"Understanding Inference Models" matching MCP servers:

MCP server for the ParalleliX Compute API that lets you offload parallel inference tasks (bulk classify, extract, summarize, etc.) to a distributed network of open-source models.

Official remote MCP server for RunComfy. 31 tools across three products: Serverless API (ComfyUI) deployment management and async inference, Model API hosted-model inference, and Trainer API LoRA training jobs.

Enables governance-grade AIops for GPU inference clusters with root-cause analysis, metrics, and policy-governed operations for vLLM and Ray.

An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents.

MCP server that exposes Telegraph Protocol's AI inference APIs as tools with automatic x402 micropayments, enabling any MCP-compatible agent to access AI miners like weather forecasting, deepfake detection, and LLM inference without handling cryptocurrency.

Enables managing Onde Inference accounts and model catalog operations through MCP tools such as login, app management, model registration, and assignment. Returns structured JSON over stdio for use with any MCP client.

Provides an MCP-compatible profiler for measuring edge and on-device LLM inference latency, including TTFT, TPOT, tokens-per-second throughput, and P50/P90/P99 jitter distributions. It enables agents and developers to run these telemetry benchmarks from MCP clients such as Claude Desktop, Cursor, and Windsurf.

Provides AI agents with a toolset to query model inventories, trace dependencies, and analyze the impact of changes across machine learning models and data pipelines.

Enables AI agents and MCP clients to estimate VRAM footprint and tensor parallelization requirements for quantized llama.cpp models, returning structured outputs without external dependencies.

Enables AI agents to make pay-as-you-go AI inference requests through x402 with automatic Solana USDC payments, no API keys or registration, while enforcing configurable spending limits.

An MCP server that uses Xiaomi MiMo v2.5 multimodal model to provide image recognition capabilities (description, multi-image analysis, OCR, and image info validation) for text-only main models like deepseek-v4-flash, accepting local paths, URLs, file://, and base64 data inputs.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

A structure-aware MCP server for querying the SPOKE biomedical knowledge graph, enabling entity resolution, schema introspection, path finding, and safe Cypher queries for biomedical knowledge inference.

Lets AI assistants use MetaModel's formula engine for certified computation, turning published calculators, pricing tools, and engineering models into AI-callable tools with no hallucinated math.

A production-ready Model Context Protocol server that enables language models to leverage AI-powered web scraping capabilities, offering tools for transforming webpages to markdown, extracting structured data, and executing AI-powered web searches.

Enables agents to search a public tire catalog and professional tire test data — finding tire models, checking their known size variants, comparing 2-4 models, and collecting cited test results — through 12 read-only tools and four workflow prompts over stdio.

A plain-files brain template and MCP server that lets models read owned, portable working memory via list, read, and grep-style search tools.

Enables AI agents to interact with Bentley STAAD.Pro models for tasks like load case definition, data extraction, and property setting through natural language.

Enables AI agents to generate, edit, and upscale videos and images using VicSee's API, with support for multiple models and asynchronous task polling.

Provides deterministic fair-housing and advertising compliance checks for US real-estate listings, with rule explanations and rewrite suggestions, ensuring models cannot override the verdict.