metacode-sci

metacode-sci

Provides read-only, offline MCP tools to find papers' own code, method chains, and evidence boundaries from a curated knowledge bundle, without executing candidate code or contacting the network.

Category
Visit Server

README

<p align="center"> <img src="./assets/readme/hero.svg" width="100%" alt="Meta-CodeGraph:通过自然语言查找科研论文自己的公开代码。"> </p>

Meta-CodeGraph 是一个本地只读的“文献—代码”知识图谱。你可以直接询问一篇论文或一种方法,获得论文自有代码的公开位置,并看到这条结果当前可以确认到什么程度。

它把两个容易混淆的问题分开回答:代码在哪里,以及它是否真的属于这篇论文。Seurat、Scanpy 等第三方工具不会被误算成论文自己的代码。

<p align="center"> <img src="./assets/readme/section-proof.svg" width="100%" alt="真实效果"> </p>

<p align="center"> <img src="./assets/readme/proof.svg" width="100%" alt="查询 POSST macrophage,返回 POSST 的 GitHub 地址、T1 和关系级导航状态。"> </p>

下面是 v0.1.0rc4 数据包的真实结果:

{
  "query": "POSST macrophage",
  "title": "Macrophage-rich niches regulate T cell dynamics at the liver invasive margin during gallbladder cancer progression.",
  "code_location_url": "https://github.com/zaozaozaonan/POSST",
  "location_kind": "GIT_REPOSITORY",
  "coverage_tier": "T1",
  "navigation_depth": "RELATION_ONLY"
}

这条结果已经确认论文自己的公开代码位置,但目前只提供关系级导航,不会假装已经定位到具体 Figure 或 Methods。

<p align="center"> <img src="./assets/readme/section-start.svg" width="100%" alt="最快跑起来"> </p>

<p align="center"> <img src="./assets/readme/workflow.svg" width="100%" alt="下载发布包、设置数据路径、运行体检并接入 MCP。"> </p>

当前版本尚未发布到 PyPI。请从 GitHub Release v0.1.0rc4 下载:

  • metacode_sci-0.1.0rc4-py3-none-any.whl
  • metacode-data-0.1.0rc4.zip
  • SHA256SUMS.txt

Windows PowerShell:

Get-FileHash .\metacode_sci-0.1.0rc4-py3-none-any.whl -Algorithm SHA256
Get-FileHash .\metacode-data-0.1.0rc4.zip -Algorithm SHA256

Expand-Archive .\metacode-data-0.1.0rc4.zip -DestinationPath .
$env:METACODE_DATA_ROOT = (Resolve-Path .\metacode-data-0.1.0rc4).Path

python -m pip install .\metacode_sci-0.1.0rc4-py3-none-any.whl
metacode-doctor

METACODE_DATA_ROOT 必须指向包含 BUNDLE_MANIFEST.json 和 content_packet_v1_1_1/ 的数据包根目录。

<details> <summary>macOS / Linux</summary>

sha256sum -c SHA256SUMS.txt --ignore-missing
unzip metacode-data-0.1.0rc4.zip
export METACODE_DATA_ROOT="$PWD/metacode-data-0.1.0rc4"

python -m pip install ./metacode_sci-0.1.0rc4-py3-none-any.whl
metacode-doctor

</details>

把 MCP 注册到 Codex、Claude Code 或其他 MCP host:

{
  "mcpServers": {
    "metacode": {
      "command": "metacode-mcp",
      "env": {
        "METACODE_DATA_ROOT": "/absolute/path/to/metacode-data-0.1.0rc4"
      }
    }
  }
}

详细接入说明:Codex · Claude Code · MCP 配置

<p align="center"> <img src="./assets/readme/section-tools.svg" width="100%" alt="可以问什么"> </p>

MCP 工具 适合的问题
find_code 这篇论文自己的公开代码在哪里?
search_analysis_routes 哪些论文和代码与这个科研问题有关?
open_research_case 打开指定论文或研究案例
trace_evidence 这条论文—代码关系有什么证据?
knowledge_status 当前数据版本覆盖了什么?

可以直接问:

ovrlpy 这篇论文自己的代码在哪里?
POSST macrophage
项目现在一共有多少代码仓库?请按证据口径拆开。

<p align="center"> <img src="./assets/readme/section-evidence.svg" width="100%" alt="结果怎么看"> </p>

层级 用户看到的含义 默认返回
T0 高置信的论文自有代码 是
T1 已确认论文自有公开位置 是
CLAIM_ONLY 论文提到代码,但没有公开地址 否
T2 第三方工具、存档或 benchmark 否
T3 论文或代码身份尚未确认 仅精确查询时

find_code 默认只返回有公开地址的论文自有代码。本地没有命中,不代表论文不存在代码。

<p align="center"> <img src="./assets/readme/section-limits.svg" width="100%" alt="使用边界"> </p>

  • 本地只读,默认不联网,不执行候选代码
  • 公开数据包不包含 PDF、论文全文、第三方仓库副本或本机路径
  • 来源文本只作为证据,不能改变工具权限
  • 软件采用 Apache-2.0
  • 项目自有注释在许可范围内采用 CC-BY-4.0
  • 第三方论文、图表和代码不由本项目重新许可

进一步阅读:数据包 · 稳定性 · 数据权利 · 安全政策

参与与引用

  • 贡献前请阅读 CONTRIBUTING.md 和 CODE_OF_CONDUCT.md。
  • 使用数据包时请优先引用原始论文;软件引用信息见 CITATION.cff。
  • 产品名是 Meta-CodeGraph,发行名是 metacode-sci,Python import 名是 metacode。

作者:做科研的 Meta 师兄

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured