Governance proxy for MCP servers. Wraps any MCP server with policy evaluation, human approval workflows, and hash-chain audit trails. Supports stdio and Streamable HTTP transports.
Wraps your existing MCP servers and checks each tool call against policy and live state before it runs.
Allow, block, or require a refresh, with a reason the agent can act on.
A zero-infrastructure, local proxy that wraps any stdio MCP server to add audit logging, policy enforcement with regex guards, and per-session/per-day budgets.
A fail-closed policy boundary that translates local stdio MCP clients to authenticated Streamable HTTP servers, enforcing allowlists or read-only modes and redacting credentials from audit trails.
Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.
A least-privilege enforcement proxy for MCP servers. It sits between MCP clients and upstream servers, enforcing tool policies, hiding denied tools, requiring human approval for risky actions, and providing a structured audit trail.