mcpcat-typescript-sdk
Verified Safeby MCPCat
Overview
MCPcat is an analytics platform designed for MCP server owners to capture user intentions and behavior patterns, offering session replay, trace debugging, and integration with existing observability tools.
Installation
No command providedEnvironment Variables
- DD_API_KEY
- DD_SITE
- DD_SERVICE
- SENTRY_DSN
- SENTRY_ENVIRONMENT
- SENTRY_RELEASE
Security Notes
The SDK performs outbound network calls to its own API (api.mcpcat.io) and configured telemetry exporters (Datadog, Sentry, OTLP). Sensitive configurations like API keys and DSNs are expected to be provided by the user, typically via environment variables, and are not hardcoded within the SDK. The SDK includes a redaction mechanism with a customizable function and a list of protected fields, which is a strong security feature for sensitive data. No 'eval' or obvious obfuscation was found. Local log files (`~/mcpcat.log`) might contain event information, but this is server-local and not exfiltrated by the SDK.
Similar Servers
mcp-shark
Aggregate multiple Model Context Protocol (MCP) servers into a single unified interface with a powerful monitoring UI, enabling real-time traffic capture, logging, and AI-powered security analysis.
mcp-servers
An MCP server for fetching, cleaning, and intelligently extracting content from web pages, designed for agent-building frameworks.
mcpcat-python-sdk
Analytics platform for MCP server owners to capture user intentions, behavior patterns, and forward telemetry to observability platforms.
mcpc
A framework for building agentic Model Context Protocol (MCP) servers by composing existing MCP tools. It enables the creation of portable, interoperable AI agents with flexible execution modes and robust logging/tracing capabilities.