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

An MCP server for accelerator programs to query, review, and manage startup applications via natural language. It enables searching applications by sector or impact score, fetching full application details with reviewer notes, listing pending reviews, and flagging applications for panel discussion.

Enables read-only queries across App Store Connect and Google Play from one toolset, letting users list apps, track release states, and review merged store feedback without extra dependencies or credentials in demo mode.

Validates startup ideas with a deterministic scorecard, evidence brief, and verdict before code is written, integrating with MCP-aware build agents to avoid building dead-on-arrival products.

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

Turns product feedback pinned to a live UI into an actionable backlog for Claude Code — list comments, open one with its target element's HTML, computed styles and screenshot, and update its status.

Generate SWOT analyses, competitive comparisons, and browse 100+ pre-built industry examples for any company, brand, or topic. Supports 12 languages.

MCP server for IDEA Base — AI-powered project management. Manage projects, tasks, and time tracking directly from Claude Code, Cursor, or any MCP-compatible AI tool.

A Model Context Protocol (MCP) server that connects Trello to Claude Code. Manage your boards, lists, cards, checklists, and more — all through natural language.

Enables goal-driven plan simplification by tracing each step's necessity, detecting cycles, broken links, and transitive waste, and classifying items as required or pointless with review and recheck capabilities.

Enables AI assistants to create and validate surveys, distribute them, read and tag responses, and generate reports or exports through a hosted Streamable HTTP MCP endpoint with API-key authentication.

MCP server for GoalT, a multi-parent value-propagating goal graph. It enables building and querying goal trees, listing priorities, and opening a live dashboard that highlights the active goal during Claude Code sessions.

Enables Claude Code to run multi-round grilling sessions in a browser UI, publishing rounds of questions with options and recommendations that users answer with buttons or free text. Supports per-question asides (re-pitch, visual diagram, plain-language explainer), chat notes between rounds, and a polling contract so sessions can stay open without blocking the client.

An MCP server that exposes a Proof workspace to MCP clients, enabling tools for reading/writing concepts, managing ideas and projects, running ideation operators, and more, with live sync and headless authentication.

Official MCP server for Weft, an agent-first Scrumban board. Agents claim tasks with leases, report progress, and finish with receipts you accept or return from an Inbox. Hosted remote endpoint, OAuth 2.1, no API keys.

Enables AI assistants to securely access design files, artboards, tokens, PRDs, and design-to-code workflows, letting users implement or match designs from delivery URLs.

Enables AI coding clients to turn code into a linked product specification and run coherence, coverage, and impact checks to surface gaps and contradictions.

Enables AI agents to query Mixpanel event data, funnel conversion rates, and retention cohorts via MCP tools or natural language.

Lets Claude Desktop, Cursor, and Claude Code search, read, and mutate a product plan — creating and editing nodes, running story-mapping workflows, managing phases, and driving the live canvas — alongside project, webhook, share-link, member, and tier operations. Each tool proxies one versioned v1 REST endpoint and returns the API's _meta coaching verbatim.

Enables managing Azure DevOps work items such as PBIs, tasks, and bugs, along with their comments, directly from MCP-compatible clients like Claude Desktop or Cursor.

Enables auditing AI products against a 12-criteria human-impact rubric and generating 0–100 scores, evidence-backed or provisional badges, and shareable teardowns from structured findings and source URLs.