"Allowing image imports via MCP" matching MCP servers:

An MCP server for querying Grafana Loki directly with a discovery-first workflow — labels, values, series, and LogQL queries without requiring Grafana.

Enables querying logs and metrics with plain SQL from any MCP client via pooml's read-only query API.

An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.

MCP server for system monitoring, enabling users to ask about CPU, memory, disk, network, and processes on their system.

Bridges Microsoft Clarity's analytics API with Claude, enabling custom date ranges and page-level filtering on top of Clarity's native limitations.

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

Model Context Protocol (MCP) server for debugging, analyzing, and diagnosing Kubernetes clusters directly from AI agents.

Enables AI agents to discover and call Xyte's device management API endpoints with typed validation, supporting fleet investigation, ticket management, and routine operations through natural language.

Read-only MCP server for XServer API, enabling Claude to check server status like disk usage, domains, mail, and cron via natural language.

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.

Unified observability gateway for AI agents — one MCP server for Prometheus, Loki, and any backend.

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).

Provides read-only access to daily trading figures for multi-site restaurant groups, detecting anomalies in control blocks such as void rates and labor percentages to uncover subtle financial leaks.

Relays error logs from other MCP servers when an LLM call fails and the returned error message is unclear, helping the model handle errors more intelligently.

MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.

Enables querying and analyzing Tenable Vulnerability Management audit logs, including activity summaries, API key usage, and anomaly detection through MCP tools.

Provides Claude with read-only access to PC diagnostics including hardware specs, live performance metrics, disk usage, network checks, and more, enabling natural language queries about PC health and performance.

Enables AI agents to self-report bugs, ambiguities, and improvement requests via a single report_issue tool, logging to PostgreSQL or JSONL with severity and mode classification.

Unofficial MCP server for Vexo analytics. Enables querying event names, counts, timelines, sessions, and recent events from Vexo Export API through natural language.

Enables LLM agents to monitor Mac thermals and control fan speed with safety limits enforced by a root daemon.