tatumio/blockchain-mcp C MCP Server Maintained
MCP server for Blockchain Data. It provides access to Tatum's blockchain API across 130+ networks with tools including RPC Gateway and Blockchain Data insights.
Browse all Model Context Protocol servers with quality scores, stars, languages and maintenance activity.
MCP server for Blockchain Data. It provides access to Tatum's blockchain API across 130+ networks with tools including RPC Gateway and Blockchain Data insights.
Twitter/X MCP server with 34 tools — post tweets, search, read timelines, manage engagement, upload media. No API keys needed, uses browser cookies. Pay per call from $0.001 via x402 micropayments.
MCP Server that connects AI Agents to [Carbon Voice](https://getcarbon.app). Create, manage, and interact with voice messages, conversations, direct messages, folders, voice memos, AI actions and more in [Carbon Voice](https://getcarbon.app).
Connects Claude Desktop to your Gmail so you can start managing your inbox using natural language. Bulk delete promos & newsletters, organize labels and get useful insights.
Control Ableton Live from Claude, Cursor or Codex through a local Remote Script bridge: inspect sets, create tracks, scenes and clips, load devices, apply music recipes, and verify changes against Live state.
Expose a company's complete design system (colors, typography, logos, components, guidelines, CSS tokens) to AI tools via MCP. Auto-parses CSS / Markdown / PDF / SVG / fonts; supports `marketing` vs `product` contexts with shared overrides; ships 12 tools, 16+ resources under `brandkit://`, and 4 prompts; stdio + SSE + Streamable HTTP transports. Install via NPM: `npx -y brandkit-mcp serve`.
In-browser debug bridge that injects into your running web app, so an agent can read the DOM, console logs and network requests, and click/fill/inspect the page. Runs inside the page (not an external CDP driver), so it works in any browser and inside Cypress/Playwright runs.
Brazilian public data for AI agents — companies (CNPJ), addresses (CEP), banks (BACEN), national holidays — via [BrasilAPI](https://brasilapi.com.br). No auth, no API key. Install: `npx -y brasil-data-mcp`.
Local-first memory & context-handoff across AI tools — capture context in one tool, resume it in another, with graceful decay, a persona layer, and a portable memory passport.
Local-first external brain CLI for coding agents. SQLite-backed context, graph-aware recall via FTS5 and RRF, and governed memory with explicit promote and review gates. Ships Codex and Claude Code host shims and a native MCP server.
Convert any URL to LLM-ready Markdown via real Chrome browsers. 3 tools: scrape, crawl, search. Free via MCP, pay-per-use via x402. Remote MCP endpoint: `https://anybrowse.dev/mcp`
Deterministic security proxy (iptables for MCP) that intercepts tool calls, enforces YAML policies, scans for secret leakage, and logs everything. No AI, no cloud.
Real-time AI industry intelligence MCP server. 6 free tools (AI news, service status, model pricing, today summary, agent activity, MCP registry snapshot) and 13 paid premium tools (routing recommendations, news search, history series, cost projection, provider deep-dive, model comparison, agents directory, what's new brief, MCP registry series, webhook watches with daily/weekly digest tier). Pay-
Multi-agent deliberation with divergent context enhancement. Roles are dynamically generated to surround the question-space and maximize divergent dialog across ChatGPT, Claude, Gemini, and Perplexity.
Remote Streamable HTTP and local stdio MCP server for defining, validating, deploying, and operating machine-readable agreements with EIP-712 permit preparation, signed participant inputs, state reads, and input history.
Read-only static scanner for MCP / agent-gateway production-readiness. The `scan_gateway` tool scores a repo across 7 security dimensions (RBAC, fail-closed, supply chain, observability, cost, secrets, prod-readiness). Never executes code or prints secret values.
Shorten links, read click analytics, generate branded QR codes, and manage links on opn.onl — the open-source, self-hostable URL shortener. Works with the hosted service or your own instance.
Workflow tools for US federal contractors — go/no-go bid scoring, incumbent intelligence (USAspending + FPDS), teaming-partner search, recompete prediction, Navy NECO lookup, and SAM.gov solicitation retrieval. Returns synthesized decisions rather than raw data.
Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised. The agent proposes, you approve on your Ledger. Read balances + DeFi positions (Aave V3, Compound V3, Morpho Blue, Uniswap V3 LP, Lido, EigenLayer, MarginFi, Kamino) and prepare transactions across Ethereum / Arbitrum / Polygon / Base / TRON / Solana / Bitcoin; private keys never leave the hardware wa
Drive the [Dolphin](https://dolphin-emu.org) GameCube/Wii emulator from any MCP client: read/write PowerPC memory (MEM1/MEM2), GameCube + Wii Remote input (buttons, IR pointer, accelerometer, MotionPlus), reset, save/load state, and frame advance. Python bridge inside [Felk's scripting fork](https://github.com/Felk/dolphin) + Node MCP server.
LEGO sets, parts, minifigs, colours, and inventories from Rebrickable. 10 tools for searching sets, finding parts by colour, browsing themes, comparing sets, and discovering MOC alternate builds. 26k sets, 62k parts, 17k minifigs embedded.
A brewing knowledge MCP server with beer styles (BJCP 2021), 113 hop varieties, malts, yeasts, water profiles, off-flavour diagnosis, recipe suggestions, and food pairings.
Local-first persistent memory for AI coding agents. Captures facts, decisions, patterns, and architecture notes in SQLite (with optional cloud embeddings) to reduce repeated context across sessions.
Search 1M+ enriched job listings from 20,000+ companies. Filter by skills, salary, location, seniority, remote type, and more. Free — 500 calls/day, no signup required. Also available as a remote MCP server at `https://mcp.jobdatalake.com`.
Translation quality evaluation using xCOMET models. Provides quality scoring (0-1), error detection with severity levels (minor/major/critical), and optimized batch processing with 25x speedup.
Music metadata search over 90M+ tracks, artists, labels, and releases: genre, release dates, ISRC/ISWC codes, and cross-platform IDs (Spotify, Apple Music, Tidal, Beatport, Discogs, MusicBrainz, YouTube). `npx -y sonovault-mcp`
Conversational Spotify control with intent-shaped tools: play by description, queue, devices, playlists, and library, plus a 2-minute PKCE setup wizard. Built for the post-Feb-2026 Spotify Web API. `npx -y @xavifabregat/spotify-mcp`
Catch bad animations before they ship. 13 deterministic checks on the live page (duration, easing, stagger, exits, reduced-motion, touch-gated hover) with no API key or LLM, plus optional vision-LLM UX review across viewports. Install via NPM: `npx -y motionlint mcp`
Agent-native UI/UX design validation: model user journeys as state machines and prove what AI-generated screens are missing (unreachable states, missing empty/loading/error states, WCAG contrast, touch targets, localization overflow) before code exists — then verify the code implements the contract. Deterministic CI gates (`uxloom check`, `uxloom audit`), one-command setup (`npx uxloom init`).
Fetch any web page's HTML (or AI-parsed JSON, or Google results) through the ScrapeUnblocker anti-bot API (Cloudflare, DataDome, PerimeterX, Akamai, Shape), using your own API key. Three tools: `fetch_html`, `fetch_parsed`, `google_search`. Install: `npx -y scrapeunblocker-mcp`.
Native Gmail MCP server with full mailbox control — search, read, label, archive, trash, download attachments, and the feature no other Gmail server ships: snooze threads until a date. Every call hits the live Gmail API (no synced index that silently misses mail). Install with `npx -y mailwarden`.
Email (IMAP/SMTP), mail filters (Sieve), calendar (CalDAV), contacts (CardDAV), and free/busy scheduling for Open-Xchange and standards-based mail platforms. Published on the official MCP Registry.
Inspect and operate Redis-backed job queues (Asynq and BullMQ): per-state counts, job detail with decoded payload and last error, and faithful retry/delete running each library's own scripts. Read-only mode for production.
Design-fidelity checks for AI agents: compare a Figma frame (or any design screenshot) against the rendered implementation and get structured discrepancies with CSS properties and severity. Resolves a natural-language component description to a URL + selector in your codebase, screenshots it with Playwright, and compares via vision AI using your existing Claude Code or Codex subscription — no API
Agentic payments on Solana: let an agent discover x402-priced endpoints, pay HTTP 402 paywalls in USDC, manage pre-paid balances and subscriptions, and buy datasets or settle store checkouts — 15 tools behind fail-closed spending caps ($1 per payment, $10 per day by default). Non-custodial: payments lock in a program-owned escrow and release 99% to the creator. Listed on the official MCP registry
Cross-chain OTC trading via sealed-bid RFQ + HTLC atomic settlement. Six tools for AI agents to swap ETH, BTC, and SUI without bridges, custodians, or information leakage. Hosted at `hashlock.markets/mcp` or local stdio via `@hashlock-tech/mcp`.
Vertical quote-to-cash agent for service businesses (machine shops, contractors, HVAC). Drive jobs, quotes, customer memory, pricing signal, follow-ups, and confirmed sends from Claude Code, Claude.ai, ChatGPT, or any MCP-aware agent. 25 tools, 6 resources, 8 prompts. `npx -y @setell/mcp`.
Read-only Hyperliquid / HyperEVM: every way to earn on HYPE in one table — liquid staking, lending with utilisation and max LTV, LP pools, and the HLP vault — with yield a pool earns separated from yield paid in emitted tokens. Also protocol TVL, fees actually paid, perp and spot markets, funding history, and order-book depth with a straight answer when a size will not fill. Where a source publish
Verify a US contractor's license, surety bond, and insurance from official state data (WA L&I live, CA CSLB beta). Agent-payable pay-per-success, MCP-native.
Location intelligence gateway across 10 providers (OpenStreetMap, OSRM, Google, Yelp, Foursquare, US Census, Kakao, Naver, Baidu, your own CSV): place search, geocoding, directions + distance matrices, travel-time isochrones, and commercial-area analysis (category density, ratings, demographics). Multi-provider merge + dedup with per-field provenance, cost budgets, and a policy engine that enforce
App Store Optimization for AI agents — keyword research with difficulty and popularity scores, daily rank tracking, review mining, competitor gap analysis, and revenue estimation across the iOS App Store and Google Play. 32 tools. `npx @sonarapp/mcp`
Observability for AI agents: 87 tools to query LLM cost, errors, and latency across OpenAI/Anthropic/Gemini/Mistral, and operate alerts, budget gates, evals, and safety checks from Claude/Cursor. Install: `npx -y @argosvix/mcp-server`.
Server ops via AI: log troubleshooting, CPU/memory/disk monitoring, code edit, Nginx & certificate management. Local or SSH-remote with two-step confirmation, command whitelist, and secret redaction. Install: `npx -y server-ops-mcp`.
Live VR / AR / XR news, full-text VR.org originals, events calendar, headset deals and comparisons
Japanese-web-native web fetching optimized for low target-site impact and token efficiency. Outline-first progressive disclosure, Shift_JIS/EUC-JP mojibake handling, PDF/CSV extraction, and polite crawling (robots.txt, rate limits, honest User-Agent). Install via `npx -y amenbo`.
Zero-setup astrology MCP server for natal charts, current transits, synastry, Moon phases and birthplace lookup, with privacy modes for compact agent payloads.
Visa eligibility matching across 102 immigration pathways in 15 countries. Scores a profile (citizenship, education, work history, income, goal) against official government criteria — points thresholds, salary floors, language requirements — and returns ranked matches with processing times, fees, PR timelines and links to the official source. Also compares pathways side-by-side and reports live in
Private, local AI-text analysis (a detection read, the exact AI-tell spans, a reuse check, and a grammar pass) for the AI you already use.