"Running code or executing programming scripts" matching MCP servers:

Enables YouTube competitor research, signal analysis, and transcript-aware pack building for content ideation and scriptwriting.

Enables AI agents to interact with the Baltamatica scientific computing kernel, executing code, managing variables, and running scripts while preserving workspace state across calls.

Provides tools to search and execute Code Ocean capsules and pipelines while managing platform data assets. It enables users to interact with Code Ocean's computational resources and scientific workflows directly through natural language interfaces.

Enables MCP clients to fetch live football odds and team form, and flag matches where the market price diverges from a simple form-based estimate.

Enables AI clients to query ContentRadar data and write low-risk content using natural language, with 15 tools for monitoring, analysis, and content management.

Enables searching and discovering machine learning papers, state-of-the-art benchmarks, tasks, datasets, methods, and leaderboards from Papers with Code. Supports mapping papers to their benchmark results and browsing evaluation tables.

Enables AI agents to interact with Jupyter notebooks via MCP tools for querying, modifying, executing, and setting up notebooks, with state preservation and real-time collaboration.

MCP server for Tracetify — trace how any product actually grew, without leaving Claude Code or Cursor.

Enables running Simulatte's 26 research SKUs (concept testing, pricing, etc.) from any MCP-compatible AI client, returning structured JSON results.

Enables AI agents to monitor MetaTrader 5 accounts on remote Windows VPS via SSH, providing read-only access to positions, history, and logs without executing trades.

Provides deterministic, plain-English narratives explaining machine learning model predictions via the Model Context Protocol. It enables users to query classification factors directly through natural language, bypassing the need for complex plots or manual code execution.

A Python MCP server for hypothesis-driven data analysis, managing analysis designs, data catalogs, and review workflows through Claude Code or any MCP-compatible client.

MCP server for Kaggle API integration that allows creating, running, and managing Kaggle notebooks programmatically.

Enables AI agents to run Gretl/Hansl scripts, execute Gretl commands, manage packages, and interact with the Gretl GUI for econometric analysis and visualization.

Enables LLM agents to interact with the MOSTLY AI Platform for generating synthetic data, including training generators, managing data connectors, executing queries, and generating synthetic datasets with OAuth 2.1 authentication.

Chat with any brand's Meta (Facebook/Instagram) ads inside Claude — research a competitor's ad library, find their longest-running winners, extract hooks and formats, and clone winning ads for your own brand.

An MCP server that enables Claude Code/Codex to directly control PsychoPy for designing, running, and analyzing psychology experiments with literature-calibrated paradigms.

Enables natural language access to Japanese patent information through the JPO API, allowing users to query patent data directly from Claude Desktop or Claude Code.

Read-only MCP server for Yandex Metrika analytics, enabling report retrieval via MCP clients like Claude Code or Cursor without modifying any data.

Enables reproducible analysis of 100 curated Swiss open-data resources by searching profiles, materializing PXWeb data, validating and executing SQL, and formatting reproduction details, with reasoning delegated to the MCP client.