"Weights & Biases" matching MCP servers:

Audits decisions for cognitive biases through an adversarial framework, exposing tools like analyze_decision, list_biases, and get_bias via MCP.

Tweet scoring using X's actual algorithm weights - 22 signals, 18 filters, 11 tools

Enables querying authoritative product data from GS1 Brasil's Verified by GS1 API via GTIN, including brand, description, classifications, images, weights, dimensions, and licensee details, with support for national and international bases and batch enrichment.

MCP server over the open index of 1,562 certification exam blueprints across 217 certifying bodies. Search exams, pull full blueprints (domains & weights, passing scores, prerequisites, renewal), and compare certifications. Read-only, public data, no API key.

Checks a social post against a platform's real character limit before it ships — X bills every URL at 23 characters and weights non-Latin script at 2, while Bluesky and Mastodon count grapheme clusters. Covers X, X Premium, Bluesky, LinkedIn, Threads, Mastodon, and Discord, with no credentials and no network access.

URL intelligence for AI agents. One URL in, structured security and data quality signals out across 7 dimensions. 13 tools, risk score 0-100 with 23 configurable weights.

A decision structure analysis engine that transforms emotional dilemmas into structured frameworks by identifying variables, constraints, and strategy paths. It helps users evaluate risk distributions and cognitive biases without offering subjective advice or definitive answers.

Checks whether an open-weight LLM fits your GPU: VRAM for weights, KV cache and overhead at each quantisation, a tokens-per-second ceiling, the longest context that fits, and what would work instead when it doesn't. Reads any Hugging Face repo's config.json. Free, read-only, no API key.

Enables comparing and recommending AI models based on scenario-specific criteria such as capability, context, relative cost, and self-hosting, with explanations of the scoring weights.

An MCP server that lets AI agents create and manage LighterPack packing lists — add gear, track weights, organize categories, and share lists, all through natural conversation.

Enables querying a Tonal fitness account for workout history with per-set weights, muscle readiness, strength scores, and lifetime stats through a remote MCP endpoint.

Enables browsing the full ingredient lists of two build-your-own cereal mixers (müsli & granola and porridge), returning composition, allergens, prices, portion weights, dietary properties and per-100g nutrition values grouped by category. Supports filtering by category and an optional lighter mode that omits detailed composition and allergen data.