Mcp Proxy Python Packages

vgs-bc-mcp

Resilient MCP stdio proxy for Microsoft Dynamics 365 Business Central. Fork of microsoft/BCTech BcMCPProxyPython with reconnect, silent token refresh, and surfaced upstream errors.

authmcp-gateway

🔐 Secure authentication proxy for MCP servers with JWT auth, real-time monitoring, and admin dashboard. Production-ready Docker deployment.

agentveil-mcp-proxy

Independent control for AI agent actions. Use any agent. Route risky actions through one policy boundary before they send, deploy, push, publish, or spend.

memtomem-stm

Short-term memory proxy gateway with proactive memory surfacing for AI agents

agentveil

Independent control for AI agent actions. Use any agent. Route risky actions through one policy boundary before they send, deploy, push, publish, or spend.

mcp-airlock

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

360solutions-bc-mcp

Resilient MCP stdio proxy for Microsoft Dynamics 365 Business Central. Fork of microsoft/BCTech BcMCPProxyPython with reconnect, silent token refresh, and surfaced upstream errors.

gcf-proxy

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.

helio-client

Governance proxy for MCP: block or hold AI agent tool calls on their arguments, route approvals with the arguments shown, enforce rules the model cannot argue with, require prerequisites, cap cumulative spend across tools and servers, and audit every call. No changes to agent code or MCP servers.

preloop

The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails

mcp-relay

Use your local MCP servers from a cloud AI agent: one authenticated endpoint, outbound connection only, no port forwarding.

preloop-hermes-plugin

The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails

avp-agentmesh

Independent control for AI agent actions. Use any agent. Route risky actions through one policy boundary before they send, deploy, push, publish, or spend.

langchain-preloop

The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails

mcp-secure-remote

Model Context Protocol Proxy using MTLS ( npx & uvx )

langchain-sidclaw

The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-demo

agentmesh-avp

Independent control for AI agent actions. Use any agent. Route risky actions through one policy boundary before they send, deploy, push, publish, or spend.