"A tool for browsing the web" matching MCP servers:

这是面向智能运维场景的 MCP 工具服务，让 Agent 能够按需检索日志内容并获取主机与应用的监控指标数据。它把实时的日志与指标证据接入 Plan-Execute-Replan 诊断流程，从而支撑自动故障排查与根因分析。

16-tool MCP server for Google PageSpeed Insights & Chrome UX Report APIs. Analyze, compare, and optimize web performance directly through Claude, Cursor, or any MCP-compatible AI client.

Enables natural language queries of the Chrome UX Report API to fetch Core Web Vitals (LCP, INP, CLS, FCP, TTFB), compare form factors, benchmark pages against site averages, and analyze up to 40 weeks of performance trends.

Enables an LLM agent to investigate a Kong Gateway through fourteen read-only, schema-validated tools and a deterministic diagnostic engine, so it can trace routes, services, plugins and upstream health and explain faults such as why authentication is failing on a path. Every fact comes from the gateway itself, and the model only selects tools and writes the evidence-backed explanation.

Enables AI agents to manage prompts and sessions via the ai-agent-logs API, with tools for health checks, login, listing/creating prompts, and retrieving sessions.

Look up what the official MCP Registry declares for a server and what Lowdown observed: daily reachability, HTTP status, tool names and tool-schema changes over the last 30 days, plus outcomes reported by agents. A public time-series record for a fixed sample of 5,000 Registry servers. Recorded facts only, no scores or rankings. Raw data: CC BY 4.0.

Privacy friendly, cookieless web analytics built MCP-first. "Add analytics to my Next.js app" → an AI agent runs the setup_analytics_for_site tool, picks the right install snippet, edits your layout file, and verifies the script is loading. OAuth onboarding, no API keys to paste.

Enables LLMs to interact with Kibana through composable toolboxes for building dashboards, managing data, and handling alerts, among other operations.

Enables observability and governance for local LLMs via Ollama, including auditing model usage, scanning prompts for secrets/PII, and enforcing allow/deny policies.

Enables agents to inspect localhost web applications through Chrome DevTools Protocol by listing Chrome targets, attaching to a page, capturing and querying network, console, navigation, and WebSocket events, and managing ephemeral sessions.

A FastMCP-based tool for interacting with Splunk Enterprise/Cloud through natural language. This tool provides a set of capabilities for searching Splunk data, managing KV stores, and accessing Splunk resources

Enables AI agents to interact seamlessly with Splunk environments through 20+ tools for search, analytics, data discovery, administration, and health monitoring. Features AI-powered troubleshooting workflows and supports multiple Splunk instances with production-ready security.

Connects AI assistants to the Vectra AI security platform to enable intelligent analysis of threat detection data and automated incident response workflows. It allows users to investigate threats, take response actions, and generate security reports using natural language.

Provides a standardized way for MCP clients to interact with Apache Airflow's REST API, supporting operations like DAG management and monitoring Airflow system health.

MCP server for the Production Master incident-investigation service, enabling any MCP client to drive investigations via tool calls with pass-through authentication.

Connects AI-powered tools to the Confident AI platform for evaluating, observing, and iterating on AI quality, enabling cloud evaluations, dataset management, prompt versioning, production tracing, and human annotations directly from editors like Cursor and Claude Code.

A Model Context Protocol server that provides AI assistants access to AWS CloudWatch Logs, enabling browsing, searching, summarizing, and correlating logs across multiple AWS services.

Ships only the MCP server, not the recorder. Recording works by wrapping a process on the host — a local proxy, a PATH shim, a shadow git index. None of that survives a container boundary, so orca record inside here would watch an empty namespace. What does travel is the read side: the six MCP tools serve runs that already exist on disk, so a client mounts its .orca directory and r

Enables users to log AI tool activity without conversation text and contribute back only user-approved, small-cell-suppressed counts through a local MCP interface.

A flight recorder for Claude Code that captures tool calls and observations into a SQLite database, then classifies them into a distilled timeline for incident troubleshooting.

Enables MCP clients to call Cloudflare Workers-hosted tools while automatically tracking events, checkpoints, and tool calls in Agnost AI analytics.

Enables MCP clients to call a hello tool and access observability features, including metrics and request traces, through a Streamable HTTP transport with SQLite-backed storage.

MITM proxy MCP server that intercepts and verifies AI agent tool calls, detecting fabrication, tracking costs, verifying outcomes, and inferring user satisfaction.

A read-only MCP server for operator-grade release inspection and benchmark browsing.

Enables AI agents to read Grafana dashboards, alert rules, and query datasources (Prometheus, Loki, etc.) through MCP tools, integrating Grafana monitoring into the IDE.

Enables Claude Desktop to access the hosted Web Speed API through MCP, requiring only an API key for setup.

A security checkpoint for AI agents that intercepts and polices tool calls with allow/block/ask verdicts, taint tracking, and audit logging.

Self-hosted web analytics platform that exposes analytics data via the Model Context Protocol, enabling natural language queries about traffic, page views, web vitals, and custom events.

A live post-mortem debugger MCP server for Home Assistant that lets AI agents list captured exceptions, walk traceback frames, read local variables, and optionally evaluate Python in the context of a captured frame for true post-mortem debugging.

A verifying MCP gateway that pins approved tool manifests and skill files to content addresses, blocking tampered descriptions before they reach model context.