Mcp Python Sdk

MCP Python SDK：Anthropic 主导的 Model Context Protocol 参考实现。2 server 层 + 3 transport + 3 原语 + 4 协议版本 + 50 条约束。 MCP Python SDK: reference Python implementation o...

This package is inconsistent: it presents as an MCP SDK but includes a compiled finance blueprint that tells the agent to run Python checks, install recipes, and rely on ZVT and environment paths that aren't declared. Before installing or running it, (1) verify you actually intended a finance/backtest blueprint rather than an MCP SDK, (2) open and read references/seed.yaml and human_summary.md in full to see the exact commands and preconditions, (3) do not let an agent run install or shell commands from this skill in a production environment — run them manually in a sandbox first, (4) confirm any required env vars (e.g., ZVT_HOME, API tokens) and package installs (zvt, pywin32, AnyIO, Starlette) and only provide secrets that are strictly necessary, and (5) ask the author to correct the skill metadata (declare required binaries/env, or remove unrelated finance content) — that clarification would materially reduce the risk and could change the assessment to benign.

Type: OpenClaw Skill Name: mcp-python-sdk Version: 0.1.0 The skill bundle is a comprehensive reference implementation and operational guide for the Model Context Protocol (MCP) and the ZVT quant trading library. The files (SKILL.md, seed.yaml) contain detailed instructions for an AI agent to manage data collection, factor computation, and backtesting. Security-wise, the bundle includes proactive constraints against common vulnerabilities, such as DNS-rebinding protection (mcp-C-003) and preventing internal data leakage in error responses (mcp-C-029). While the preconditions in references/seed.yaml perform file system checks (e.g., PC-04 touching ~/.zvt), these actions are strictly aligned with the stated purpose of initializing local financial databases. No evidence of malicious intent, exfiltration, or unauthorized remote execution was found.