transfer with progress.
Governance proxy for MCP - enforce policies, cap cumulative cross-tool spend, route approvals, check evidence, and audit every AI agent tool call. No changes to agent code or MCP servers.
MITM proxy for Claude Code with real-time TUI, web UI & MCP server — intercept, inspect, and send messages to the Anthropic API. Headless mode for automation.
MCP proxy server that reduces LLM context overhead with on-demand tool loading from multiple upstream servers.
Multiplexer for MCP tool calls: parallel execution, batching, caching, and pipelining for any MCP server
MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.
Open source control-plane proxy for AI agents: identity, policy, budget, audit for MCP and beyond
MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.
MCP proxy server — 85-96% token savings via lazy tool loading & fuzzy search across 100+ MCP servers. npm i mcp-tool-search
Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shadowing defense, and NIST AI RMF + OWASP LLM Top-10 audit trails for any MCP server. Works with Claude, Cursor, Cline, Windsurf.
Open-source security gateway for MCP tool calls — blocks secret leaks, enforces agent policies, and requires human approval for risky actions
The open-source run log for MCP agents. Get a shareable report to verify and reproduce what the agent did — plus a protective mode for common dangerous SQL.
Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.
Docker image to run a self-hosted MCP (Model Context Protocol) gateway with Bearer token auth. Multi-server hub powered by MCPHub + Caddy. Streamable HTTP + SSE transport. Access filesystem, fetch, GitHub, Brave Search, Git, PostgreSQL, memory, and more from a single endpoint. Multi-arch: amd64, arm64.
Drop-in MCP proxy for debugging AI agents. Real-time timeline, replay, diff. Local-first, no telemetry, one binary.
Open-source zero-trust proxy for MCP servers — adds OAuth 2.1, tool-level RBAC, audit logging, and rate limiting to any MCP server. One Docker command, zero code changes.
The guardian layer for AI agents — identity, secrets, audit via MCP. Gate + Vault + Watch.
Orchestrate multi-hop pivots, SOCKS/forwards, and intranet recon through MCP tools. Authorized use only.
Intercept & tamper proxy for MCP traffic — X-ray and rewrite the JSON-RPC between an AI agent and its MCP servers. Burp Suite for AI agents. Authorized testing only.
Self-hosted MCP gateway/proxy for AI agents — OIDC auth, Casbin RBAC/ABAC, circuit breaking, PII redaction, a 42-connector catalog, and a full admin dashboard. TypeScript.
Open-source MCP governance proxy -- authentication, authorization, audit, and a marketplace for AI tools. Self-hosted via Docker.
Smart MCP proxy — connect N MCP servers, expose one endpoint with discover/describe/call meta-tools
Skill + browser MCP for Claude Code and Codex: your app and browser reach domestic services over the real ISP while the agent stays on the VPN. Per-socket binding, per-host routing, no admin, nothing global.
Security proxy for MCP servers. Catches indirect prompt injection attempts before they reach your AI agent.
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard, mTLS, semantic shell analysis, STRIDE threat model
A multi-profile proxy for the AWS MCP Server: opens one SigV4-signed connection per AWS profile and adds a profile argument to every tool, so a single client connection can reach multiple AWS accounts. Needs no config file, no uvx and no mcp-proxy-for-aws.
Transparent MCP proxy for agent observability. Logs every tool call, exposes trace history, reduces token overhead.