"Sublime Text" matching MCP servers:

An MCP server that exposes GPU-accelerated anomaly detection to AI assistants via the Model Context Protocol. Provides two MCP tools: waveguard_scan (send training + test data in one call, returns per-sample anomaly scores and top explanatory features) and waveguard_health (check API and GPU status). Works on time series, JSON, numbers, text, and images — fully stateless.

Diagnoses why a FiveM server or resource is broken by scanning local configs, manifests, and logs, returning ranked findings with evidence. It can also propose and apply low-risk text fixes when enabled.

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.

Enables querying Furiosa dashboard benchmark data and generating deep-link URLs to viewer pages such as commit comparisons, IR text, tactic debug, and TC viewer through MCP tools.

Lets coding agents read a local, redacted recording of the user's dev-browser session — pages, clicks, typed fields, API calls with their bodies, console errors and screenshots — so they can see what the user just did and what failed before asking. Exposes a recent-activity timeline tool with optional time, text and event-kind filters plus a tool that returns an individual screenshot as an image.

Enables querying OpenTelemetry logs stored in OpenSearch across development and production environments. Provides tools for searching logs by various criteria including free-text Lucene queries, trace IDs, service names, error levels, and specific fields.

Enables evidence-bearing change monitoring for public text pages, providing normalized diffing, SHA-256 hashing, and signed webhook notifications.

The MCP Internet Speed Test is a specialized Model Context Protocol (MCP) server that enables AI models and agents to perform internet speed measurements.

Enables querying and formatting Loki logs from Grafana via the Model Context Protocol. It supports LogQL queries, label retrieval, and provides results in text, JSON, or markdown formats.

Enables AI agents to run GPU acceptance tests on NVIDIA nodes you administer over SSH, executing DCGM diagnostics, a CUTLASS GEMM benchmark, HBM and PCIe bandwidth tests and NCCL all-reduce, then reporting each measurement against the matching profile's thresholds. Supports creating tests, tracking progress, sharing reports, and requires two owner-only confirmations before nodes are added or a test starts.

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

Enables natural-language querying and investigation of homelab logs from syslog, Docker, OTLP, and AI transcripts, with SQLite full-text search, timeline correlation, incident clustering, and fleet topology insights.

Enables Claude to analyse a Nostr relay read-only: reachability, NIP-11 details, recent and counted events, activity reports, author lookups, spam triage and event engagement, with third-party text fenced as untrusted. When explicitly enabled, it also lets Claude draft notes and reactions and publish them through a NIP-46 remote signer, with the user's key staying in the signer and every publication requiring human confirmation.

Bridges Parallel's Monitor API with Poke to receive SMS notifications when web monitors detect changes and conversationally create/manage monitors through text messages.

A Model Context Protocol server that analyzes various log types on Windows systems, allowing users to register, query, and analyze logs from different sources including Windows Event Logs, ETL files, and structured/unstructured text logs.

Privacy-first events from Luxonis OAK cameras for AI agents: person enter/leave zone events, depth changes and camera health as text. Never returns pictures.

Enables MCP clients to query YouTube channel health, diagnose video performance, full-text search transcripts, and vet topics/scripts directly from an editor or chat interface.

Remote execution layer for agentic systems exposing 64 production tools via MCP for file, network, system, text, git, crypto, and monitoring operations.

Enables fast, on-device machine learning with production-grade persistence through the Model Context Protocol. It allows instant training of text classifiers using Extreme Learning Machines, with SurrealDB-backed persistence and monitoring.

MCP server for querying VictoriaMetrics (PromQL/MetricsQL) and VictoriaLogs (LogsQL), also compatible with Prometheus, returning compact text summaries for LLM agents.