"How to create and edit edge functions on Supabase" matching MCP servers:

PT-Edge gives AI assistants live intelligence on the AI ecosystem — 47 tools to search 11K+ GitHub repos, 18K+ HuggingFace models, 42K+ datasets, and 2,500+ public APIs, plus trend analysis, project comparison, and community discourse tracking across Hacker News and V2EX.

Provides read-only tools to retrieve source-linked catalyst evidence dossiers for public-company tickers, including deterministic catalyst scores and paged source records.

Grades prediction market trade logs to determine if a strategy has a statistically significant, fee-adjusted edge using out-of-sample holdout, returning a signed verdict.

Analyzes user-authorized CSV, JSON, or XLSX comment exports locally to generate risk signals, prioritized comments, evidence-backed actions, and reports while keeping data private.

A Cloudflare Workers MCP server that puts a SOC analyst's enrichment, investigation, and detection-context workflow behind a single endpoint. It aggregates over 20 threat-intel sources into 18 MCP tools for IP, domain, URL, hash, and CVE lookups.

Provides a consolidated 0DTE options cockpit for SPX/SPXW, including chain, Greeks, dealer exposure, volatility term structure, and economic events, using free delayed market data.

Provides unofficial access to Philippine Stock Exchange data including quotes, price history, disclosures, financial reports, and market data via MCP.

Made-to-order data for AI agents via x402 micropayments on Base. Describe a need in plain language, get a custom quote, pay per call. No signup, no API keys. HTTP + MCP transports. 5 tools.

Enables AI agents to access audited SEC intelligence, including scored catalyst picks and track record data, via the Model Context Protocol.

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.

Converts PDF files to text for use with MCP-compatible applications like Cursor IDE.

Enables AI clients to search a local literature library via vector semantic retrieval, with automatic conversion of Zotero items and arbitrary files into Markdown (including OCR for scanned PDFs). It supports natural language queries and provides answers with page-level citations.

Enables any agent to query the same interview corpus as the UI over stdio, exposing tools to list transcripts, search quoted lines, retrieve verified themes with citations and dropped reasons, and fetch source lines.

Query iOS App Store revenue and download estimates for any app directly from your agent. Two tools: estimate_app returns monthly revenue and downloads with a confidence label (verified / calibrated / modeled), and search_apps resolves an app name to its App Store id.

Enables coding agents to check what already exists, identify duplicate projects and missing features, and prepare merge plans or targeted outreach for overlapping work, with human approval before any message is sent.

Answers operational questions about route on-time performance, such as lateness rates and trip evidence, using structured tools for route summary, trip lateness, and data quality.

Give AI agents cited funding, money-market, FX and capital-market evidence through 16 public MCP tools. Keep source dates, freshness checks and coverage gaps attached; China macro coverage is metadata-only. No API key is required for the public surface. Research context only; no trade execution.

CNN's Fear & Greed index for the US stock market: current score and rating, the seven component indicators, and about a year of daily history. Go standard library only, no API key required.

Classifies company sites as B2B or B2C and as SaaS, online store, agency, manufacturer, wholesaler, distributor, or marketplace, while matching your own buyer phrases and returning the quoted text and page as evidence. Runs deterministically on Apify, giving one row per domain with grace-free status rows for unreachable, blocked, or empty sites.

An MCP server providing progressive discovery tools for SDMX statistical data, enabling AI agents to explore and access SDMX-compliant repositories through interactive tools, resources, and prompts.

Deterministic US equity-compensation tax optimizer. Six tools cover ISO/AMT exercise scheduling, NSO sell-vs-hold, RSU vest-and-sell, single-stock concentration, protective put / zero-cost collar pricing, and Section 1202 QSBS qualification. Federal plus 50-state plus DC tax math.

One-call Australian health and welfare data plumbing via AIHW — cited responses for practical analysis, not a data broker.

Given a company domain or name, it checks ten app marketplaces — HubSpot, Salesforce AppExchange, Slack, Zapier, Shopify, Atlassian, Chrome Web Store, Microsoft, Google Workspace, and WordPress — to report where the company is listed, with each listing's URL, installs, rating, review count, and match confidence. Useful for competitive research and partner-ecosystem audits across many domains in a single run.

Enables users to pull portfolio company lists from Y Combinator, a16z, Sequoia, Accel, and other investors or any portfolio page URL, returning one row per company with name, domain, website, description, and stage or batch. Runs on Apify and produces Clay-ready output, with YC results filterable by batch, industry, region, status, and search terms.

An MCP-native pipeline for collecting structured intelligence on higher education institutions using the WHED schema, enabling scraping, extraction, validation, and saving of profiles.

MCP server exposing 40 best-practice product management skills plus workflows and lifecycle tools, instantly accessible to any AI via Model Context Protocol.

This project implements a Model Context Protocol (MCP) server providing Formula One racing data using the Python FastF1 library. Inspired by an existing TypeScript server, it offers similar F1 data functionalities natively in Python via FastF1.

Enables researchers to turn property-history questions into reviewable evidence dossiers by gathering sources, tracing people and places, linking conclusions to supporting or opposing passages, and exporting portable backups.

Enables agent tools to validate queries, assess token costs, and extract structured datasets from unstructured text using multiple LLM providers.

Enables Claude Code to convert PDF files to high-quality PNG images, download academic papers, and batch process PDFs with automatic folder organization.