$ loading_
A drop-in proxy that secures MCP servers with policy and logging.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-doorman" yet — see the docs or source repo.
I want to put a proxy in front of an existing MCP server to block policy violations, redact sensitive data, and keep audit logs. Outline the integration approach.
Explains how to place the proxy in front of the MCP server and enable policy, redaction, and audit logging.
Explain how to use this MCP proxy to screen for prompt injection and reduce malicious instruction impact.
Describes how to use the proxy to screen for prompt injection.
I need to rate-limit MCP tool calls and keep audit records. Describe what this tool can provide.
Describes rate limiting and audit logging capabilities.
When a team exposes MCP servers to more users or clients, this proxy can enforce policy and security checks at the entry point. It helps reduce sensitive-data leaks and risky calls.
If you need to track who called which MCP capabilities, this proxy can keep audit logs. It fits compliance and incident investigation needs.
Before launching a new MCP service, you can put it behind this proxy for redaction, prompt-injection screening, and rug-pull detection. It adds a security layer without changing the service itself.
It is a drop-in proxy placed in front of MCP servers for policy enforcement, security checks, and audit logging. The description also says it supports secret redaction, prompt-injection screening, rug-pull detection, and rate limiting.
It mainly addresses sensitive-data leakage, prompt injection, rug-pull risk, excessive requests, and auditability needs.
The description calls it a drop-in proxy, which means it is used as a proxy layer. Specific integration and deployment details are not provided.
Secure MCP servers with policy checks, redaction, access control, and audit logs
Enforce permissions, approvals, sanitization, and audit for AI agent MCP calls.
Add security scanning, risk gating, and safe execution to MCP tool calls.
Proxy and manage multiple MCP servers through one secure unified interface.
Proxy multiple MCP servers while reducing token usage with on-demand tool loading.
Enforce policy checks on AI tool calls without exposing system credentials.