inspector
by modelcontextprotocol
Overview
Inspect, debug, and interact with Model Context Protocol (MCP) servers, including OAuth authentication flows, resource management, and tool execution.
Installation
npm run devEnvironment Variables
- HOST
- CLIENT_PORT
- SERVER_PORT
- DANGEROUSLY_OMIT_AUTH
- ALLOWED_ORIGINS
- INSPECTOR_URL
Security Notes
The server component (MCP Inspector Proxy) presents critical security risks. It directly parses untrusted JSON strings from URL query parameters ('query.env') and HTTP headers ('x-custom-auth-headers', 'x-mcp-proxy-auth') using `JSON.parse`. This is a severe JSON injection vulnerability, potentially leading to prototype pollution or remote code execution, depending on the JavaScript runtime. Furthermore, the proxy functionality directly accepts a server URL from query parameters ('query.url') and uses it to initiate connections (`SSEClientTransport`, `StreamableHTTPClientTransport`). This creates a Server-Side Request Forgery (SSRF) vulnerability, allowing an attacker to force the proxy to make requests to arbitrary internal or external systems. The use of `shell-quote` to parse arguments from query parameters (`query.args`) for spawning external commands also adds a potential command injection risk. While a session token is generated on startup for proxy authentication, it can be bypassed using the `DANGEROUSLY_OMIT_AUTH` environment variable, which could lead to unauthorized access if misconfigured. These vulnerabilities make it extremely unsafe to run in any environment where it might be exposed to untrusted users or the public internet.
Similar Servers
chrome-devtools-mcp
Enables AI coding agents to control and inspect a live Chrome browser for reliable automation, in-depth debugging, and performance analysis via the Model-Context-Protocol (MCP).
mcp-grafana
Provides an MCP interface to Grafana, enabling AI assistants to interact with dashboards, datasources, Prometheus, Loki, incidents, alerting, OnCall, Sift, Pyroscope, and admin functionalities for observability and automation.
AgentUp
AgentUp is an infrastructure framework for developing, deploying, and managing production-ready AI agents, providing Docker-like consistency, security, and extensibility.
AgentUp
A developer-first framework for building, deploying, and managing secure, scalable, and configurable AI agents, supporting various agent types (reactive, iterative) and the Model-Context Protocol (MCP) for seamless interactions.