obsidian/raw/_processed/Using MCP via API.md at main

Vadym/obsidian

Fork 0

Vadym Samoilenko 0631673e44 vault backup: 2026-04-30 14:42:43

2026-04-30 14:42:43 +01:00

6 KiB

Raw Permalink Blame History

title

source

author

published

created

description

Requires LM Studio 0.4.0 or newer.

LM Studio supports Model Context Protocol (MCP) usage via API. MCP allows models to interact with external tools and services through standardized servers.

How it works

MCP servers provide tools that models can call during chat requests. You can enable MCP servers in two ways: as ephemeral servers defined per-request, or as pre-configured servers in your mcp.json file.

Ephemeral vs mcp.json servers

Feature	Ephemeral	mcp.json
How to specify in request	`integrations` -> `"type": "ephemeral_mcp"`	`integrations` -> `"type": "plugin"`
Configuration	Only defined per-request	Pre-configured in `mcp.json`
Use case	One-off requests, remote MCP tool execution	MCP servers that require `command`, frequently used servers
Server ID	Specified via `server_label` in integration	Specified via `id` (e.g., `mcp/playwright`) in integration
Custom headers	Supported via `headers` field	Configured in `mcp.json`

Ephemeral MCP servers

Ephemeral MCP servers are defined on-the-fly in each request. This is useful for testing or when you don't want to pre-configure servers.

Info

curl http://localhost:1234/api/v1/chat \
  -H "Authorization: Bearer $LM_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ibm/granite-4-micro",
    "input": "What is the top trending model on hugging face?",
    "integrations": [
      {
        "type": "ephemeral_mcp",
        "server_label": "huggingface",
        "server_url": "https://huggingface.co/mcp",
        "allowed_tools": ["model_search"]
      }
    ],
    "context_length": 8000
  }'

The model can now call tools from the specified MCP server:

{
  "model_instance_id": "ibm/granite-4-micro",
  "output": [
    {
      "type": "reasoning",
      "content": "..."
    },
    {
      "type": "message",
      "content": "..."
    },
    {
      "type": "tool_call",
      "tool": "model_search",
      "arguments": {
        "sort": "trendingScore",
        "limit": 1
      },
      "output": "...",
      "provider_info": {
        "server_label": "huggingface",
        "type": "ephemeral_mcp"
      }
    },
    {
      "type": "reasoning",
      "content": "\n"
    },
    {
      "type": "message",
      "content": "The top trending model is ..."
    }
  ],
  "stats": {
    "input_tokens": 419,
    "total_output_tokens": 362,
    "reasoning_output_tokens": 195,
    "tokens_per_second": 27.620159487314744,
    "time_to_first_token_seconds": 1.437
  },
  "response_id": "resp_7c1a08e3d6e279efcfecb02df9de7cbd316e93422d0bb5cb"
}

MCP servers from mcp.json

MCP servers can be pre-configured in your mcp.json file. This is the recommended approach for using MCP servers that take actions on your computer (like microsoft/playwright-mcp) and servers that you use frequently.

Info

curl http://localhost:1234/api/v1/chat \
  -H "Authorization: Bearer $LM_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ibm/granite-4-micro",
    "input": "Open lmstudio.ai",
    "integrations": ["mcp/playwright"],
    "context_length": 8000,
    "temperature": 0
  }'

The response includes tool calls from the configured MCP server:

{
  "model_instance_id": "ibm/granite-4-micro",
  "output": [
    {
      "type": "reasoning",
      "content": "..."
    },
    {
      "type": "message",
      "content": "..."
    },
    {
      "type": "tool_call",
      "tool": "browser_navigate",
      "arguments": {
        "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
      },
      "output": "...",
      "provider_info": {
        "plugin_id": "mcp/playwright",
        "type": "plugin"
      }
    },
    {
      "type": "reasoning",
      "content": "..."
    },
    {
      "type": "message",
      "content": "The YouTube video page for ..."
    }
  ],
  "stats": {
    "input_tokens": 2614,
    "total_output_tokens": 594,
    "reasoning_output_tokens": 389,
    "tokens_per_second": 26.293245822877495,
    "time_to_first_token_seconds": 0.154
  },
  "response_id": "resp_cdac6a9b5e2a40027112e441ce6189db18c9040f96736407"
}

Restricting tool access

For both ephemeral and mcp.json servers, you can limit which tools the model can call using the allowed_tools field. This is useful if you do not want certain tools from an MCP server to be used, and can speed up prompt processing due to the model receiving fewer tool definitions.

curl http://localhost:1234/api/v1/chat \
  -H "Authorization: Bearer $LM_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ibm/granite-4-micro",
    "input": "What is the top trending model on hugging face?",
    "integrations": [
      {
        "type": "ephemeral_mcp",
        "server_label": "huggingface",
        "server_url": "https://huggingface.co/mcp",
        "allowed_tools": ["model_search"]
      }
    ],
    "context_length": 8000
  }'

If allowed_tools is not provided, all tools from the server are available to the model.

Custom headers for ephemeral servers

When using ephemeral MCP servers that require authentication, you can pass custom headers:

curl http://localhost:1234/api/v1/chat \
  -H "Authorization: Bearer $LM_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ibm/granite-4-micro",
    "input": "Give me details about my SUPER-SECRET-PRIVATE Hugging face model",
    "integrations": [
      {
        "type": "ephemeral_mcp",
        "server_label": "huggingface",
        "server_url": "https://huggingface.co/mcp",
        "allowed_tools": ["model_search"],
        "headers": {
          "Authorization": "Bearer <YOUR_HF_TOKEN>"
        }
      }
    ],
    "context_length": 8000
  }'

6 KiB Raw Permalink Blame History