Skip to main content

MatriX MCP

V1.1.2-Beta Build 20261105

© 2026-2026 Xu Rendong. All Rights Reserved.

Project Summary

MatriX 金融数据 MCP 工具层:让 AI 助手(Trae / Claude Code / Cursor / WorkBuddy / Codex 等)直接查询量化金融数据,自动控制返回规模。依赖 matrix-api(pip 安装本包时自动带上)。

AI Agent 自动部署指引(Agent 请照此执行)

用户要求"安装 / 使用 matrix-api-mcp"时,按以下步骤操作,用户无需手工编辑任何配置文件:

  1. 安装本包(用目标机器的 Python):
    python -m pip install matrix-api-mcp
    
  2. 向用户询问两个信息(切勿编造或留空):MatriX 数据服务地址(形如 http://host:port)与认证 token。
  3. 执行一键配置,--ide 按用户所用 IDE 选择 trae / claude / cursor / workbuddy / codex:
    python -m matrix_mcp install --ide trae --base-url http://127.0.0.1:8100 --token mx-xxxxxxxx
    
    • trae / claude 为项目级配置,须在用户项目根目录执行(可用 --project-dir 指定);其余为用户级全局配置。
    • 命令幂等可重复执行;写入前自动备份 .bak,不影响已配置的其他 MCP server。
  4. 告知用户重启对应 IDE 后生效。

手工配置参考

不想用 install 子命令时,可将下方条目合并进 IDE 的 MCP 配置(command 换成实际 Python 绝对路径):

{
  "mcpServers": {
    "matrix": {
      "command": "D:\\Python310\\python.exe",
      "args": ["-m", "matrix_mcp"],
      "env": {
        "MATRIX_API_URL": "http://127.0.0.1:8100",
        "MATRIX_TOKEN": "mx-你的认证码",
        "PYTHONUTF8": "1"
      }
    }
  }
}

Codex(~/.codex/config.toml)对应形态:

[mcp_servers.matrix]
command = 'D:\Python310\python.exe'
args = ["-m", "matrix_mcp"]
env = { MATRIX_API_URL = "http://127.0.0.1:8100", MATRIX_TOKEN = "mx-你的认证码", PYTHONUTF8 = "1" }

Contact Information

WeChat:xrd_ustc,QQ:277195007,E-mail:xrd@ustc.edu

Metadata

Release files for matrix-api-mcp 1.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for matrix-api-mcp 1.1.2
File Interpreter ABI Platform Actions
matrix_api_mcp-1.1.2-py3-none-any.whl Python 3 none any Details for matrix_api_mcp-1.1.2-py3-none-any.whl

Release files / matrix_api_mcp-1.1.2-py3-none-any.whl

Download URL matrix_api_mcp-1.1.2-py3-none-any.whl
Size 19.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
28f0b3ac8c6f175b5b67c7a6dd1f09ebddcf289eb4a43ab15b7d5d1f77f6b5b0
BLAKE2b-256 checksum
How to use checksums
2a02f1c2b6cb51647253121a9dc47fc3680ce1e528de65bcd3ee93df05a14a5e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.11

Security for matrix-api-mcp 1.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page