BullRun
Stock screening, company financials, ETF search, and personal portfolio analysis over a remote OAuth-protected MCP server https://mcp.bull-run.org/mcp
README
Bullrun MCP
A hosted remote MCP server that turns Claude (and other MCP clients) into a stock-research analyst over global market data and your own portfolios.
| Endpoint | https://mcp.bull-run.org/mcp — Streamable HTTP, OAuth 2.1 + PKCE |
| Web app | https://bull-run.org |
| Official MCP Registry | org.bull-run/bullrun |
| Glama connector | https://glama.ai/mcp/connectors/org.bull-run/bullrun |
| Privacy policy | https://bull-run.org/privacy |
Bullrun is a hosted service — there is nothing to install and no API key to manage. You point your MCP client at the remote endpoint and sign in with Google. This repository holds the connector's public metadata (
server.json) and connection docs; the service source is maintained privately.
Connect
Claude (web, Desktop, mobile) — requires a paid Claude plan:
- Settings → Connectors → Add custom connector
- Name it
Bullrun, pastehttps://mcp.bull-run.org/mcp, and add it. - Click Connect and complete the Google sign-in / authorize step.
Claude Code:
claude mcp add --transport http bullrun https://mcp.bull-run.org/mcp
Full setup for Cursor, VS Code, and the MCP Inspector is in docs/mcp-connect.md.
What you can do once connected
Public market-data tools work for any connected client. The portfolio tools resolve your own Bullrun account after Google sign-in; the two draft tools require a Bullrun Pro account.
| Tool | What it does |
|---|---|
screen_stocks |
Screen the global universe by sector / industry / country / market cap; sort by P/E, dividend yield, revenue or revenue growth. |
get_stock_metrics |
Consolidated snapshot for one ticker — identity (ISIN/LEI/CIK), latest price, valuation, most recent financials, description. |
get_financial_history |
1–15 fiscal years of annual/quarterly statements, per-share metrics, margins, CAGRs and consistency checks. |
get_quality_moat_metrics |
ROIC, ROIC-vs-WACC spread, ROE/ROA, accruals, cash conversion, capex intensity, dividend payout/growth, buyback proxy. |
get_forward_estimates |
Consensus revenue / EPS / EBITDA, guidance, estimate revisions, and derived forward P/E & PEG context. |
get_operating_kpis |
Domain KPIs — ARR, net revenue retention, RPO, billings, customer counts, payment & cross-border volume. |
get_revenue_breakdown |
Segment, geography, product or customer revenue splits. |
get_earnings_call_transcript |
Speaker-tagged earnings-call transcript chunks, fiscal-period filters and text search. |
query_etfs |
Search ETFs by ticker / fund name, category, focus, domicile; profile, price history and holdings for an exact ticker. |
list_portfolios |
Your virtual portfolios with value, day change, cost basis and total return. (sign-in) |
get_portfolio_context |
Deep snapshot of one portfolio: every holding with weight, sector and return, plus Bullrun's insights. (sign-in) |
get_portfolio_analytics |
Correlation/covariance, contribution-to-risk, factor exposure, sector/currency/country concentration, stress scenarios, and candidate-fit analysis. (sign-in) |
create_portfolio_draft |
Draft a new paper portfolio from a plain-English brief. Draft-only — saved for review, never changes a live position. (Pro) |
create_position_draft |
Suggest additions to an existing portfolio. Draft-only — saved for review. (Pro) |
Authentication & privacy
The server is an OAuth 2.0 protected resource (RFC 9728). On first connect your client runs an
automatic discovery handshake and sends you through Google sign-in; after you authorize, per-user
tools resolve your Bullrun account. The MCP layer is a thin proxy with no database of its own —
read tools return market data and your own holdings, the per-user read tools accept a privacyMode
(full by default, or weights_only to return only relative figures), and the draft tools never
mutate live holdings. See the privacy policy.
License
MIT. This repository contains documentation and connector metadata only.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。