"Generating PowerPoint slides from Power BI datasets in folders" matching MCP servers:

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

An AI-powered Power BI dataset health monitor that connects Claude to a simulated Power BI tenant for running health checks, diagnosing failures, and prioritizing fixes.

Read-only AMD GPU monitoring for Claude on Linux — VRAM, temperature, clocks, power, and running ML processes via rocm-smi.

Enables data observability operations with the Sifflet platform. Supports exploring assets, monitors, incidents, generating monitor-as-code YAML from descriptions, and performing impact analysis.

Enables local-first observability for MCP agent workflows by recording tool calls, prompts, latency, and token usage in a local SQLite database, and provides tools for inspecting, comparing, exporting, and generating dashboards from traces.

An MCP server that enables AI agents to query real-time NVIDIA GPU metrics like utilization, memory, temperature, and power without external monitoring tools.

MCP server for Grafana enabling management of dashboards, datasources, alert rules, folders, and annotations via stdio.

Enables AI agents and MCP clients to query and debug traces, sessions, observations, and exceptions, plus access prompts, datasets, annotation queues, scores, and metrics from a local server.

Enables management of VMware vSphere/ESXi vCenters and standalone hosts across multiple named environments, covering read-only inventory introspection plus policy-gated destructive operations like VM deletion, snapshots, and power actions. Adds a guardrail layer with declarative policy, two-phase confirmation tokens, append-only audit logging, and optional human-in-the-loop web approval.

Enables AI agents to locally query and debug traces, sessions, exceptions, route decisions, prompts, datasets, and metrics from any MCP client. Supports token-efficient output control, selective tool-group loading, and a read-only mode for safer access.

Enables AI agents to manage Dell PowerEdge servers via Dell OpenManage Enterprise (OME) REST API, providing tools for device inventory, power control, firmware updates, alert management, and compliance baselines.

Enables management of oVirt / Red Hat Virtualization environments via AI assistants, supporting VM lifecycle, power operations, snapshots, and infrastructure queries.

Enables AI agents to query and debug trace data from Langfuse, including sessions, exceptions, prompts, datasets, metrics, and annotation queues, through the Model Context Protocol.

Enables AI agents to query traces, sessions, exceptions, prompts, datasets, annotation queues, scores, and metrics from a Langfuse instance for local debugging and observability, with read-only mode and selective tool-group loading.

Enables AI agents to debug and observe LLM applications by querying traces, sessions, observations, exceptions, route decisions, prompts, datasets, scores, and metrics from Langfuse, with compact output modes, selective tool loading, and an optional read-only mode.

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

Enables classification of GPU workloads as training, inference, or idle from telemetry data, with tools for one-shot classification, benchmarking, and audit log verification.

Provides MCP tools to create and query SigNoz trace funnels, enabling agents to measure their own step conversion rates from within the agent loop.

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