#58 · Primary category： LLM Application Frameworks
mcporter
Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.
Project last updated：08/28/26
GitHub Stars
5.0K
Forks
336
Contributors
46
License
MIT
Why we included this project
The same MCP servers you already use inside an editor like Claude Code or Cursor can also be driven from your own TypeScript code or a plain terminal. MCPorter's runtime exposes each tool as an ordinary callable function, so scripts and agents treat external tools like native TypeScript APIs instead of working with the protocol directly. The CLI handles discovery, invocation, and OAuth, and can package tools into a standalone binary for people who should not have to touch a terminal. It also picks up server configs you have already set up in the major AI editors, so you rarely have to configure the same servers again. Developers and small teams get one consistent way to reuse MCP tools across scripts, CLIs, and agents.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform