SpecStream for LM Studio

What you get

• Your model stays localThe model runs on your own hardware, and SpecStream receives only the tool calls it makes.
• Any tool-use model you loadSpecStream sits in LM Studio's mcp.json, so Qwen, Gemma, Llama or DeepSeek reach the same account as soon as you load one that supports tool use.
• Austin clinics, ready to callAsk for every dental clinic in Austin, Texas with its phone, website and Google rating, and the model gets rows it can sort by rating or summarize.

Set it up

1. 1Under Agents & API in the SpecStream workspace, create an API key for LM Studio and set its spending limit.
2. 2In LM Studio, open the Program tab in the right sidebar, click Install, then Edit mcp.json, and add SpecStream with your key.
3. 3Load a model that supports tool use, turn SpecStream on in the chat, and ask.

The full setup guide has every step, with what to do if something doesn’t arrive.

• ClaudeA connector in Claude, one command in Claude Code
• ChatGPTMention @SpecStream in any ChatGPT chat
• GeminiGemini on your phone, and in Gemini CLI
• GrokRecords in Grok chats and xAI API calls
• Le ChatMistral's Le Chat, with EU prices in euros
• PerplexityPerplexity questions answered as records