"Weights & Biases" matching MCP servers:

An MCP server that enables LLMs to detect cognitive biases and logical fallacies in text, list supported biases, and provide links to relevant psychology tests.

Enables running ML experiments from a local laptop by coordinating GitHub for code, Kaggle for data and GPU training, Weights & Biases for tracking runs, and Google Drive for small artifacts.

C++26 paper reference MCP with lookup_paper, fuzzy search, and compiler_status tools over a 216-paper ISO/IEC 14882:2026 corpus. Backs a Claude Code plugin that biases the model toward final-form C++26 idioms (reflection, contracts, std::execution senders, expansion statements, #embed).

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.

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.

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.

An MCP server for chemistry: it computes molecular weights and isotope distributions from chemical formulae and resolves compound name/formula lookups, backed by NIST atomic-weight data and a cached finder over multiple online and offline sources.

An MCP server that provides AI trading agents with persistent, outcome-weighted memory to learn from historical performance and detect behavioral biases. It enables agents to automatically adjust strategies and optimize position sizing based on context-aware recall of past trade outcomes.

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.

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.