MCPサーバー

Noise data tools for AI agents — free, no auth, no config. Estimated noise levels for 50 world cities (ranked, WHO-anchored), measured noise-exposure rankings for the 100 largest US cities (federal BTS data), decibel levels of common sounds (CDC/NIOSH-sourced), NIOSH safe-exposure-time math, and info on the Decibel Shield iOS sound meter. Typed structured output on every tool. Data CC BY 4.0 — please cite decibelshield.app. Endpoint: https://decibelshield.app/api/mcp (Streamable HTTP). Docs: https://decibelshield.app/mcp/

Bring enterprise-grade stock market data to agents and LLMs

Mentionkit is a AI first social listening tool with MCP support. After creating your account, you'll get a MCP url. Follow the instructions at https://app.mentionkit.com/mcp for Claude, ChatGPT or your favourite chat tool.

NameSniper checks brand name, domain, and social handle availability across all the major social platforms, generates name ideas, and screens trademarks for conflicts. It also keeps watching taken usernames and alerts you the moment one frees up or drops, so you can claim a handle before anyone else. All from your AI client - Claude, Cursor, or any MCP host.

Remote MCP server exposing free, read-only crypto whale-tracking & market-intelligence tools to AI agents. No auth. 17 tools across 14 chains: whale movements, tracked wallets, platform stats, trending tokens, gas, funding rates, stablecoin flows, liquidations, airdrops, narratives, bridge flows, burn tracker, social sentiment, Fear & Greed, market heatmap.

Explore Savvly MCP: retirement projections, eligibility, comparisons, and FAQs for an SEC-registered fund that pairs full market upside with later-life longevity payouts. Savvly offers longevity-linked, SEC-registered investment products — built on the Savvly 80+ fund — that invests pooled contributions in a low-cost S&P 500 ETF and makes milestone cash payouts at ages 80, 85, 90, and 95, turning a longer life into a financial reward rather than a risk. Savvly MCP lets financial advisors, planning tools, and AI agents query fund data, model projections, and compare against alternative retirement products directly, in real time, in any conversation, and without any manual lookup.

MCP server for retrieval of Australian economic and financial data - supports ABS, RBA and APRA Docs: https://auseconmcp.com

Mobile proxies, Non-VoIP SMS verifications, and global eSIM data plans for AI agents and MCP clients. 25 tools for renting phone numbers, purchasing mobile proxies, buying eSIM data plans and managing it all.

MCP-native workflow engine for your AI harness. Progi teaches your agent how you like to get things done. So you can do your best work without re-explaining your process or losing context between sessions.

A hosted, read-only Model Context Protocol server that gives an AI voice agent phone intelligence in one call — who is this inbound caller, and is this number one to think twice about — before it burns agent minutes. Four read-only tools: phone_lookup (validity, line type, range carrier, country, CNAM where available, STIR/SHAKEN verstat, a labeled spam signal, a first-party do-not-contact signal, and a signed receipt), caller_risk, line_type, and dnc_check. Every billable answer carries an Ed25519-signed receipt — verifiable 'checked as of T' evidence — and no raw phone number is ever stored (hashed only). Remote/hosted: nothing to install; point your agent at the URL.

CodePic MCP lets your AI agent (Cursor, Claude Desktop) create editable hand-drawn diagrams directly in CodePic — instead of static images or Mermaid text you paste manually. It returns a link that opens in the editor, where you can move shapes, edit labels, share a read-only link, and export PNG/JSON. Remote Streamable HTTP server, no local install. Tools: list_templates, create_from_template, create_diagram, get_diagram, update_diagram. Get a free API key at https://codepic.cc/settings/api-keys

An MCP server for Blank Invoice Maker, the free no-signup invoice generator. Describe an invoice in plain language and it returns a link that opens the editor fully pre-filled; invoice data stays in your browser.

Create, manage, and clean up Flagsmith feature flags directly from your AI tool. Flagsmith is an open source feature flag and remote config platform you can self-host or run in the cloud, and the MCP server lets you control flags, environments, and segments through natural language in any MCP-compatible editor.

Perplexity for social. Ask anything about what's happening across social and get answers grounded in real ad and creative data, not guesses. Adology watches the brands, creators, and topics you care about across TikTok, Instagram, Meta Ads, YouTube, and more, then answers your questions the way you'd ask them.

Turn prototype feedback into product decisions that your whole team can trace.

IT桔子 MCP 是面向 VC、产业投资、FA、政府招商和企业战略部门的一级市场 AI 数据服务。通过 MCP 客户端连接后，用户可以用自然语言查询 IT桔子结构化数据，包括公司画像、融资事件、上市相关事件、并购事件、投资机构、机构投资案例、FA 服务案例、标签、行业、轮次、公司资质、融资排名和赛道融资统计。该服务适用于赛道研究、标的发现、融资动态追踪、机构研究和投研问答等场景。使用本服务需要 IT桔子 MCP API Key。

Real-time, AI-enriched financial news for AI agents and trading bots. Full-text and ticker search, trending and "actionable-now" feeds, SEC Form 4 insider transactions, and two-ticker read-across — every story carries per-ticker analysis and a 1–10 relevance score. Hosted at mcp.alphai.io over Streamable HTTP; connect with OAuth (no API key to paste), free tier 100 calls/hour.

A framework for collaborative agent memory. Kage is shared, code-grounded memory for developers and their coding agents: capture a learning once — a bug cause, a decision, a gotcha — and the whole team plus every agent recalls it next time it's relevant. Memory is grounded in your actual code and stored as git-tracked JSON reviewed in PRs, not a personal vector blob that drifts: citations are validated on write, and stale memory (whose code was deleted or refactored) is withheld from recall and flagged for you. Works with Claude Code, Codex, Cursor, Windsurf, and any MCP client. No vector DB, API key, or service to run. Try it in 30s: npx -y @kage-core/kage-graph-mcp demo