"All items" matching MCP servers:

MCP server for Kibana / Elasticsearch — log search, aggregations, index discovery, and dashboard browsing. Hits Elasticsearch REST API directly for log queries; falls back to Kibana Console proxy when no direct ES URL is configured. Supports ApiKey auth (best for agents), Basic auth, and anonymous access. All 5 tools are read-only (readOnlyHint: true). Returns structured JSON (outputSchema).

🔌 Complete MCP server for Zabbix integration - Connect AI assistants to Zabbix monitoring with 40+ tools for hosts, items, triggers, templates, problems, and more. Features read-only mode and comprehensive API coverage.

A locally-hosted MCP (Model Context Protocol) server that gives Claude real tools to debug Docker containers — fetch logs, inspect memory/CPU, and run diagnostic commands inside a container, all from a chat with Claude Desktop.

An MCP server that exposes macOS-native device trust signals — the facts about a Mac that cannot be gathered from a Linux container or a cloud runner. All tools are strictly read-only.

Extends the official Google Ads MCP with a safe write layer for creating paused-by-default Search campaigns and an account auditor, all running locally with no hosted dependencies.

Enables AI agents to query Oracle WebLogic Server runtime state, health, and JVM metrics through the REST management API, and to start, shut down, or force-shut-down servers via Node Manager, all under a least-privilege account with allowlisting, read-only mode, and JSON audit logging for every call.

A read-only MCP server that lets an AI agent inspect a ROS2 graph, its underlying DDS participants, readers, writers and QoS mismatches, and recorded bag files, with twelve typed tools that behave the same against a live robot or built-in mock fixtures. It has no write path at all, so it can never publish to the bus or command a robot.

MCP server exposing Tracearr's Public API v2 as read-only tools to query Plex, Jellyfin, and Emby monitoring data such as watch history, active streams, media, users, libraries, and recently added items.

Lets AI assistants query Dynatrace Managed environments — services, traces, metrics, pods, and problems — by running read-only GET requests through your already logged-in browser session, so no API tokens are needed. All traffic stays on your machine between the AI client, a local server, and a browser extension.

Performs comprehensive website health audits including SSL, DNS, email authentication, performance, uptime, and broken link checks, all without requiring API keys. Returns a scored report with weighted metrics and actionable recommendations.

Enables AI coding agents to observe real-time Node, Vite, Next.js, Storybook, TypeScript, and browser runtime errors from a wrapped dev server, source-mapped to exact file, line, and column with the log lines preceding each crash. It exposes MCP tools for listing open errors, fetching full stack details, and checking or marking fixes as resolved, all locally with no code changes.

Lets an AI assistant inspect a Linux machine through ten fixed read-only tools covering load, memory, disks, processes, ports, interfaces, systemd units, the journal, and allowlisted log files. All output is size-capped, control-character-stripped and secret-redacted, and nothing in the package can write to the system.

Enables AI assistants to query privacy-first web analytics from Measure.events, including pageviews, top pages, referrers, and custom event tracking, all via natural language.

Enables AI tools that support the Model Context Protocol to query Plausible Analytics traffic and conversion data, break metrics down by page, source, country, device, and UTM parameters, and compare two date ranges side by side. All query tools are read-only and work with either a hosted bring-your-own-key endpoint or a local STDIO install.

Enables an agent to list configured websites and fetch all connected SEO data for a site in a single call, drawing from Search Console, GA4, PageSpeed Insights, Chrome UX Report, Bing Webmaster Tools, and Microsoft Clarity while reporting per-source status.

Lets an MCP client read live power from a local IoTaWatt energy monitor over its HTTP API, query history logs for energy and interval data, inspect device configuration and channel definitions, and sample current waveforms to identify load types. All tools are read-only and require no cloud account.

Connects Huawei AppGallery Connect operational data to any MCP-capable AI client, letting users analyze report trends across 16 report types, crash and AppFreeze metrics, review and rating insights, and generate Markdown daily or weekly digests. All 13 tools are strictly read-only, run with zero dependencies, and keep credentials in memory only.

Enables Claude to capture screenshots, watch your screen in real-time, read text via OCR, and analyze video files, all running locally as an MCP server.

Reads the Claude Code, Codex and OpenCode usage logs already on your machine and reports token totals, per-day and per-hour activity, a per-agent and per-model breakdown, and a year-in-review recap. It makes no network request at all — a test fails if any source file in the package can open a socket.

Enables AI agents to diagnose broken XAMPP/WAMP localhost stacks by inspecting real machine state — running processes, listening ports, HTTP probes, and Apache/MySQL error logs — to pinpoint port conflicts, startup crashes, unclean-shutdown damage, and zombie processes with plain-English explanations. All diagnostics are read-only, so agents can safely answer questions like why Apache won't start or why localhost refuses to connect instead of guessing.

Provides comprehensive Firewalla MSP firewall integration via MCP protocol with 28 tools for real-time security monitoring, network analysis, bandwidth tracking, and rule management. Supports all MCP-compatible clients for automated network security operations.

UniFi semantic-analysis MCP — 54 tools on Site Manager API and Cloud Connector. 8 workflow Prompts (4 fleet-ops + 4 MSP). Read-only.

Airflow MCP server — read DAGs, runs, task instances, log tails; trigger and clear (write-gated).

Enables access to SORACOM IoT platform data including Harvest sensor data, file storage, SoraCam camera footage/events, and SIM statistics through authenticated API calls.

Enables AI clients to inspect a running Unity editor's state and capture console and compiler errors, trigger asset refreshes to recompile externally edited scripts, and execute editor menu items. It closes the edit → compile → check loop by bridging tool calls to the editor main thread over a local-only HTTP listener.

Scheduled scans across all Binance spot and perpetual pairs using CEL rules (RSI, volume, MAs, price action). Runs server-side 24/7, fires webhooks on match, with delivery proof and alert explainability.

Enables incident management and on-call operations for the All Quiet platform, allowing MCP clients to triage incidents, check who is on call, and access the full public API through generic tools.

Enables AI agents to investigate Splunk exports or live queries using deterministic detectors and an iterative analysis loop, all running locally without data leaving the machine.

Enables centralized management and monitoring of multiple distributed worker MCP servers. Provides tools to list workers, get status of all workers, and query specific worker status.

MCP server for On-Call Health burnout analysis. Connects AI assistants to your on-call data for workload insights.