Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.
A reliability & security proxy for the Model Context Protocol (MCP).
Self-healing connections, runtime tool-security, and a compliance-mapped audit trail for your MCP servers.
mcp-bastion sits between your MCP client (Claude Code, Cursor, Cline, Windsurf, Zed, Claude Desktop, or any MCP-compliant agent) and your MCP servers. It is client-agnostic — it works with any compliant client through configuration alone, with zero client-specific code — and non-invasive: your servers run unchanged, and removing Bastion is a one-line config revert.
- Why - How it works - Features - Quick start - Demo - Control tools - Configuration - Transports - Runtime security - Audit & compliance - Client setup - Architecture - Development - Roadmap - Contributing - Security - License
When an MCP server disconnects mid-session, the agent only sees a generic "No such tool available" error — indistinguishable from a tool that never existed — and it cannot reconnect; only a human can. Long agent sessions silently lose capabilities and fail in confusing ways.
Bastion closes that gap. It health-checks every server, auto-reconnects with backoff, and — crucially — exposes control tools so the agent itself can inspect connection health and recover a dropped server without human intervention.
Bastion now spans three layers: reliability (v0.1), runtime security (v0.2 — tool pinning / rug-pull & poisoning detection), and audit & compliance (v0.3 — pluggable sinks mapped to NIST AI RMF / OWASP LLM Top 10). See the roadmap.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Gowthaman90--mcp-bastion.html)
MCP server for Asterisk and FreeSWITCH. Lets AI assistants inspect channels, SIP registrations, trunk status and dialplan on a live PBX.
0xwilliamortiz/openclaude-improvedruns anywhere. uses anything
agent-chaperone/agent-chaperoneScreens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
slxca/opencontextA Model Context Protocol server for persistent project-specific AI agent context.
polymind-inc/agent-framework-jsA TypeScript implementation of the Microsoft Agent Framework programming model, with semantic parity to the official .NET, Python, and Go implementations. Independent community project.
modulastack/modula-relayLocal MCP relay for cross-model agent teams. Your Claude, Codex, and other agents talk to each other over Unix sockets. No broker, no network, no accounts.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.