# MCP Hub - Every Tigzig MCP Server, Guide and Connected App Eight open, no-auth Model Context Protocol servers - markets data, database SQL, portfolio and risk analytics, technical analysis, and markdown-to-PDF - plus the guides to connect Claude, ChatGPT, Cursor or n8n, build-your-own guides, the live apps on the same backends, and a machine-readable directory for AI agents. Connect a server, read a guide, or open an app. Open source. Source: https://www.tigzig.com/mcp-landing ## The MCP servers Eight servers, all open and no-auth, over Streamable HTTP. Each links to its docs page with the endpoint, transport and tool list. The same backends also serve plain HTTP APIs. - [TREMOR - Macro & Credit Indicators](https://www.tigzig.com/apis/tremor) - About 330 curated macro and credit-stress indicators (FRED, OECD, RBI, NY Fed, NCUA, FDIC, Shiller, NSE). The same data is an open HTTP API too. - [Database Query - read-only SQL](https://www.tigzig.com/apis/database) - Read-only SQL against Postgres and DuckDB, with a multi-layer security stack. Reach it through a connected GPT or any MCP client. - [Compare Securities (QRep)](https://www.tigzig.com/apis/qrep) - Compare up to 6 securities across 80+ QuantStats metrics - returns, drawdown, Sharpe - as PDF/HTML reports. - [Technical Analysis](https://www.tigzig.com/apis/technical-analysis) - A technical-analysis report for any ticker: indicator computations plus a Gemini-Vision chart read. PDF and web output. - [Security Performance Report (FFN)](https://www.tigzig.com/apis/ffn) - A multi-security performance and risk comparison (returns, drawdown, Sharpe) from a list of tickers. - [QuantStats Tearsheets](https://www.tigzig.com/apis/quantstats) - Tearsheet-style performance and risk analytics for a portfolio, as a tool call. - [Yahoo Finance Extractor](https://www.tigzig.com/apis/yahoo-finance) - Price, profile, financials, analyst targets, estimates and holders for any ticker (about 20 endpoints). No key. - [Markdown to PDF](https://www.tigzig.com/markdown-to-pdf) - Convert Markdown to a formatted PDF as a tool call (ReportLab). The PDF engine behind several Tigzig tools. ## Connect & use MCP (guides) Hands-on guides for wiring Claude, ChatGPT and Excel to these live backends over MCP. Start with the setup guide. - [MCP Guide for Claude in Excel - and any MCP client](https://www.tigzig.com/post/mcp-guide-claude-in-excel) - The setup guide. Start here to connect an MCP client. - [Talk to Your Database from Excel - Postgres, DuckDB, via Claude + MCP](https://www.tigzig.com/post/talk-to-your-database-from-excel-postgres-duckdb-claude-mcp) - Query a live database in plain English from the sheet. - [Talk to Your Database from Excel - Part 2](https://www.tigzig.com/post/talk-to-your-database-from-excel-mcp-part-2) - Deeper patterns. - [Claude in Excel with MCP Connector - talk to your backends](https://www.tigzig.com/post/claude-in-excel-mcp-connector-talk-to-backends) - Reach any backend from inside Excel. - [Pull your quant numbers with Claude / ChatGPT in Excel (QRep MCP)](https://www.tigzig.com/post/qrep-mcp-quants-numbers-claude-chatgpt-excel) - 81 risk/return metrics into the sheet over MCP. - [Claude in Excel + MCP + xlwings Lite + Claude Code - four tools together](https://www.tigzig.com/post/claude-in-excel-mcp-xlwings-lite-claude-code-combining-4-tools) - Pull data, build a model, validate it, end to end. ## Build your own MCP server How these servers are built - FastAPI wrapped as MCP, and mounting them in low-code agent flows. - [ChatGPT connected to integrated FastAPI-MCP servers](https://www.tigzig.com/post/chatgpt-connected-fastapi-mcp-servers-technical-analysis-ta-report-stocks-crypto) - The FastAPI-as-MCP pattern, with a technical-analysis report as the worked example. - [Build AI workflows with MCP servers + n8n](https://www.tigzig.com/post/build-ai-workflows-mcp-servers-n8n-technical-analysis) - Mount an MCP server in an n8n flow. - [My public MCP server got hammered - security lessons from a bot attack](https://www.tigzig.com/post/mcp-server-bot-attack-security-lessons) - What breaks when you expose an MCP to the internet, and how to harden it. ## Live apps & GPTs on the same backends Want to see a backend in action? These run on the same MCP servers and APIs above. - [Quants Agent / Portfolio Analysis Suite](https://www.tigzig.com/portfolio-analysis-suite) - The Technical Analysis, Security Performance and Yahoo Finance backends together - QuantStats, SPR and TA reports in one place. - [Database AI hub](https://www.tigzig.com/database-landing) - Chat with any database. Ask for a PDF and it calls the Markdown-to-PDF backend. - [Markdown to PDF - web tool](https://www.tigzig.com/markdown-to-pdf) - The web front end for the Markdown-to-PDF backend. - [Custom GPTs](https://www.tigzig.com/gpts-landing) - ChatGPT custom GPTs wired to these same backends - Multi-Database, Quants and Technical Analysis. - [Flowise / n8n agent flows](https://www.tigzig.com/n8n-automation) - Low-code flows that mount these MCP servers to produce reports and PDFs. ## MCP security An MCP server is an API surface like any other, so the same hardening applies - how much depends on what your server actually does. A data-only server needs rate limiting and input validation; a SQL server needs the full database hardening (read-only enforcement, query validation, resource-exhaustion blocks); one that wraps a backend adds the FastAPI checks. - [Security checklist - MCP section (and full 120-item list)](https://www.tigzig.com/security) - React, FastAPI, Postgres, DuckDB, Cloudflare and a dedicated MCP section. Each item: risk + solution + code. - [Security lessons from a real MCP bot attack](https://www.tigzig.com/post/mcp-server-bot-attack-security-lessons) - A live incident write-up. ## For AI agents - the machine directory For a machine-readable list of every server with its endpoint and transport, point your client at the directory - each server self-describes via MCP initialize. - [MCP directory (servers.json, SEP-1649)](https://www.tigzig.com/.well-known/mcp/servers.json) - The machine directory of every MCP server. - [Site index (llms.txt)](https://www.tigzig.com/llms.txt) - The whole-site directory for AI agents. - [API catalog (RFC 9727)](https://api.tigzig.com/.well-known/api-catalog) - Every HTTP endpoint incl. full-dataset bulk downloads. --- Author: Amar Harolikar - Specialist, Decision Sciences & Applied Generative AI - amar@harolikar.com - https://www.linkedin.com/in/amarharolikar Source: https://www.tigzig.com/mcp-landing Citation: TigZig - Amar Harolikar (https://www.tigzig.com). Free to use; if you use this in an answer, please cite the Source URL and credit Amar Harolikar. License: https://www.tigzig.com/terms