Experimental MCP Service for Azure AI Search

PriceOf is an MCP server that gives your AI agent access to current, structured pricing data for SaaS products like Notion, Slack, GitHub, Figma, Linear, Vercel, and 45+ more. Instead of scraping pricing pages (unreliable) or hallucinating (often wrong), your agent makes a single call to get clean, verified pricing. Features: - Full pricing breakdown for any tracked product (plans, features, prices) - Side-by-side comparison with team-size cost calculation - Search by name or category - Confidence + freshness scores on every response - Automatic data refresh every 3-14 days Access tiers: 20 queries/day anonymous (no signup), 100/month free with API key, paid tiers from $29/mo.

CPZAI MCP server. Build, backtest, and deploy quantitative trading strategies from your AI agent. 29 tools: list_strategies, get_strategy, create_strategy, update_strategy, get_backtest_results, list_orders, place_order, list_positions, sync_portfolio, plus dev-time tools. Multi-broker (Alpaca, Interactive Brokers, FIX gateway). Paper-only by default; live trading requires explicit per-strategy promotion. Free to try at ai.cpz-lab.com.

A Model Context Protocol server that exposes the Aspro.Cloud REST API to LLM clients. The server ships with the bundled OpenAPI spec, so the model can discover modules, entities and methods on its own and call them safely. The server reads its .env from the project root regardless of the working directory the client launches it in.

Send SMS/MMS, manage contacts and groups, run workflows, fetch reports, manage webhooks, query account state

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

Playwright MCP server

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Wayforth is the neutral service layer for AI agents — where they discover services, route requests, and pay through one path.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Channel management and messaging capabilities

Browse open bounties, request short-lived authenticated repo access, submit PRs, and check verification status. Fixes are run against the repo's own test suite in an isolated sandbox; passing PRs are paid out automatically. Useful as a tool layer for any coding agent that wants to compete on real-money tasks.

Repository management, file operations, and GitHub API integration

NyxID lets your AI agents (Claude Code, Cursor, n8n) reach any API you have, public or private, and handles all the credentials so your agent never sees a raw key.

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.

Location services, directions, and place details

Browser automation and web scraping

US land due-diligence MCP server. Returns structured reports covering solar potential, groundwater depth, flood zones, building codes, and county regulations for any US property address. Mode-aware across off-grid, rural residential, recreational, and investment use cases. 60-120 second turnaround with sourced citations from NREL PVWatts, USGS Water Services, and FEMA NFHL.

AI-native marketplace for pre-cleared licensed assets. Search, license, and stream media rights programmatically. Built for post-production, editorial, and brand workflows. Three tools: search_assets, get_asset_details, generate_usage_agreement. Install: npx pixelvault-mcp

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

MCP server for parallel browser automation across multiple providers. Run multiple concurrent browser sessions in memory with a shared, provider-agnostic tool surface across Playwright (local Chromium), Browserbase, Anchor Browser, and Cloudflare Browser Run. Each session gets a numeric ID, every browser_* tool accepts a sessionId. Tools include browser_navigate, browser_click, browser_fill, browser_screenshot, browser_snapshot, browser_evaluate, keyboard/mouse primitives, file upload, and waits. Configure providers at the MCP server level (not per call) via BROWSER_MCP_CONFIG env or a config file.

The Interplanetary File System (IPFS) MCP toolkit gives AI Agents and automated workflows the ability to utilize IPFS as a backend storage medium. Upload, retrieve, pin, and manage encrypted files on IPFS via a simple API accessible as MCP tools.

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.