"Linux Foundation" matching MCP servers:

Enables users to perform deterministic time series forecasting through Claude by running reproducible Python statistical and foundation models, providing tools for loading data, cross-validation, forecasting, anomaly detection, and exporting re-runnable manifests without any LLM involvement.

Lets coding agents such as Claude Code and Codex hand summarising, field extraction, classification and OCR to the free, offline on-device model for Apple Foundation Models on macOS 27. One Rust binary, installed with Homebrew.

Self-hosted Linux administration over MCP: 38 tools for processes, disks, network, systemd, journal and files, served over HTTPS. Each call runs as the caller's own OS user; root is granted per tool, limited to paths, networks and sysctl keys.

Enables AI clients to produce probabilistic forecasts with prediction intervals for numeric time series such as sales, demand, traffic, and sensor readings, using a panel of zero-shot foundation models or an accuracy-weighted ensemble. Supports up to 64 series per call, optional covariates, horizons up to 512 steps, and usage or credit checks, all without training or feature engineering.

Drives an existing VisoMaster Fusion installation on a remote Linux GPU workstation over SSH, running durable background GPU jobs for face detection, previewing and rendering. Returns progress, face crops, previews and finished media to the client.

Bridges Archetype AI's Newton physical-world foundation model to any MCP-compatible agent, letting it answer natural-language questions grounded in inline text/JSON events or uploaded files, and turn channel-first sensor windows into 768-dimensional per-channel embeddings. It exposes just a couple of auditable tools over Newton's documented query API, with a mock backend for credential-free use and a proposed contract layer for policy-approved, verified physical actions.

Integrates with IBM watsonx.ai to enable Claude Code to delegate text generation, chat, embeddings, and model listing to IBM foundation models like Granite and Llama.

MCP server for predictalot, providing streamable HTTP tools for zero-shot time-series forecasting with multiple foundation models and per-type ensembles. Tabular ML endpoints are currently HTTP-only.

Exposes geospatial foundation model inference as MCP tools for LLM agents, enabling building extraction, water segmentation, object detection, change detection, zero-shot scene classification, and embeddings on CPU.

MCP server that enables local Apple on-device Foundation Model access via any MCP client, supporting text generation, structured output, and multi-turn chat on macOS.

Enables inspecting ONNX models, probing the deployment environment, and benchmarking inference latency and FPS either locally or on remote SSH targets such as Linux workstations and Jetson devices. Benchmark results are validated against FPS, P95 latency and model-size constraints to produce PASS/FAIL deployment gates.

Enables AI agents to segment 2D and 3D biomedical images using Microsoft's MedImageParse foundation models via free-text prompts, returning masks and statistics. Supports both local stdio MCP server and a hosted Azure API Management gateway for remote agents like Microsoft Foundry.