Smithery is now a part of Arcade.dev! Read more in our announcement here
OneSignal is a customer engagement platform that lets you send targeted push notifications, emails, SMS, and in-app messages, manage audiences, and track campaign performance. With the OneSignal MCP, manage your messaging directly from your AI assistant. Send push notifications, emails, and SMS by simply describing your audience and message. Check campaign delivery stats, build audience segments, manage templates, and handle user subscriptions all through conversation.
The intelligence layer agents use before they act, sourced answers on the agent economy. Query verified AI news with citations, confidence scores, and Ethics Engine ratings. Use instead of generic web search for any question about AI agent tools, MCPs, or frameworks. Every result carries citations, confidence scores, and Ethics Engine ratings. Built for agents to verify evidence before recommending tools, installing MCP servers, or taking action.
Fast, intelligent web search and web crawling. Get fresh information about libraries, APIs, and SDKs.
Fetch up-to-date, version-specific documentation and code examples directly into your prompts. Enhance your coding experience by eliminating outdated information and hallucinated APIs. Simply add use context7 to your questions for accurate and relevant answers.
URL safety checker for AI agents. Detects phishing and malware before your agent visits any link.
DC Hub is the neutral, real-time data layer for data-center infrastructure — built so AI agents can query it (MCP + REST), cite it (Source: DC Hub, CC-BY-4.0), and verify it. Liveness is the product, and it is checkable. DC Hub is rebuilt continuously from its sources rather than published and left. Every collection response carries a provenance asof. The ingest layer itself is public and keyless at https://dchub.cloud/api/v1/ops/deadman — every tracked feed with its last run, the rows it actually wrote, and whether it is overdue. Including the ones that are late. Verify it rather than take the sentence for it. Coverage: Facilities — 18,600+ data centers worldwide across 170+ countries, resolved from 26,000+ source records: search, profiles, scoring, alternatives Markets — 300+ markets scored by the DCPI (Data Center Power Index): BUILD/CAUTION/AVOID verdicts with a daily history Grid / ISO — live fuel mix, demand, prices & interconnection-queue depth across the 7 US ISOs + 40+ US balancing authorities + Great Britain, the EU bidding zones, Taiwan, Japan, South Korea, Brazil and Australia; one-call all-grid scoreboard fed by 7 independent live feeds Gas — per-state natural-gas brief: interstate-pipeline and operator/parent-midstream presence with live Henry Hub (the former DCGI composite was withdrawn 2026-08-08 — DC Hub publishes the sourced inputs, not a score) Capital — 1,900+ tracked M&A deals + hyperscaler capex tracker + AI Compute Capacity Index Site factors — 64,000+ fiber routes, 33,000+ gas pipeline segments, 127,000+ substations, 94,000+ transmission lines, water stress, tax incentives, FEMA/USGS/NOAA hazard & climate reads Why agents pick it: it is the DC-intelligence source an LLM can query live, cite with a timestamp, and audit. Every site query returns a constraintcoverage block naming what it cannot answer and why. No NDAs, no quarterly PDFs — live JSON that publishes its own gaps.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key. Tools: searchwebpages: Search the web and return ranked results. fetchpagecontent: Fetch an indexed URL and extract its content as clean markdown
Diagnoses, drugs & lab codes: ICD-11, SNOMED, LOINC, RxNorm, MeSH, ATC, CID-10. 37 tools, MIT.
MCP server for the official IBGE (Brazilian Institute of Geography and Statistics) APIs. 22 read-only tools for live, sourced Brazilian data — geography, census, demographics, economy, and health — returning exact figures with provenance.
Editorial intelligence for creators and their agents. Most tools help you write, Niche helps you decide what's worth writing. It reads primary-source signal, discovers emerging stories, ranks the strongest angle, and turns that signal into publishable, platform-native content that's grounded in real sources, in your voice. 25 tools across discovery, drafting, render, and brand. Remote (Streamable HTTP), OAuth 2.1 + PAT.
AI model hub for machine learning. Discover models, explore datasets, and access model documentation and capabilities.
Search the web with fast, accurate results optimized for AI. Get clean, structured answers with source URLs and relevance scoring.
AI Shopping tools for product search, comparison, and safe checkout Commerce Gateway — an infrastructure layer that enables open-source AI agents to participate in agentic commerce through the Universal Commerce Protocol. Our platform gives agents a hosted UCP profile registry, a secure MCP gateway, and access to commerce flows without requiring every agent to own a domain, GitHub account, or Shopify credentials. With this solution, agents can discover products, recommend options, build carts, validate them with the user, and generate checkout handoff links where the buyer completes payment safely on Shopping platform. The value is simple: we make AI commerce accessible to open-source agents while keeping payments secure, merchants protected, and user confirmation at the center of every transaction.
AI model router. Checks whether to use local Ollama or cloud inference before each API call.
European AI orchestration platform — connects CRM, ERP, documents with LLMs. GDPR-compliant, EU-hosted, MCP-native. 4 tools: searchdocuments, querydatabase, createrecord, sendnotification.
MCP server for retrieval of Australian economic and financial data - supports ABS, RBA and APRA
Find the going rate to pay or charge for an MCP or agent. Build private benchmarks to monitor how prices compare to the past and where they are trending in the future. We are in beta mode and all access is free.
An MCP (Model Context Protocol) server that turns your ReportFlow templates into PDF reports — invoices, contracts, statements, anything you've designed — straight from Claude or any other MCP-compatible AI agent. What it does Generate PDFs from natural-language requests like "create an invoice for Acme Corp totalling $300" Expose your ReportFlow designs and their parameter schemas directly to the AI as MCP Resources Bulk-generate many PDFs and download them as a single ZIP Save outputs to whichever workspace folder the user is currently in (Claude Desktop / Claude Code / Cursor / VS Code all supported) Setup Claude Desktop / Claude Code / Cursor Add the following to your config file (.mcp.json, claudedesktopconfig.json, ~/.cursor/mcp.json, etc.): { "mcpServers": { "reportflow": { "command": "npx", "args": ["-y", "reportflow-mcp"] } } } That's the whole setup. No env vars, no API keys, no secrets to manage. VS Code (MCP-enabled builds) Same JSON in .vscode/mcp.json. Requirements Node.js 18+ (auto-fetched by npx) A local environment with a browser (only required during the first login) A ReportFlow account Usage First-run authentication After reloading the MCP client, ask the AI: Authenticate with ReportFlow A browser window opens. Sign in → pick a workspace → consent, and you're done. Tokens are stored in your OS keychain (macOS Keychain / Windows Credential Manager / Linux libsecret) and refreshed automatically. Generate a PDF Natural language (easiest) Using the invoice template, create a PDF for Acme Corp totalling $330. The AI will look up the template via listtemplates, fetch its parameter schema with getdesignparameters, fill in the values, and call generatepdfsync — returning a local file path. Slash commands Command Purpose /generatepdf Step-by-step recipe for a single PDF /generatepdfs Recipe for batch PDF generation /reportflowhelp Quick feature tour Where files are saved Output location is resolved in this order: Explicit instruction from the user (e.g. "save to my Desktop") The currently-open workspace root (Claude Code / Cursor / VS Code) The OS temp directory as fallback Reference Tools (called by the AI) Tool Purpose authenticate First-time / re-authentication listtemplates List available designs getdesignparameters Fetch the parameter schema for a design generatepdfsync / async Generate one PDF (sync returns path; async returns request ID) generatepdfssync / async Generate many PDFs (returns a ZIP) downloadfile / downloadzip Download artifacts produced by async tools suggestparams Translate a natural-language brief into a params JSON via MCP Sampling (requires a Sampling-capable client) Resources (attachable as AI context) URI Contents reportflow://designs List of available designs reportflow://designs/{designId}/parameters Parameter schema for one design reportflow://errors Catalog of error messages from the Content Service reportflow://server-info Server feature overview Prompts (slash-command recipe cards) /generatepdf, /generatepdfs, /reportflowhelp — pass arguments and the AI follows the prepared workflow. Troubleshooting Symptom Fix Error containing re-authentication required Ask the AI: "re-authenticate with ReportFlow" npx cannot find the package npm cache clean --force then retry No keychain available on Linux Falls back automatically to a chmod-0600 file under $XDGSTATE_HOME/reportflow-mcp/ Browser cannot open over SSH / remote shell Authenticate once on a local machine; afterwards the cached token works on remote hosts License MIT — see LICENSE. Links ReportFlow: https://re-port-flow.com npm: https://www.npmjs.com/package/reportflow-mcp Issues: https://github.com/re-port-flow/reportflow-mcp/issues
Highest accuracy web search for AIs
Smart contract security library for blockchain. Browse audited contracts, explore security patterns, and reference Solidity documentation.
text Agentic local business intelligence for Florida — 983 ZIPs, OSM POI layer, IRS income data, sector gap analysis, and 500 oracle prompts. 20 MCP tools. LLMs pay $0.01–$0.05/call. Free discovery tier available. Built for autonomous agents and LLM pipelines. thelocalintel.com