xiaozhi-esp32/main/mcp_server.cc

/*
 * MCP Server Implementation
 * Reference: https://modelcontextprotocol.io/specification/2024-11-05
 */

#include "mcp_server.h"
#include <esp_log.h>
#include <esp_app_desc.h>
#include <algorithm>
#include <cstring>

#include "application.h"
#include "display.h"
#include "board.h"

#define TAG "MCP"

McpServer::McpServer() {
    AddCommonTools();
}

McpServer::~McpServer() {
    for (auto tool : tools_) {
        delete tool;
    }
    tools_.clear();
}

void McpServer::AddCommonTools() {
    auto& board = Board::GetInstance();

    AddTool("self.get_device_status",
        "Provides the real-time information of the device, including the current status of the audio speaker, screen, battery, network, etc.\n"
        "Use this tool for: \n"
        "1. Answering questions about current condition (e.g. what is the current volume of the audio speaker?)\n"
        "2. As the first step to control the device (e.g. turn up / down the volume of the audio speaker, etc.)",
        PropertyList(),
        [&board](const PropertyList& properties) -> ReturnValue {
            return board.GetDeviceStatusJson();
        });

    AddTool("self.audio_speaker.set_volume", 
        "Set the volume of the audio speaker. If the current volume is unknown, you must call `self.get_device_status` tool first and then call this tool.",
        PropertyList({
            Property("volume", kPropertyTypeInteger, 0, 100)
        }), 
        [&board](const PropertyList& properties) -> ReturnValue {
            auto codec = board.GetAudioCodec();
            codec->SetOutputVolume(properties["volume"].value<int>());
            return true;
        });
    
    auto backlight = board.GetBacklight();
    if (backlight) {
        AddTool("self.screen.set_brightness",
            "Set the brightness of the screen.",
            PropertyList({
                Property("brightness", kPropertyTypeInteger, 0, 100)
            }),
            [backlight](const PropertyList& properties) -> ReturnValue {
                uint8_t brightness = static_cast<uint8_t>(properties["brightness"].value<int>());
                backlight->SetBrightness(brightness, true);
                return true;
            });
    }

    auto display = board.GetDisplay();
    if (display && !display->GetTheme().empty()) {
        AddTool("self.screen.set_theme",
            "Set the theme of the screen. The theme can be `light` or `dark`.",
            PropertyList({
                Property("theme", kPropertyTypeString)
            }),
            [display](const PropertyList& properties) -> ReturnValue {
                display->SetTheme(properties["theme"].value<std::string>().c_str());
                return true;
            });
    }

    auto camera = board.GetCamera();
    if (camera) {
        AddTool("self.camera.take_photo",
            "Take a photo and explain it. Use this tool after the user asks you to see something.\n"
            "Args:\n"
            "  `question`: The question that you want to ask about the photo.\n"
            "Return:\n"
            "  A JSON object that provides the photo information.",
            PropertyList({
                Property("question", kPropertyTypeString)
            }),
            [camera](const PropertyList& properties) -> ReturnValue {
                if (!camera->Capture()) {
                    return "{\"success\": false, \"message\": \"Failed to capture photo\"}";
                }
                auto question = properties["question"].value<std::string>();
                return camera->Explain(question);
            });
    }
}

void McpServer::AddTool(McpTool* tool) {
    ESP_LOGI(TAG, "Add tool: %s", tool->name().c_str());
    tools_.push_back(tool);
}

void McpServer::AddTool(const std::string& name, const std::string& description, const PropertyList& properties, std::function<ReturnValue(const PropertyList&)> callback) {
    AddTool(new McpTool(name, description, properties, callback));
}

void McpServer::ParseMessage(const std::string& message) {
    cJSON* json = cJSON_Parse(message.c_str());
    if (json == nullptr) {
        ESP_LOGE(TAG, "Failed to parse MCP message: %s", message.c_str());
        return;
    }
    ParseMessage(json);
    cJSON_Delete(json);
}

void McpServer::ParseCapabilities(const cJSON* capabilities) {
    auto vision = cJSON_GetObjectItem(capabilities, "vision");
    if (cJSON_IsObject(vision)) {
        auto url = cJSON_GetObjectItem(vision, "url");
        auto token = cJSON_GetObjectItem(vision, "token");
        if (cJSON_IsString(url) && cJSON_IsString(token)) {
            ESP_LOGI(TAG, "Setting explain URL: %s, token: %s", url->valuestring, token->valuestring);
            auto camera = Board::GetInstance().GetCamera();
            if (camera) {
                camera->SetExplainUrl(std::string(url->valuestring), std::string(token->valuestring));
            }
        }
    }
}

void McpServer::ParseMessage(const cJSON* json) {
    // Check JSONRPC version
    auto version = cJSON_GetObjectItem(json, "jsonrpc");
    if (version == nullptr || !cJSON_IsString(version) || strcmp(version->valuestring, "2.0") != 0) {
        ESP_LOGE(TAG, "Invalid JSONRPC version: %s", version ? version->valuestring : "null");
        return;
    }
    
    // Check method
    auto method = cJSON_GetObjectItem(json, "method");
    if (method == nullptr || !cJSON_IsString(method)) {
        ESP_LOGE(TAG, "Missing method");
        return;
    }
    
    auto method_str = std::string(method->valuestring);
    if (method_str.find("notifications") == 0) {
        return;
    }
    
    // Check params
    auto params = cJSON_GetObjectItem(json, "params");
    if (params != nullptr && !cJSON_IsObject(params)) {
        ESP_LOGE(TAG, "Invalid params for method: %s", method_str.c_str());
        return;
    }

    auto id = cJSON_GetObjectItem(json, "id");
    if (id == nullptr || !cJSON_IsNumber(id)) {
        ESP_LOGE(TAG, "Invalid id for method: %s", method_str.c_str());
        return;
    }
    auto id_int = id->valueint;
    
    if (method_str == "initialize") {
        if (cJSON_IsObject(params)) {
            auto capabilities = cJSON_GetObjectItem(params, "capabilities");
            if (cJSON_IsObject(capabilities)) {
                ParseCapabilities(capabilities);
            }
        }
        auto app_desc = esp_app_get_description();
        std::string message = "{\"protocolVersion\":\"2024-11-05\",\"capabilities\":{\"tools\":{}},\"serverInfo\":{\"name\":\"" BOARD_NAME "\",\"version\":\"";
        message += app_desc->version;
        message += "\"}}";
        ReplyResult(id_int, message);
    } else if (method_str == "tools/list") {
        std::string cursor_str = "";
        if (params != nullptr) {
            auto cursor = cJSON_GetObjectItem(params, "cursor");
            if (cJSON_IsString(cursor)) {
                cursor_str = std::string(cursor->valuestring);
            }
        }
        GetToolsList(id_int, cursor_str);
    } else if (method_str == "tools/call") {
        if (!cJSON_IsObject(params)) {
            ESP_LOGE(TAG, "tools/call: Missing params");
            ReplyError(id_int, "Missing params");
            return;
        }
        auto tool_name = cJSON_GetObjectItem(params, "name");
        if (!cJSON_IsString(tool_name)) {
            ESP_LOGE(TAG, "tools/call: Missing name");
            ReplyError(id_int, "Missing name");
            return;
        }
        auto tool_arguments = cJSON_GetObjectItem(params, "arguments");
        if (tool_arguments != nullptr && !cJSON_IsObject(tool_arguments)) {
            ESP_LOGE(TAG, "tools/call: Invalid arguments");
            ReplyError(id_int, "Invalid arguments");
            return;
        }
        DoToolCall(id_int, std::string(tool_name->valuestring), tool_arguments);
    } else {
        ESP_LOGE(TAG, "Method not implemented: %s", method_str.c_str());
        ReplyError(id_int, "Method not implemented: " + method_str);
    }
}

void McpServer::ReplyResult(int id, const std::string& result) {
    std::string payload = "{\"jsonrpc\":\"2.0\",\"id\":";
    payload += std::to_string(id) + ",\"result\":";
    payload += result;
    payload += "}";
    Application::GetInstance().SendMcpMessage(payload);
}

void McpServer::ReplyError(int id, const std::string& message) {
    std::string payload = "{\"jsonrpc\":\"2.0\",\"id\":";
    payload += std::to_string(id);
    payload += ",\"error\":{\"message\":\"";
    payload += message;
    payload += "\"}}";
    Application::GetInstance().SendMcpMessage(payload);
}

void McpServer::GetToolsList(int id, const std::string& cursor) {
    const int max_payload_size = 8000;
    std::string json = "{\"tools\":[";
    
    bool found_cursor = cursor.empty();
    auto it = tools_.begin();
    std::string next_cursor = "";
    
    while (it != tools_.end()) {
        // 如果我们还没有找到起始位置，继续搜索
        if (!found_cursor) {
            if ((*it)->name() == cursor) {
                found_cursor = true;
            } else {
                ++it;
                continue;
            }
        }
        
        // 添加tool前检查大小
        std::string tool_json = (*it)->to_json() + ",";
        if (json.length() + tool_json.length() + 30 > max_payload_size) {
            // 如果添加这个tool会超出大小限制，设置next_cursor并退出循环
            next_cursor = (*it)->name();
            break;
        }
        
        json += tool_json;
        ++it;
    }
    
    if (json.back() == ',') {
        json.pop_back();
    }
    
    if (json.back() == '[' && !tools_.empty()) {
        // 如果没有添加任何tool，返回错误
        ESP_LOGE(TAG, "tools/list: Failed to add tool %s because of payload size limit", next_cursor.c_str());
        ReplyError(id, "Failed to add tool " + next_cursor + " because of payload size limit");
        return;
    }

    if (next_cursor.empty()) {
        json += "]}";
    } else {
        json += "],\"nextCursor\":\"" + next_cursor + "\"}";
    }
    
    ReplyResult(id, json);
}

void McpServer::DoToolCall(int id, const std::string& tool_name, const cJSON* tool_arguments) {
    auto tool_iter = std::find_if(tools_.begin(), tools_.end(), 
                                 [&tool_name](const McpTool* tool) { 
                                     return tool->name() == tool_name; 
                                 });
    
    if (tool_iter == tools_.end()) {
        ESP_LOGE(TAG, "tools/call: Unknown tool: %s", tool_name.c_str());
        ReplyError(id, "Unknown tool: " + tool_name);
        return;
    }

    PropertyList arguments = (*tool_iter)->properties();
    for (auto& argument : arguments) {
        bool found = false;
        if (cJSON_IsObject(tool_arguments)) {
            auto value = cJSON_GetObjectItem(tool_arguments, argument.name().c_str());
            if (argument.type() == kPropertyTypeBoolean && cJSON_IsBool(value)) {
                argument.set_value<bool>(value->valueint == 1);
                found = true;
            } else if (argument.type() == kPropertyTypeInteger && cJSON_IsNumber(value)) {
                argument.set_value<int>(value->valueint);
                found = true;
            } else if (argument.type() == kPropertyTypeString && cJSON_IsString(value)) {
                argument.set_value<std::string>(value->valuestring);
                found = true;
            }
        }

        if (!argument.has_default_value() && !found) {
            ESP_LOGE(TAG, "tools/call: Missing valid argument: %s", argument.name().c_str());
            ReplyError(id, "Missing valid argument: " + argument.name());
            return;
        }
    }

    Application::GetInstance().Schedule([this, id, tool_iter, arguments = std::move(arguments)]() {
        try {
            ReplyResult(id, (*tool_iter)->Call(arguments));
        } catch (const std::runtime_error& e) {
            ESP_LOGE(TAG, "tools/call: %s", e.what());
            ReplyError(id, e.what());
        }
    });
}