Sampling

specification/2025-11-25/client/sampling New page · 631 lines, new page

# Sampling ## User Interaction Model ## Tools in Sampling ## Capabilities ## Protocol Messages ### Creating Messages ### Sampling with Tools ### Multi-turn Tool Loop ## Message Content Constraints ### Tool Result Messages ### Tool Use and Result Balance ## Cross-API Compatibility ### Message Roles ### Tool Choice Modes ### Parallel Tool Use ## Message Flow ## Data Types ### Messages #### Text Content #### Image Content #### Audio Content ### Model Preferences #### Capability Priorities #### Model Hints ## Error Handling ## Security Considerations

A whole new page. There's nothing to diff it against, so here is what it says.

# Sampling

<div id="enable-section-numbers" />

The Model Context Protocol (MCP) provides a standardized way for servers to request LLM
sampling ("completions" or "generations") from language models via clients. This flow
allows clients to maintain control over model access, selection, and permissions while
enabling servers to leverage AI capabilities—with no server API keys necessary.
Servers can request text, audio, or image-based interactions and optionally include
context from MCP servers in their prompts.

## User Interaction Model

Sampling in MCP allows servers to implement agentic behaviors, by enabling LLM calls to
occur *nested* inside other MCP server features.

Implementations are free to expose sampling through any interface pattern that suits
their needs—the protocol itself does not mandate any specific user interaction
model.

<Warning>
  For trust & safety and security, there **SHOULD** always
  be a human in the loop with the ability to deny sampling requests.

  Applications **SHOULD**:

  * Provide UI that makes it easy and intuitive to review sampling requests
  * Allow users to view and edit prompts before sending
  * Present generated responses for review before delivery
</Warning>

## Tools in Sampling

Servers can request that the client's LLM use tools during sampling by providing a `tools` array and optional `toolChoice` configuration in their sampling requests. This enables servers to implement agentic behaviors where the LLM can call tools, receive results, and continue the conversation - all within a single sampling request flow.

Clients **MUST** declare support for tool use via the `sampling.tools` capability to receive tool-enabled sampling requests. Servers **MUST NOT** send tool-enabled sampling requests to Clients that have not declared support for tool use via the `sampling.tools` capability.

## Capabilities

Clients that support sampling **MUST** declare the `sampling` capability during
[initialization](/specification/2025-11-25/basic/lifecycle#initialization):

**Basic sampling:**

```json theme={null}
{
  "capabilities": {
    "sampling": {}
  }
}
```

**With tool use support:**

```json theme={null}
{
  "capabilities": {
    "sampling": {
      "tools": {}
    }
  }
}
```

**With context inclusion support (soft-deprecated):**

```json theme={null}
{
  "capabilities": {
    "sampling": {
      "context": {}
    }
  }
}
```

<Note>
  The `includeContext` parameter values `"thisServer"` and `"allServers"` are
  soft-deprecated. Servers **SHOULD** avoid using these values (e.g. can just
  omit `includeContext` since it defaults to `"none"`), and **SHOULD NOT** use
  them unless the client declares `sampling.context` capability. These values
  may be removed in future spec releases.
</Note>

## Protocol Messages

### Creating Messages

To request a language model generation, servers send a `sampling/createMessage` request:

**Request:**

```json theme={null}
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "sampling/createMessage",
  "params": {
    "messages": [
      {
        "role": "user",
        "content": {
          "type": "text",
          "text": "What is the capital of France?"
        }
      }
    ],
    "modelPreferences": {
      "hints": [
        {
          "name": "claude-3-sonnet"
        }
      ],
      "intelligencePriority": 0.8,
      "speedPriority": 0.5
    },
    "systemPrompt": "You are a helpful assistant.",
    "maxTokens": 100
  }
}
```

**Response:**

```json theme={null}
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "role": "assistant",
    "content": {
      "type": "text",
      "text": "The capital of France is Paris."
    },
    "model": "claude-3-sonnet-20240307",
    "stopReason": "endTurn"
  }
}
```

### Sampling with Tools

The following diagram illustrates the complete flow of sampling with tools, including the multi-turn tool loop:

```mermaid theme={null}
sequenceDiagram
    participant Server
    participant Client
    participant User
    participant LLM

    Note over Server,Client: Initial request with tools
    Server->>Client: sampling/createMessage<br/>(messages + tools)

    Note over Client,User: Human-in-the-loop review
    Client->>User: Present request for approval
    User-->>Client: Approve/modify

    Client->>LLM: Forward request with tools
    LLM-->>Client: Response with tool_use<br/>(stopReason: "toolUse")

    Client->>User: Present tool calls for review
    User-->>Client: Approve tool calls
    Client-->>Server: Return tool_use response

    Note over Server: Execute tool(s)
    Server->>Server: Run get_weather("Paris")<br/>Run get_weather("London")

    Note over Server,Client: Continue with tool results
    Server->>Client: sampling/createMessage<br/>(history + tool_results + tools)

    Client->>User: Present continuation
    User-->>Client: Approve

    Client->>LLM: Forward with tool results
    LLM-->>Client: Final text response<br/>(stopReason: "endTurn")

    Client->>User: Present response
    User-->>Client: Approve
    Client-->>Server: Return final response

    Note over Server: Server processes result<br/>(may continue conversation...)
```

To request LLM generation with tool use capabilities, servers include `tools` and optionally `toolChoice` in the request:

**Request (Server -> Client):**

```json theme={null}
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "sampling/createMessage",
  "params": {
    "messages": [
      {
        "role": "user",
        "content": {
          "type": "text",
          "text": "What's the weather like in Paris and London?"
        }
      }
    ],
    "tools": [
      {
        "name": "get_weather",
        "description": "Get current weather for a city",
        "inputSchema": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "City name"
            }
          },
          "required": ["city"]
        }
      }
    ],
    "toolChoice": {
      "mode": "auto"
    },
    "maxTokens": 1000
  }
}
```

**Response (Client -> Server):**

```json theme={null}
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "role": "assistant",
    "content": [
      {
        "type": "tool_use",
        "id": "call_abc123",
        "name": "get_weather",
        "input": {
          "city": "Paris"
        }
      },
      {
        "type": "tool_use",
        "id": "call_def456",
        "name": "get_weather",
        "input": {
          "city": "London"
        }
      }
    ],
    "model": "claude-3-sonnet-20240307",
    "stopReason": "toolUse"
  }
}
```

### Multi-turn Tool Loop

After receiving tool use requests from the LLM, the server typically:

1. Executes the requested tool uses.
2. Sends a new sampling request with the tool results appended
3. Receives the LLM's response (which might contain new tool uses)
4. Repeats as many times as needed (server might cap the maximum number of iterations, and e.g. pass `toolChoice: {mode: "none"}` on the last iteration to force a final result)

**Follow-up request (Server -> Client) with tool results:**

```json theme={null}
{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "sampling/createMessage",
  "params": {
    "messages": [
      {
        "role": "user",
        "content": {
          "type": "text",
          "text": "What's the weather like in Paris and London?"
        }
      },
      {
        "role": "assistant",
        "content": [
          {
            "type": "tool_use",
            "id": "call_abc123",
            "name": "get_weather",
            "input": { "city": "Paris" }
          },
          {
            "type": "tool_use",
            "id": "call_def456",
            "name": "get_weather",
            "input": { "city": "London" }
          }
        ]

Cut at 300 lines. The page has the rest.