Skip to main content
AllMCPs
BrowseBestCategoriesStackCompareToolsGuidesBlog
Log in Submit MCP

Stay in the loop

Get new MCP servers and top picks in your inbox.

AllMCPs

The open directory for discovering and installing Model Context Protocol servers.

AllMCPs on GitHub (opens in a new tab)
Launched onTiny Startupstinystartups.com
Explore
  • Browse servers
  • Best MCP servers
  • Categories
  • MCP clients
  • Agent prompts
  • Stack Builder
  • Compare servers
  • Random discovery New
  • Submit a server
  • Pricing & Boost Boost
Learn
  • Guides hub
  • What is MCP?
  • Install guide
  • Build an MCP server
  • Deploy an MCP server
  • Security guide
  • Troubleshooting
  • MCP for SEO & AEO
  • Protocol versioning
  • Transports: stdio vs HTTP
  • State of MCP (stats)
  • Blog & updates
Tools
  • All developer tools
  • Config generator
  • Config validator
  • Config auditor
  • MCP playground
  • Token calculator
  • OpenAPI → MCP
  • Badge generator
For agents
  • REST API docs
  • Trust & traffic Live
  • Remote MCP server SSE ↗ (opens in a new tab)
  • llms.txt ↗ (opens in a new tab)
  • Catalog JSON ↗ (opens in a new tab)
Company
  • About
  • Advertise Sponsor
  • Contact
  • GitHub ↗ (opens in a new tab)
  • Terms
  • Privacy
AllMCPs VerifiedAllMCPs VerifiedFeatured on Nick LaunchesFeatured on Nick LaunchesLaunch Llama NewsletterLaunch Llama NewsletterVerified DR - allmcps.comVerified DR - allmcps.comFeatured on SaaSGrowFeatured on SaaSGrowFeatured on Twelve ToolsFeatured on Twelve ToolsFeatured on Saaspa.geFeatured on Saaspa.geFeatured on Findly.toolsFeatured on Findly.toolsFeatured on Startup FameFeatured on Startup FameFeatured on LaunchKiwiFeatured on LaunchKiwiFeatured on ScrollLaunchFeatured on ScrollLaunchFeatured on DailyPingsFeatured on DailyPingsFazier badgeFazier badgeFeatured on NewTool.siteFeatured on NewTool.siteFeatured on saasfame.comFeatured on saasfame.comDR Checker - Domain RatingDR Checker - Domain RatingListed on Turbo0Listed on Turbo0Launched on LaunchBoard - Product Launch PlatformLaunched on LaunchBoard - Product Launch PlatformList on SimilarlabsList on Similarlabshttps://codetrendy.comhttps://codetrendy.comListed on DevTool.ioFeatured on BuildlistFeatured on BuildlistLaunched on Tiny StartupsFeatured on ShowMeBestAIFeatured on ShowMeBestAIFind us on LaunchZoneFind us on LaunchZoneAllMCPs VerifiedAllMCPs VerifiedFeatured on Nick LaunchesFeatured on Nick LaunchesLaunch Llama NewsletterLaunch Llama NewsletterVerified DR - allmcps.comVerified DR - allmcps.comFeatured on SaaSGrowFeatured on SaaSGrowFeatured on Twelve ToolsFeatured on Twelve ToolsFeatured on Saaspa.geFeatured on Saaspa.geFeatured on Findly.toolsFeatured on Findly.toolsFeatured on Startup FameFeatured on Startup FameFeatured on LaunchKiwiFeatured on LaunchKiwiFeatured on ScrollLaunchFeatured on ScrollLaunchFeatured on DailyPingsFeatured on DailyPingsFazier badgeFazier badgeFeatured on NewTool.siteFeatured on NewTool.siteFeatured on saasfame.comFeatured on saasfame.comDR Checker - Domain RatingDR Checker - Domain RatingListed on Turbo0Listed on Turbo0Launched on LaunchBoard - Product Launch PlatformLaunched on LaunchBoard - Product Launch PlatformList on SimilarlabsList on Similarlabshttps://codetrendy.comhttps://codetrendy.comListed on DevTool.ioFeatured on BuildlistFeatured on BuildlistLaunched on Tiny StartupsFeatured on ShowMeBestAIFeatured on ShowMeBestAIFind us on LaunchZoneFind us on LaunchZone
© 2026 Jackalope Digital LLC. All rights reserved.
  1. Home
  2. 💻 Developer Tools
  3. AKShare
A
Health: Not checked yetWe have not completed a health check for this listing yet.No health check has run yet.

AKShare

User RatingsBe the first to rate and review this MCP server! Enrichment pendingWe haven’t run our AI enrichment pass on this listing yet, so the overview, use cases, and FAQ below may be sparse or missing. We work through the catalog over time — check back soon.
View Repository

Let a model explore AKShare's 1000+ China market data functions on its own — search, inspect, call

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.

Manual Client & Custom JSON ConfigExpand JSON ▾
No confirmed setup config for this listing yet. We only publish a config block when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for AKShare, and we’d rather show nothing than a guess you’d paste into your client. Follow the project’s own setup instructions for the current steps.
Install Directory Badge Claim listing Alternatives💻 More in Developer Tools

Documentation Overview

🌏 中文(当前)· English

HunterCode

HunterCode

Community Edition

自部署的 AI 投研助手 · A股 / 港股 / 美股 · 数据和对话都在你自己的机器上

HunterCode 是腾讯 WorkBuddy 金融版的开源本地替代方案 · 面向私募与专业个人投资者
腾讯、WorkBuddy 是腾讯公司的商标。HunterCode 与腾讯公司无隶属、合作或授权关系。

License CI Release Stars Discussions

HunterCode 演示:功能总览 → 选股器扫描 A股/港股/美股 → 小鹿智能体研究台

🚀 在线演示  ·  ⚡ 5 分钟部署  ·  📖 文档  ·  💬 讨论区

🏆 入围世界人工智能开源大赛(GOAI)总决赛 · 赛道二 TOP 15 · 与 WorkBuddy 金融版逐项对比(附官方来源) · 完整演示视频 3 分钟(2026-09-19 录制)

⚠️ 免责声明:本项目是投研分析工具,所有输出为 AI 生成内容,仅供研究参考,不构成任何投资建议。投资有风险,决策需谨慎。


⏱ 30 秒看懂

它是什么 —— 一个跑在你自己电脑或服务器上的金融 AI 助手。你给它一个大模型 key,它就能查行情、拉新闻、做个股深度分析、预测走势、管理自选和持仓,并按你写的 SKILL(分析方法论)工作。对话、持仓、投资论点全部存在本地数据库。

它不是什么 —— 不接券商交易,不替你做决策,不保证预测准确。它是把公开数据、分析方法论和大模型组织起来的研究助手。

适合谁 —— 会用 Docker 的个人投资者、私募研究员、小型量化团队;想掌控自己的数据,或想把自己的数据源和方法论接进来的人。


☁️ 一键部署到云平台

不想自己管服务器的,可以直接部署到下面这些平台,部署完打开域名走一遍首启向导就能用。

平台适合谁说明
Zeabur国内外都能用,能力最全模板自动生成密钥、绑域名、挂卷
Sealos国内用户K8s 模板,postgres / redis 走 KubeBlocks
Railway海外用户控制台里手工搭 6 个服务的逐条清单 + 生成模板的步骤
1Panel自有服务器 + 国产面板应用包,表单里填端口和口令即可
Coolify / Dokploy自有服务器 + 自托管 PaaS两份可以整段粘贴的 compose

ℹ️ 这一版还没有「一键部署」按钮。 我们没有这些平台的账号,一次真实部署都没做过, 更没有上架到任何一家的模板市场 —— 所以不放按钮,只给文档。 每份模板都做过等价验证:把模板机械翻译成 compose(同镜像、同环境变量、 用平台自己的方式生成的随机密钥、同卷、同依赖),在本机从空卷跑完 「六服务健康 → 走完向导 → 真实对话 → 深度分析 → 重启数据不丢」。 各篇文档里都写明了「哪些验过、哪些没验过、平台上要自己核对什么」。 有账号的朋友帮忙实测一次,欢迎来 Issues 说结果 —— 验过就加按钮。

公网部署必看:这些平台上的实例一创建就在公网上。模板都默认 关掉了单用户免登录(HUNTER_SINGLE_USER=0)并生成了一道初始化口令 HUNTER_SETUP_TOKEN,向导第 0 步要填它 —— 不然谁先打开谁就能把大模型配成他自己的。 口令在平台的环境变量面板里看。


🖥 桌面启动器(推荐给不熟悉命令行的用户)

下载 → 填一把 key → 等几分钟,整套 HunterCode 自动装好,全程不用敲一条命令。

装完打开按向导走:欢迎 → 填 key → 一次授权 → 选模型 → 自动安装。检测 Docker、挑下载源、 算端口、写配置、拉镜像、起容器由它连着跑完,装好自动打开浏览器。 启动器仓库:agentpit-io/HunterLauncher · 图文说明与截图:www.agentpit.io/hunter-community

最新版本 —— 徽章上就是当前最新版,下面的链接永远指向它,不用找版本号。

平台直接下载(国内可达)其他来源
macOS 12+ · Intel / Apple 芯片通用hunter-launcher-latest-universal.dmgGitHub Releases
Windows 10 / 11 · x64 · 推荐hunter-launcher-latest-x64-setup.exeGitHub Releases
Windows · 组策略分发hunter-launcher-latest-x64.msiGitHub Releases
Linux x64hunter-launcher-latest-amd64.deb / .AppImageGitHub Releases

这几个链接是固定的:每次发版都会把最新安装包覆盖到同一个地址, 所以收藏它、贴进文章、做成二维码都不会失效。

想要带版本号的包、逐个文件的 sha256、或是历史版本,看 checksums.txt、manifest.json 与 Releases。manifest.json 里有当前版本号、发布日期与三个包的 体积和完整 sha256 —— 下载页 显示的就是它。

系统要求

  • macOS 12+(Intel / Apple 芯片通用)—— 不需要你先装 Docker。本机没有 Docker 时, 启动器会自己准备一套运行环境(内置 Colima + Lima,全装在 ~/.hunter/runtime), 不碰你已有的 ~/.colima、~/.lima、别人的容器与数据卷。本机已有 OrbStack / Docker Desktop / Colima 的话它一个字节都不下。
  • Windows 10 / 11 · x64 —— 需要你先装好 Docker Desktop 与 WSL2。 Windows 上装 Docker Desktop 要 WSL 与管理员权限,启动器这一版还没有做这条链路; 装好 Docker Desktop 之后回来点一次「重新检测」就能继续。

安装包没有做代码签名,第一次打开要放行一下

  • Windows:SmartScreen 会拦一下 —— 点「更多信息」→「仍要运行」。
  • macOS:不要双击,在图标上右键 → 打开,在弹出的对话框里再点一次「打开」。

现状(如实说明)

  • 目前每一版都标预发布(prerelease),原因就是上面那条:包没有代码签名。
  • macOS 已在真机验证过全流程:2026-09-23 在 Intel · macOS 14.8.5 上跑通了自动准备运行环境 (虚拟机层第一次在真虚拟机上跑通)、开机自检、每日定时备份(LaunchAgent 强制触发后真跑出备份)、 删除应用,以及「备份 → 删除 → 重装 → 恢复」闭环(重装 57 秒、6/6 服务健康、数据原样沿用)。 · 已知问题:0.1.13 及更早版本在 macOS 上的「自动更新」不可用(会下错成 Linux 的包), 这几版升级请手动下载新安装包覆盖安装。
  • Windows 尚未真机验证:只在 CI 里编译与打包通过,没有在任何一台真 Windows 上跑过。 你是第一个跑的话,欢迎来 Issues 说结果。
  • Linux 在测试机上真机跑通过从零安装、升级、回滚与离线导入。

想自己敲命令,或者要装到远程服务器上,往下看「5 分钟跑起来」—— 两条路装出来的是同一套东西。


🚀 5 分钟跑起来

准备:Docker Desktop(Windows / macOS)或 Docker Engine + Compose v2(Linux) · 磁盘 10 GB · 内存 4 GB(实测峰值约 1.3 GB) · 能访问 ghcr.io

六个服务的镜像都同时提供 amd64 与 arm64,Apple Silicon 与 arm 云主机原生运行,不用模拟。

[!IMPORTANT] 开始前只需要理解两件事

  1. 模型从哪来。推荐走 HunterCode 内置额度:免费申请一把 hunt_tools_ 平台 key(约 30 秒),在向导第 2 步选第一张卡,不用自己去各家申请大模型 key,地址和模型名向导自动填好。详见 内置额度使用说明。 · 额度:每把 key 每天 1000 万 token(输入 + 含 thinking 的输出),北京时间 0 点重置;另有每分钟请求数与并发上限。额度用完不是断服 —— 对话里会用中文说清几点重置、怎么改用自带 key,工具与数据供给照常。额度与服务可能调整或下线。 · 隐私:网关只记 token 数与模型名,不记任何 prompt 与回复内容。 · 使用前请读一遍 服务条款与可接受使用政策(English) —— 仅限自部署用户的研究用途,禁止转售、禁止当通用 API 用。 高级路径:自带大模型 key —— DeepSeek 或任何 OpenAI 兼容网关(通义、Claude、GPT、OpenRouter、OneAPI、AIHubMix 等)都行,向导里粘进去当场检测。两条路随时互相切换。
  2. 数据从哪来(三选一,可以先不管):① 免费开源源(A 股行情要在 .env 设 DATA_SOURCE_PROVIDER=akshare);② 接你自己的 MCP / 数据源;③ 平台数据管道,免费申请 key。详见 数据供给三选一。 走内置额度的话这一步已经顺带解决了 —— 同一把 hunt_tools_ key 也是数据供给的 key,向导会直接告诉你已解锁。

耗时:自 v1.1.0 起六个服务全部走预构建镜像,不再本地构建 —— 首次约 3–5 分钟(全在下镜像),之后 up -d 几十秒。向导本身约 1 分钟。

bash
git clone https://github.com/agentpit-io/hunter-community
cd hunter-community
docker compose up -d
open http://localhost:3100          # 浏览器里完成首启向导,不用改任何文件

没有第二步。 自 v1.1.0 起 .env 一个字都不用改 —— 密钥自动生成、数据库自动迁移、 六个服务全走预构建镜像;大模型在浏览器里配。

浏览器里的首启向导

第一次打开会自动进入向导(没配大模型时),五步:

步骤做什么
1 · 环境自检六个服务连通、迁移账本、密钥来源与强度、卷可写、访问方式 —— 逐项真探测
2 · 选大模型第一张卡是「使用 HunterCode 内置额度」(推荐):选中即自动填好地址与模型名,你只要一把 hunt_tools_ key。下面几张是自带 key 的高级路径,带实测的工具调用命中率与耗时(来自 docs/model-testing/)
3 · 填 key 当场测连通 → 对话 → 工具调用三项,失败分类报错,测不通不让保存;内置额度路径下还会顺带把深度分析指向 hunter-deep、用同一把 key 解锁数据供给
4 · 数据供给免费开源源 / 平台数据管道 / 自接 MCP,三选一,可以跳过。走内置额度的话这里会直接显示「同一把 key 已解锁」
5 · 完成不重启任何容器热生效,给三个示例问题带你进对话

第 2 步 · 内置额度是第一张卡

全部截图见 docs/screenshots/builtin-llm/(内置额度全流程) 与 docs/screenshots/setup-wizard/(自带 key 路径)。

[!IMPORTANT] 这台实例只要能从公网打开,就先在 .env 里设 HUNTER_SETUP_TOKEN(随便一串随机值, openssl rand -base64 24),然后 docker compose up -d。 不设的话,谁先打开这个页面谁就能配置大模型 —— 向导判断「来源是不是本机」靠的是 HTTP 转发头,裸 docker compose(前面没有 nginx 之类的反代)时那是访问者可以伪造的。 设了之后向导第 0 步会要这个口令,连错 5 次锁 15 分钟。本机 / 内网使用不需要设。

想走老路(在 .env 里写死)也行,而且优先级更高:填了 LLM_BASE_URL / LLM_API_KEY / LLM_DEFAULT_MODEL 的实例是锁定状态,向导只读展示、改不了它(演示站就是这么跑的)。 要换模型改 .env 后 docker compose up -d(不是 restart —— restart 不重读 .env)。 内置额度也能写死(一键部署模板会这么预填),写法见 内置额度使用说明 · 第六节。

不配大模型时六个服务照样健康,只是发消息会收到一句中文的「大模型尚未配置」。 想以后再配,向导最后一步点「先进对话页(稍后再说)」即可; 要重新跑向导:设置 → 大模型 → 「重新运行初始化向导」。

要改代码的开发者叠加开发覆盖文件 —— 它带回本地构建与全部源码挂载(改 apps/web/public 下的静态文件、scripts/ 下的 MCP 与插件都立即生效):

Terminal
docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d --build

从 v1.0.x 升级

bash
git pull
docker compose pull && docker compose up -d
bash scripts/migrate-volumes.sh          # ⚠️ 只有老用户需要,见下

[!WARNING] 装过 SKILL / 导入过数据包的老用户必须跑一次 scripts/migrate-volumes.sh。 v1.0.x 把 ./user-skills 和 ./data-packages 两个仓库目录直接挂给 api; v1.1.0 起改成 api 自己的具名卷 —— 云平台上没有仓库目录,挂不了。 直接升级的话新卷是空的,你装过的 SKILL 会从界面上消失。 文件一个都没丢(还在 user-skills/ 下),这个脚本就是把它们搬进新卷; 幂等,目标非空时不覆盖。api 启动日志里也会提示。

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives
  • O
    Openapi MCP Server

    Connect any HTTP/REST API server using an Open API spec (v3)

    💻 Developer Tools3 views
    Compare vs Openapi MCP Server →
  • C
    Claude Task Master

    AI-powered task management system for AI-driven development. Features PRD parsing, task expansion, multi-provider support (Claude, OpenAI, Gemini, Perplexity, xAI), and selective tool loading for optimized context usage.

    💻 Developer Tools8 views
    Compare vs Claude Task Master →
  • M
    MCP Server Docker

    Integrate with Docker to manage containers, images, volumes, and networks.

    💻 Developer Tools3 views
    Compare vs MCP Server Docker →
  • N
    Next Devtools MCP
    Verified

    Official Next.js MCP server for coding agents. Provides runtime diagnostics, route inspection, dev server logs, docs search, and upgrade guides. Requires Next.js 16+ dev server for full runtime features.

    💻 Developer Tools6 views
    Compare vs Next Devtools MCP →

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about AKShare

We don't have a confirmed install command for AKShare yet, so we don't publish a generated one — a guessed package name would point at the wrong package or none at all. Follow the project's own README or setup instructions (https://github.com/agentpit-io/hunter-community) for the current steps.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAKShare AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/akshare?style=directory)](https://allmcps.com/mcp/akshare)
HTML Embed
<a href="https://allmcps.com/mcp/akshare"><img src="https://allmcps.com/api/badge/akshare?style=directory" alt="AKShare on AllMCPs" /></a>

Technical Specs & Signals

Category💻Developer Tools
More technical detailsExpand ▾
Last updatedSep 28, 2026
Views0
Unique ViewsTotal visits recorded for this listing page on AllMCPs.
Installs0
Installs & Copy ActionsTotal times users copied install commands or configuration snippets for this server.
27Quality signal: Emerging · 27/100How this signal is calculated ▾
Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20
Documentation & tools11/30
Adoption & activity1/15
Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Featured
A

AllMCPs Server

The official MCP server for AllMCPs.com - submit and manage tools directly from your AI. The open directory for MCP servers. Connect Claude, Cursor, Windsurf, and AI agents to databases, tools, files, and APIs. Explore 10,000+ servers. AllMCPs is the premier, open directory for discovering, evaluating, and installing Model Context Protocol (MCP) servers to equip AI agents and LLMs with real-world superpowers.

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge and attach your website — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to AKShare →Install in Claude DesktopInstall in CursorInstall in VS CodeSetup guides for all 13 MCP clients