AI Workstation Open Source Intelligence

io.github.zxhwolfe-dev由 GitHub 账号 zxhwolfe-dev 发布v0.3.3更新于 Oct 24, 2026

Read-only AI project discovery, verification, comparison, shortlisting, and stack planning.

发布方自己的服务：Source

已验证Streamable HTTP可网页运行知识与记忆开发者工具

概览

AI 生成的概览

只读的远程 MCP 服务器，用于调研开源 AI 项目：搜索、核实事实与许可证、比较项目并规划技术栈。

可以做什么
按明确需求搜索并核实开源 AI 项目，获取指定项目有证据支撑的公开事实，包括观测到的许可证证据（不构成法律意见）。在明确的决策场景下比较两到五个项目，或在保留硬性约束的前提下寻找经过核实的替代方案。组合候选开源 AI 技术栈并暴露未知的兼容性。浏览 Radar 的排名、合集、分类、场景、主题与筛选条件，并浏览或按 ID 打开 Radar Skills 库中的条目。结果区分已核实事实、建议、未知项与风险。
适用场景
当你需要按部署、隐私、集成、预算或许可证要求筛选、比较或核查开源 AI 项目，或在不安装、不运行任何第三方代码的情况下拟定候选技术栈时适用。
运行要求
远程 streamable HTTP 端点；未声明需要身份验证、API 密钥或环境变量。README 说明匿名访问有按 IP 的速率限制（例如短窗口每分钟 60 次请求、持续每分钟 10 次）以及 256 KB 请求体上限。另提供用于开发的本地 Python 包方式。
安装前请注意
只读且仅提供数据：不会执行或安装第三方仓库代码，也不暴露服务端模型调用或结账功能。许可证输出属于技术证据而非法律意见，缺少许可证不应视为获得授权。兼容性结论可能未经核实，会以未知项呈现；结果中包含发布方链接，不应将其当作已核实事实。

安装

在 SourceWeft 中

  1. 打开 控制台中的 AI Workstation Open Source Intelligence，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.zxhwolfe-dev%2Faiworkstation-open-source-intelligence/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "ai-workstation-open-source-intelligence": {
      "type": "http",
      "url": "https://mcp.aiworkstation.cn/mcp"
    }
  }
}

README

AI Open Source Intelligence

One Skill. Nine live read-only Radar tools. Evidence-backed open-source AI research without a second server-side model call.

简体中文 · Product page · AI Open Source Radar · Quickstart

AI Open Source Intelligence is the Skills/MCP product layer for AI Open Source Radar.

[AI Open Source Radar production homepage showing rankings, project cards, and the AI Open Source Intelligence product entry]

Production screenshot captured 2026-08-29. Rankings and project data update with Radar snapshots.

Product shape

text
User in ChatGPT / Codex / compatible host                 |                 v      1 unified product Skill                 |                 v      9 read-only MCP tools                 |                 v     AI Workstation public Radar

The user does not choose separate research/comparison/stack Skills. The single Skill routes the task internally.

The host model performs natural-language reasoning and synthesis. The AI Workstation server provides data/evidence only on this product path.

One active Skill

text
ai-open-source-intelligence

It handles:

  • browsing rankings, collections, categories, scenarios and the Radar Skills library;
  • finding projects from deployment, privacy, integration, budget and license requirements;
  • verifying named-project facts and license evidence;
  • comparing two to five projects for a concrete use case;
  • finding alternatives while preserving hard requirements;
  • planning candidate open-source AI stacks and exposing unverified compatibility.

The only product Skill is packaged from:

text
skills/ai-open-source-intelligence/SKILL.mdskills/ai-open-source-intelligence/agents/openai.yaml

agents/openai.yaml makes the Skill's dependency on the canonical ai_open_source_intelligence Hosted MCP explicit while keeping automatic invocation enabled. This is the Skill-level dependency contract; .mcp.json is the matching Plugin-level connection contract.

The previous split research/comparison/stack Skill files are removed from the current product and distribution bundle.

Nine standard MCP tools

text
search_ai_projectsget_project_factsget_license_evidencecompare_ai_projectsfind_alternativescompose_ai_stackget_radar_overviewbrowse_radar_projectsbrowse_radar_skills

All nine are read-only. They do not execute or install third-party repository code.

No AI Workstation server-model execution

This is a hard product boundary for the current release.

The Hosted MCP exposes no Premium model tool, no checkout tool and no runtime OAuth/Premium switch. Requirement-based selection calls the public Radar selector with:

text
use_model=false

Therefore an ordinary Skill/MCP workflow is:

text
ChatGPT/Codex host model        -> chooses/read tools        -> AI Workstation public Radar data/evidence        -> host model synthesizes the final answer

It is not:

text
host model -> AI Workstation model -> second model bill

If member-linked server-model capabilities are added later, they must ship as a new reviewed product version rather than being enabled through a hidden environment variable.

Evidence model

Every tool result separates:

  1. verified facts — source-backed observations that crossed the evidence boundary;
  2. recommendations — host-model/rules analysis;
  3. unknowns — unavailable or unverified information;
  4. risks — license, maintenance, deployment, security and integration limits.

A value in data is not automatically a verified fact. License evidence is deliberately stricter and is technical evidence, not legal advice.

Requirement tools publish the actual typed constraint contract through MCP:

json
{"id":"web_ui","value":true,"polarity":"required"}

Formal matches are revalidated against project-detail evidence. README excerpts may directly verify narrow Docker, self-hosting, browser UI and low/no-code claims; unresolved hard requirements become near-match blockers. A License label is exposed only as observed_license_label until a direct LICENSE-family source supports a verified license fact. Response observation time and evidence-source freshness are reported separately.

Official resources in results

MCP tool results include canonical, non-tracking publisher links under:

text
data.official_resources

with:

The unified Skill may show these once at the end of a normal user-facing answer. They are kept separate from verified facts so publisher attribution never changes a research conclusion.

Hosted MCP

Canonical endpoint:

text
https://mcp.aiworkstation.cn/mcp

Current Hosted mode is intentionally:

text
anonymousread-onlydata-only9 toolsno OAuthno WorkOS dependencyno Premium/server model

The container stays on host loopback 127.0.0.1:8001 behind Nginx/TLS.

Anonymous abuse controls

The gateway uses two per-IP request windows plus a connection cap:

  • short-window: 60 requests/minute, burst 30;
  • sustained: 10 requests/minute, burst 300;
  • concurrent connections: 10 per IP;
  • MCP request body: 256 KB maximum;
  • unrelated paths on the dedicated MCP hostname return 404.

This is intentionally request-based rather than token-based because the nine data tools do not consume AI Workstation model tokens.

Use it now

The published v0.3.3 Plugin packages the unified Skill and the production Hosted MCP configuration together. Codex and the ChatGPT desktop Codex host can install both from one version-pinned marketplace entry. The public ChatGPT directory listing is still pending review. Today:

  • Codex / ChatGPT desktop users can install the complete repository Plugin;
  • ChatGPT web users can register https://mcp.aiworkstation.cn/mcp as a No Authentication developer-mode app while the public listing is pending;
  • Python users can install the matching CLI/MCP package from PyPI with:
bash
python -m pip install \  "aiworkstation-open-source-intelligence[mcp]==0.3.3"

See the Quickstart for exact ChatGPT, Codex and Python steps and the v0.3.3 Release for signed-off assets and checksums. The immutable v0.3.0 archive remains the earlier Skills-only artifact; the complete Plugin uses the current v0.3.3 patch identity rather than replacing it.

Local development

bash
python -m venv .venvsource .venv/bin/activatepython -m pip install -e ".[mcp]"

Offline fixture data:

bash
OSI_PROVIDER=mock osi-mcp

Live public Radar data:

bash
OSI_PROVIDER=http \AIWORKSTATION_RADAR_BASE_URL=https://aiworkstation.cn \osi-mcp

Hosted configuration check requires an exact candidate identity:

bash
OSI_PROVIDER=http \OSI_HOSTED_ACCESS_MODE=public \OSI_RELEASE_COMMIT=<exact-40-char-sha> \OSI_IMAGE_COMMIT=<same-exact-40-char-sha> \osi-mcp-hosted --check-config

Setting OSI_HOSTED_ACCESS_MODE=oauth fails closed in the current release.

Safety rules

  • never execute third-party repository code as part of research;
  • never infer permission from a missing license;
  • never silently weaken a hard requirement to manufacture a match;
  • never claim cross-project compatibility without evidence or a controlled test;
  • never substitute model memory for unavailable live evidence;
  • never enable AI Workstation server-side model execution in the current standard Skill/MCP path.

Development checks

bash
python -m compileall -q src testspython -m unittest discover -s tests -vosi-validate-plugin --root .osi-readiness --root .

CI covers Python 3.10 and 3.12, deterministic Skill packaging, MCP round trips, data-only Hosted configuration and container packaging.

License

The public repository is licensed under Apache-2.0. That does not grant rights to private AI Workstation databases, unpublished datasets, credentials, infrastructure or trademarks.

来源：README.md，提交 73ada4a

工具

9

search_ai_projects

Search open-source AI projects

Find and verify open-source AI projects from explicit requirements.

输入参数query必填localerequest_idconstraints

get_project_facts

Get verified project facts

Get current evidence-backed public facts for one project.

输入参数localeproject_id必填request_id

get_license_evidence

Get project license evidence

Get observed license evidence; the result is not legal advice.

输入参数localeproject_id必填request_id

compare_ai_projects

Compare open-source AI projects

Compare two to five projects in one explicit decision context.

输入参数localecontextcriteriarequest_idproject_ids必填

find_alternatives

Find open-source project alternatives

Find verified candidate alternatives while preserving constraints.

输入参数localeproject_id必填request_idconstraints

compose_ai_stack

Compose an open-source AI stack

Compose a candidate open-source AI stack and expose unknown compatibility.

输入参数localerequest_idconstraintsbusiness_goal必填existing_stack

get_radar_overview

Get AI Open Source Radar overview

Discover current rankings, collections, categories, scenarios and filters.

输入参数localerequest_id

browse_radar_projects

Browse AI Open Source Radar projects

Browse rankings, collections, categories, scenarios, topics or filtered projects.

输入参数rolelayerlimitquerytopiclocaleoffsetlicenserankingcategoryscenariouse_case另有 6 个

browse_radar_skills

Browse AI Open Source Radar Skills

Browse/filter the Radar Skills library or open one Skill by ID.

输入参数kindsortlimitquerylocaleoffsetlicensecategoryskill_idrequest_idinstallable

版本历史

1
  1. v0.3.3最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Source 集成

Source

app.source官方发布者

Source 提供的远程 MCP 端点，让助手访问已接入 Source 的网站的营销归因与分析数据。

Streamable HTTP可网页运行鉴权
数据与分析需要凭据Nov 5, 2026

ArxSource

由 GitHub 账号 nicolaiprodromov 发布

本地 MCP 服务器，让助手检索 arXiv 论文、按章节或 LaTeX 原文阅读、追踪引用，并找到论文对应的代码。

STDIO仅桌面
开发者工具尚未验证Nov 7, 2026

SourceMed

io.sourcemed

SourceMed 为助手提供经来源核实的临床证据库：可提出证据问题、浏览书架并阅读带引用的卡片。

STDIO仅桌面
AI 与机器学习4 个工具Nov 6, 2026

Spree Commerce: open-source B2B and marketplace ecommerce

由 GitHub 账号 spree 发布

Spree 的 MCP 服务器让 AI 助手用自然语言管理 Spree 商店的商品目录、回答报表问题并完成店铺设置。

Streamable HTTP可网页运行
商业与电商尚未收录Nov 6, 2026

PlushSource

由 GitHub 账号 quickman924 发布

本地 MCP 服务器，内置定制毛绒玩具制造商名录，让助手搜索、筛选、比较并引用厂商条目。

STDIO仅桌面
商业与电商5 个工具Nov 3, 2026