"Using code execution to replace native tooling" matching MCP servers:

Enables efficient AI agent operations through sandboxed Python code execution with progressive tool discovery, PII tokenization, and skills persistence, achieving up to 98.7% token reduction by processing data in a sandbox rather than in context.

Executes Python code in isolated rootless containers while proxying MCP server tools, reducing context overhead by 95%+ and enabling complex multi-tool workflows through sandboxed code execution.

Enables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through the Execute.run platform.

MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.

An autonomous MCP server that uses the Claude Code CLI to solve coding problems without permission prompts.

Enables orchestrator agents to route coding tasks to native CLI worker agents via MCP, providing tools for agent discovery, task submission, waiting, inspection, and cancellation.

An MCP server that lets Claude Code delegate durable background tasks, reasoning profiles, thread resumption, and native image generation to your local Codex CLI.

MCP server that verifies restaurant booking outcomes by reconciling API claims against independent re-reads, with a recovery dial for stakes-based retry policies.

Enables macOS computer-use automation through public Apple APIs, supporting app and window discovery, clicking, typing, scrolling, and field setting via accessibility controls.

Provides comprehensive tools for React Native development, automating project initialization, version management, upgrades, Expo integration, and development workflows through AI assistance.

Enables MCP-capable agents to control the macOS mouse and keyboard using screenshots and Quartz-based input events, including app switching, clicks, scrolling, text entry, shortcuts, and action-triggered screenshots.

An MCP server that enables AI agents to execute sandboxed JavaScript and TypeScript code instead of calling individual tools directly. It significantly reduces token usage by allowing agents to filter, aggregate, and transform data locally before returning results.

Enables AI agents to connect to Revit 2024 via MCP, inspect documents and selections, query and modify elements, and validate, preview, or commit plans with audit logging and rollback.

Enables any MCP client (zcode, Claude Code, Cursor) to give its model bi-temporal long-term memory, auditable evidence-cited retrieval, LLM-assisted document extraction, and deterministic A* skill planning with precondition/effect verification. All four capabilities share one portable SQLite store and can be mounted independently on demand.

Enables AI sales agents to interact with a CRM via event-sourced actions, identity resolution, guard checks, and an approval inbox, managing communications and tasks while adhering to compliance rules.

A runtime for inspectable agent workflows that provides MCP tools, bounded Python execution, session memory, and deterministic evaluation.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Enables multi-agent council workflows for coding assistants, providing parallel independent reviews, plans, brainstorms, validation, and research with strict read-only boundaries.

A security filter that blocks dangerous code patterns by comparing normalized structural syntax trees against a blacklist of known threats using vector embeddings. It acts as a gatekeeper to prevent malicious code execution by identifying dangerous structures regardless of specific identifiers or literals.

One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose