Home › MCP 协议

MCP 协议

基于 stdio 的 Model Context Protocol v2024-11-05。JSON-RPC 2.0 传输，13 个 C 语言原生工具，零拷贝消息解析。

v2024-11-05MCP Version
stdioTransport
13Tools
JSON-RPC 2.0Protocol

概述

scorpiox code 将 Model Context Protocol（MCP）实现为原生 C 服务器。MCP 层使用 JSON-RPC 2.0 帧在 stdio 上运行——AI 客户端通过 stdin/stdout 连接并通过结构化 JSON 消息调用工具。所有 13 个工具都从 sx_tools.c 编译到二进制文件中，零运行时依赖。

# MCP server architecture (from sx_tools.c)

stdin  ──▶  JSON-RPC parser  ──▶  tool dispatcher  ──▶  result  ──▶  stdout

# All tools compiled into single static binary
# Source: scorpiox/libsxutil/sx_tools.c
# Zero runtime dependencies — no Node.js, no Python, no JVM

传输层

The MCP server uses stdio as its transport — the simplest, most reliable pipe. The AI client spawns the scorpiox binary and communicates via stdin/stdout using newline-delimited JSON-RPC 2.0 messages. No HTTP server, no WebSocket, no port binding. 

# Transport: stdio (stdin/stdout)
# Framing: newline-delimited JSON-RPC 2.0
# Each message is a single JSON object terminated by \n

# Client sends request →
{"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}}

# Server responds ←
{"jsonrpc": "2.0", "id": 1, "result": {"tools": [...]}}

初始化握手

Before calling tools, the client must complete the MCP initialization handshake. This establishes the protocol version and declares capabilities. 

# Step 1: Client sends initialize request
{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {
  "protocolVersion": "2024-11-05",
  "capabilities": {},
  "clientInfo": {"name": "claude-ai", "version": "1.0"}
}}

# Step 2: Server responds with capabilities
{"jsonrpc": "2.0", "id": 1, "result": {
  "protocolVersion": "2024-11-05",
  "capabilities": {"tools": {}},
  "serverInfo": {"name": "scorpiox-code", "version": "1.0.0"}
}}

# Step 3: Client sends initialized notification
{"jsonrpc": "2.0", "method": "notifications/initialized", "params": {}}

JSON-RPC 方法

The MCP server handles 4 JSON-RPC methods. All tool invocations go through tools/call.

方法 方向 Description
initialize client → server Initialize MCP session with protocol version and client capabilities
notifications/initialized client → server Notification sent after successful initialization handshake
tools/list client → server List all tools available from the MCP server
tools/call client → server Call a specific tool with JSON arguments and receive result 
# Example: calling the Bash tool
{"jsonrpc": "2.0", "id": 42, "method": "tools/call", "params": {
  "name": "Bash",
  "arguments": {"command": "ls -la /tmp", "timeout": 5000}
}}

# Server response
{"jsonrpc": "2.0", "id": 42, "result": {
  "content": [{"type": "text", "text": "total 48\ndrwxrwxrwt 12 root root ..."}],
  "isError": false
}}

工具目录 (13)

All tools are implemented in scorpiox/libsxutil/sx_tools.c and compiled into the static binary. Each tool declares a JSON Schema for input validation.

Bash shell

Execute a bash command

参数: command, timeout
必填: command
ReadImage filesystem

Read an image file and display it visually

参数: file_path
必填: file_path
ReadDocs web

Fetch URL content as markdown via headless browser

参数: url, format, wait_ms
必填: url
WebSearch search

Search the web using 11 engines concurrently

参数: query
必填: query
TaskManager workflow

Manage persistent tasks with create/add/complete

参数: action, query, task_id, step_id, text
必填: action, query
PlanMode workflow

Manage plan mode for complex tasks

参数: action, goal, plan_file
必填: action
AskUserQuestion interaction

Ask interactive multiple-choice questions via TUI

参数: questions_json
必填: questions_json
InvokeSkill workflow

Invoke a skill by name for reusable workflows

参数: skill_name, arguments
必填: skill_name
BackgroundBash shell

Execute bash command in background, returns immediately

参数: command
必填: command
ReadBgOutput shell

Read new output from a background task

参数: task_id
必填: task_id
ListBgTasks shell

List all background tasks with status and runtime

参数: —
必填: —
KillBgTask shell

Kill a running background task by ID

参数: task_id
必填: task_id
SetCallback workflow

Manage scheduled callback messages with repeats

参数: action, message, delay_seconds, repeat_count, callback_id
必填: action

工具模式参考

Complete input_schema for each tool, as declared in the tools/list response.

Bash shell
参数TypeStatusDescription
command string required The bash command to execute
timeout integer optional Timeout in milliseconds (default: 30000)
ReadImage filesystem
参数TypeStatusDescription
file_path string required The absolute path to the image file
ReadDocs web
参数TypeStatusDescription
url string required The URL to fetch
format string optional Output format: text, html, or markdown
wait_ms integer optional Wait time for page load in ms
WebSearch search
参数TypeStatusDescription
query string required The search query
TaskManager workflow
参数TypeStatusDescription
action string required Action: create, add, complete, list, pending, switch
query string required The search query
task_id integer optional Task ID
step_id integer optional Step ID
text string optional Task name or step text
PlanMode workflow
参数TypeStatusDescription
action string required Action: enter, exit, status, json, reset
goal string optional Goal/description
plan_file string optional Path to markdown plan file
AskUserQuestion interaction
参数TypeStatusDescription
questions_json string required JSON string with questions and options
InvokeSkill workflow
参数TypeStatusDescription
skill_name string required The skill name to invoke
arguments string optional Arguments to pass to the skill
BackgroundBash shell
参数TypeStatusDescription
command string required The bash command to execute
ReadBgOutput shell
参数TypeStatusDescription
task_id integer required The task ID returned by BackgroundBash
KillBgTask shell
参数TypeStatusDescription
task_id integer required The task ID to kill
SetCallback workflow
参数TypeStatusDescription
action string required Action: set, list, cancel
message string optional Callback message
delay_seconds integer optional Seconds to wait (1-3600)
repeat_count integer optional Times to fire before cancel
callback_id integer optional Callback slot ID

配置

MCP is enabled by default. The server advertises tools capability during initialization. Configuration is handled via scorpiox-env.txt. 

# scorpiox-env.txt — MCP-related settings

TOOLS=true                  # Enable MCP tool serving (default: true)
STREAMING=true              # Stream tool results as they arrive
MODEL=sonnet                # AI model for tool-use conversations

# The MCP server binary path is auto-detected:
# Linux:   ~/.scorpiox/scorpiox-code
# macOS:   ~/.scorpiox/scorpiox-code
# Windows: %USERPROFILE%\.scorpiox\scorpiox-code.exe

# Client config (e.g., Claude Desktop mcp_servers.json):
# {"scorpiox": {"command": "~/.scorpiox/scorpiox-code", "args": []}}
© 2025 scorpiox — 与众不同。