v2.2.0 · MIT
Track competitors across X, Instagram, TikTok, and YouTube, see what they post, what performs, and get content ideas backed by real engagement data. Cross-host plugin for Claude Code & Codex.
v1.0.0 · no license
Find verified businesses & service providers by trade and area. Returns structured provider data.
v1.0.0 · no license
SEC Form 4 insider trades, daily trading plans, 8-K catalysts and market data for AI assistants.
v0.2.0-alpha.4 · MIT
Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.
v0.7.0 · MIT
Claude Code plugin for EODHD financial data — 150k+ tickers, 70+ exchanges, OAuth MCP server with 80 tools, 7 workflow skills, financial-analyst agent, 5 slash commands. MIT.
v3.9.1 · Apache-2.0
Verified generative visualization for React and agents, with deterministic chart validation, repair, rendering evidence, and MCP.
v0.3.0 · MIT
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
v2.3.0 · MIT
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
v1.14.0 · MIT
Evidence-based learning engine for OpenCode — learn anything, verify by free recall, schedule with FSRS, adapt from your own data.
v0.1.2 · BSD-3-Clause
在 DSH 对话中生成交互式可视化|Render model-generated interactive cards inside DSH conversations
v0.2.10 · MIT
Provider balances, subscription quotas, and token-usage analytics for the DeepSeek Harness Web GUI (dsh web).
v1.0.0 · MIT License
Provides read-only access to normalized Amazon marketplace data, including product details, search, offers, reviews, sellers, categories, deals, best sellers, identifiers, stock, and sales estimates across 13 marketplaces.
v0.1.0 · MIT
A divide-and-conquer wiki of system-design skills for Claude Code — reason about scalable systems, don't memorize architectures.
— · Apache-2.0
An autonomous agent that conducts deep research on any data using any LLM providers
— · MIT
Data API builder provides modern REST, GraphQL endpoints and MCP tools to your Azure Databases and on-prem stores.
v0.1.0 · Apache-2.0
Provides MCP tools for interacting with the Technocore agent protocol, including signed messaging, nonce management, DID verification, end-to-end encrypted communication, and untrusted data fencing.
— · MIT
Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..
— · MIT
Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..
v1.0.0 · no license
Provides read-only access to live Bay Area transit data, including routes, stops, real-time departures, vehicle positions, and service alerts, for use by large language models.
v1.0.0 · no license
Provides read-only access to Canvas LMS data, enabling an LLM to query courses, assignments, grades, submissions, announcements, discussions, modules, pages, and files via the Canvas REST API.
— · MIT License
Provides read-only access to a China-region Garmin Connect account, enabling retrieval of daily summaries, sleep, heart rate, HRV, training readiness, body battery, and activity data.
— · MIT
Provides read-only real-time market data, including snapshots, quotes, candlesticks, order book, tickers, and security search, from the Futu OpenAPI to MCP clients like Codex.
— · MIT License
Provides fail-closed, read-only PostgreSQL and MongoDB access for AI agents via MCP, enabling structured data inspection and bounded queries without mutation capabilities.
— · no license
Provides four MCP tools for neural retrieval: personalized user recommendations, item-to-item similarity, cold-start text search, and explainable recommendation scores, enabling LLM agents to query a trained two-tower recommender over Amazon Reviews data.