AIAny
Icon for item

MCPorter

Discovers MCP servers already configured in Cursor, Claude, Codex and other editors, then calls their tools from TypeScript or the CLI. Can also turn any server into a standalone command-line tool or a typed TypeScript client.

Introduction

Every editor that speaks MCP — Cursor, Claude Desktop, Codex — keeps its own list of configured servers, and every script that wants to use them re-implements the same discovery, transport, and auth plumbing. MCPorter's bet is that those configs are already a usable runtime: point it at the servers you've set up once, and call their tools from a shell or a TypeScript file with no extra wiring.

What Sets It Apart
  • Zero-config discovery reads servers straight from existing Cursor/Claude/Codex config, so there's no second source of truth to maintain.
  • Function-call syntax lets you invoke a tool the way you'd call a method, instead of hand-building JSON-RPC requests.
  • Typed clients and CLI packaging are separate emitters: emit-ts generates a .d.ts interface and a typed TypeScript client whose type safety comes from the server's own schema, not hand-written wrappers, while generate-cli converts an MCP definition into a standalone, shareable command-line tool.
  • Daemon mode keeps stateful servers (a Chrome DevTools session, say) warm between calls instead of paying cold-start each time, and OAuth tokens are cached for headless use.
Who It's For

Great fit if you script against several MCP servers and are tired of copying transport and auth boilerplate between projects, or if you want to ship an MCP capability as a plain CLI others can run without an MCP client. Look elsewhere if you only talk to a single server from inside one editor — the editor's built-in integration already covers that, and a TypeScript/Node runtime is extra weight you won't use.

Information

  • Websitegithub.com
  • OrganizationsPeter Steinberger
  • AuthorsPeter Steinberger (steipete)
  • Published date2025/11/05

Categories

More Items

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).

GitHub

Cross-platform API client for debugging, designing, testing and mocking GraphQL, REST, WebSockets, SSE and gRPC. Provides selectable storage backends (Local Vault, Git Sync, Cloud Sync with optional E2EE), a native OpenAPI editor, built-in test suites and a plugin ecosystem — useful for reproducible API development and pre-production validation.