"A method to allow vision models to process and understand image files" matching MCP servers:

Enables interaction with Google Cloud services including billing cost analysis, log querying, and metrics monitoring through natural language commands. Provides comprehensive tools for managing GCP resources, analyzing costs, detecting anomalies, and retrieving operational insights.

Fetches Langfuse observability traces directly into a VS Code coding agent's context, enabling querying and viewing trace data through natural language.

An MCP server that provides cost and reliability observability for LLM and agent workflows. It records model calls and allows querying and aggregating telemetry data through MCP tools.

Enables precise measurement of live HTTP and WebSocket services while maintaining an append-only, evidence-based ledger of claims that agents can query with explicit timestamps, staleness indicators, and instructions for re-verification.

Enables AI agents to monitor Docker containers, system resources, ports, and logs in real-time.

Read-only MCP server for TrueNAS Scale debugging, providing k3s tools for kubectl operations and whitelisted midclt calls for system info, apps, and pools.

A production-oriented reliability, benchmarking, and evaluation system that layers multi-version protocol negotiation, adaptive streaming, connection pooling, and resilience onto an MCP agent runtime.

Provides governed MCP tools for querying optionally restricted Microsoft Sentinel/Log Analytics tables and optional Defender XDR hunting data, retrieving incidents and entities, and—for agent identities only—adding attributed incident comments, with Entra ID authentication, KQL validation, rate limits, and redacted audit logging.

Enables Claude to discover and understand infrastructure-as-code drift by listing projects with drift, analyzing Terraform plan outputs, and providing remediation information.

Live .NET runtime diagnostics for AI assistants. Ask Claude to diagnose memory leaks, GC pressure, LOH fragmentation, and thread starvation in any running .NET process — no code changes required.

Enables investigation and diagnosis of CIB Seven BPM process instances through the CIB Seven REST API. Supports querying process instances, incidents, activity history, and BPMN definitions with Keycloak authentication and configurable variable redaction.

A comprehensive Linux system performance profiler with MCP remote invocation support, featuring advanced process profiling and flame graph generation.

Exposes system telemetry tools to retrieve CPU, memory, disk, battery, network, process, and GPU metrics from a local machine.

Enables read-only Kubernetes cluster inspection through MCP, with namespace allow/deny and resource block policies enforced before any API call.

This project provides a Model Context Protocol (MCP) server that allows language models and other MCP clients to interact with a SuzieQ network observability instance via its REST API.

Сonnects to live JVMs via JDWP protocol, enabling LLM agents to autonomously debug Java applications — attach to a running process, pause threads, set breakpoints (including conditional), inspect stacks with auto-resolved object fields, evaluate methods, set variable values, and diagnose issues like deadlocks and hung queries.

Enables MCP clients to inspect an ISOTEL IDM smart gateway's devices, parameters, records, protocol stacks, streams, and connections, with read-only tools by default and opt-in allow-listed validated writes.

Enables AI-powered analytics for OpenReplay user sessions through natural language queries. Supports session search, user journey analysis, error tracking, performance metrics, and funnel analysis to understand user behavior patterns.

A read-only MCP server for Linux system monitoring and OS algorithm simulation, exposing tools for memory, filesystem, process, and CPU scheduling observations.

Provides AI agents with real-time system monitoring and control for creative workstations, enabling thermal management and process prioritization to prevent crashes.

Provides a governance layer for MCP servers, enforcing policy-based allow/deny/approval rules, requiring human approval for risky calls, and recording an auditable trail of every AI agent tool call.

Enables AI clients to create and configure monitors, subscribe to their evidence streams with durable cursors, and process observations with guaranteed at-least-once delivery.

Connects MCP clients to Gemini Cloud Assist APIs, enabling users to understand, manage, and troubleshoot their Google Cloud environment using natural language.

Enables AI agents and assistants to manage a SutramX workspace by listing and changing monitors, reading check results, handling incidents, and managing status pages through the SutramX API. Access can be limited to read-only or optionally allow destructive operations.

Enables AI assistants to monitor and analyze industrial process data from DCS/SCADA systems via MCP protocol, with domain expert knowledge for anomaly detection and recommendations.

Enables MCP clients to ask permission before an agent acts, returning allow, deny, or ask_human with receipts, and to monitor agent spend, limits, and recent decisions.

Enables read-only inspection and narrowly scoped maintenance of a local Docker Desktop environment, covering containers, images, logs, stats, Compose status, and Scout vulnerability/SBOM data, plus limited actions such as image pulls, container restarts, dangling-image pruning, and allowlisted Compose redeploys, all without exposing the raw Docker socket to the client.

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

A read-only observability server that lets external agentic AI clients query CPU, memory, load, uptime, allowlisted filesystem capacity, bounded process snapshots, and permitted journald logs. It also provides a JSON system summary resource and a safe health-check prompt, with no arbitrary shell or destructive operations exposed.

Enables LLM assistants to run guarded, read-only SPL searches and inspect Splunk indexes, saved searches, health, server info, and Enterprise Security notables using only a token, with enforced row caps, index allow-lists, command blocking, and audit logging.