"Understanding Inference Models" matching MCP servers:

MCP server for the DAG Studio causal-inference engine, enabling AI agents to construct, analyze, and validate causal directed acyclic graphs (DAGs) through tools for analysis, data simulation, and code generation.

An MCP server that enables MCP clients to directly access and process arXiv papers by fetching the LaTeX source, improving mathematical content understanding.

Exposes InferenceIndexer's live and historical inference pricing as MCP tools, enabling search of models, providers, price comparisons, and SIT index trends.

Enables gender inference from names, email addresses, and usernames, returning probability, sample size, source, and optional country-weighted results.

Provides verified statistical inference and hypothesis testing tools, including t-tests, effect sizes, power analysis, and multiple comparisons correction, with assumption checks and citations.

MCP server for FisPro fuzzy inference systems, enabling reading .fis files, running inferences, and explaining rule firings in natural language.

Enables reading and understanding NetCDF files, providing tools to inspect structure, variables, metadata, and data quality for scientific datasets.

Enables AI assistants to solve linear, nonlinear, and integer optimization models with a locally installed LINGO 11 solver and read the results back as structured data — status, objective, variable values, reduced costs, row slacks, and dual prices. It also runs arbitrary LINGO command-window analyses, reports the detected installation and license status, and lists the bundled sample models, correctly flagging infeasible or unbounded models instead of inventing an optimum.

Enables a primary Codex agent to queue independent, read-only research jobs that execute in parallel using any OpenAI Responses-compatible inference provider while the agent continues its own work.

A Model Context Protocol server for exploring and analyzing CSV files, providing tools for inspection, sampling, schema inference, statistics, filtering, and more.

Enables AI-powered competitor pricing analysis by scraping LLM inference pricing websites via Firecrawl, storing the data in SQLite, and answering cost comparison queries through natural language.

Automates competitive research for startup ideas by executing a 7-step pipeline including idea understanding, competitor discovery, profile extraction, feature comparison, market gap analysis, innovation scoring, and report generation.

Enables LLM agents to programmatically inspect hardware resources, run in-memory inference benchmarks, list supported fMRI studies, and retrieve cortical and subcortical atlas region indices via JSON-RPC 2.0.

Enables scraping and comparing pricing information for LLM inference services across multiple providers (CloudRift, DeepInfra, Fireworks, Groq) using Firecrawl API and SQLite storage.

An MCP server that provides a toolbox for interacting with EPA SWMM stormwater models, enabling users to analyze model data and interpret results through LLM-driven tools. It assists stormwater modelers in understanding hydraulic systems and modeling behavior using natural language interfaces.

AI-powered quantitative research assistant with 45 tools for causal inference methods (DID, RDD, IV, PSM), regression analysis, power calculations, and statistical code generation in R, Stata, and Python.

Enables search and retrieval of calibrated SWAT+ watershed models, national groundwater lithology and PFAS inventories, plus API-key-secured ordering and downloading of custom watershed models.

Provides signed AI-inference-storage benchmark data, technical article search, and KV-cache tiering ROI estimation with transparent provenance.

Connects AI tools to Remapdb vehicle tuning data, enabling search and retrieval of manufacturers, models, engines, and tuning information.

Enables analysis and inference on WiFi CSI sensing data, providing multi-user presence detection and activity recognition through a Model Context Protocol interface.