Use SpecStream in LM Studio

Add SpecStream to LM Studio and use it with the models you run on your own machine: DeepSeek, Qwen, Gemma or Llama. The model runs locally; SpecStream reads the live web and brings back the results with their sources.

What you need

• A SpecStream account. Start free: $10 of work for 30 days, no card.

The server address is the same for every client:

https://api.specstream.ai/mcp

Connect

Create an API key

1. Open Agents & API in the workspace and choose API keys.
2. Choose Create API key. Give it only what the task needs: read, prepare or execute permissions, the projects it may use, an expiry and a spending limit.
3. Copy the key when it's shown. It isn't shown again.

Add it to mcp.json

1. In LM Studio, open the Program tab in the right sidebar, click Install, then Edit mcp.json.
2. Add SpecStream with your key and save:

{
  "mcpServers": {
    "specstream": {
      "url": "https://api.specstream.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Pick a model that supports tool use, then turn SpecStream on in the chat.

Try it

Once LM Studio shows SpecStream's tools, ask in your own words:

Use SpecStream to find every dental clinic in Austin, Texas with its phone, website and Google rating. Show me the price first.

SpecStream reads the request back and gives you the price. Nothing is spent until you approve a maximum, and you pay only for the matches, each with its source.

Set access and spending limits

An agent works on your account, with the same balance, permissions and spending limits you have. Give its key the least it needs: read, prepare or execute permissions, project limits, an expiry and a spending ceiling. Paid work needs an approved price with a ceiling, and reading, exporting and sharing cost nothing.

More

• MCP connection details, with every tool your agent can call.
• The REST API, the SDKs and command line, and everything your agent can do.
• How quotes and billing work.
• Other clients: Claude, ChatGPT, Cursor, VS Code, Perplexity, Gemini, Grok, Le Chat, Manus, Cherry Studio, AnythingLLM.

Get started – free

LM Studio's own documentation: LM Studio: MCP in LM Studio.