Smithery's MCP Proxy and managed identity shut down on October 31. See what's changing
The most comprehensive food safety MCP server. 5 tools: check any food additive (E-number, CAS, name), scan full ingredient lists for risks, search by category/concern, look up nutritional profiles of 4,624 Israeli foods, and check pesticide residue limits on crops. Data: 6,450+ additives with PubChem molecular data, 6,563 JECFA ADI evaluations, 5,251 EFSA toxicology records, 77,278 synonyms, 4,624 MOH nutrition profiles, 3,708 pesticide MRLs, 1,290 FDA GRAS notices, Israeli regulatory status, dietary flags (vegan/halal/kosher). Built by Two Halves — twohalves.ai
DC Hub is the live data layer for data-center site selection and the power, grid and energy infrastructure behind it. Its DCPI is a daily score of where data centers can get grid power, across 300+ markets. Agents can query it and cite it. It also covers 330,000+ mapped power, grid, gas and fiber assets and ISO interconnection queue snapshots, and carries live grid feeds from the seven US ISOs (PJM, ERCOT, CAISO, MISO, SPP, NYISO, ISO-NE), plus retail and wholesale electricity prices by state and ISO. Answers carry an as-of timestamp and a citation line. The server has 94 MCP tools at https://dchub.cloud/mcp plus a REST API at https://dchub.cloud/api/v1. The free tier needs no key; paid plans: dchub.cloud/pricing. Capacity Source adds a free capacity marketplace: operators list data-center capacity at https://dchub.cloud/listings, and agents search it by size and location with sourcecapacity, then request an introduction with requestcapacity_intro.
Primary-source commodities for agents — EIA inventories, FRED cash, CFTC COT, USDA fundies, USGS minerals, derived crack/crush via x402 USDC on Base.
Cannabis and controlled substances regulatory intelligence MCP server. Query state-by-state cannabis testing limits (pesticides, heavy metals, microbials, solvents, potency) across 18+ US states. Check substances against UN INCB Yellow List (154 scheduled narcotics), EU Drug Precursors Regulation (46 controlled chemicals), and EMCDDA Novel Psychoactive Substances database. Verify Health Canada cannabis compliance (383 regulations). 2,566 total records across 5 databases. Built by Two Halves — twohalves.ai
One (free) MCP for the Web. Easily search, crawl, navigate, and extract websites without getting blocked. Ideal for discovering and retrieving structured insights from any public source - effortlessly and ethically. New features are live - check out what’s new: https://brightdata.com/ai/mcp-server/launch-week
Fast, intelligent web search and web crawling. Get fresh information about libraries, APIs, and SDKs.
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliability. Transform webpages into structured markdown, extract data using AI, and execute AI-powered web searches seamlessly. Enhance your applications with powerful web data extraction capabilities through this integration. It could also make web search, browser automation and markdownification
Verifiable document intelligence for AI agents. Extract text, tables, and structured data from PDFs and URLs. Summarize, answer questions, check claims, and translate — all with cited evidence. Store tamper-evident evidence bundles with cryptographic signatures and on-chain attestation via Base L2. Cross-document semantic search and Q&A across named collections. Pay per call with USDC (x402) or use an API key.
Web scraping and automation platform. Run scrapers, extract structured data, and automate browser-based workflows.
Unified MCP server for six medical terminologies — ICD-11, LOINC, RxNorm, MeSH, ATC and the Brazilian CID-10 (Portuguese) — with authoritative WHO ICD-10→ICD-11 mapping, cross-terminology search and provenance (source, version, timestamp) on every response. Read-only retrieval, not clinical decision support. Remote (Streamable HTTP, no auth, no credentials) or local stdio.
Search the web in real time to get trustworthy, source-backed answers. Find the latest news and comprehensive results from the most relevant sources. Use natural language queries to quickly gather facts, citations, and context.
Senado BR MCP Brazilian Federal Senate open data over MCP — read-only tools covering the legislative process, Senate administration, and citizen participation. Hosted on Cloudflare Workers (Streamable HTTP), no authentication required. Connect https://senado.sidneybissoli.com/mcp ▎ Tool names and responses are in Portuguese (pt-BR), matching the official Senate data. Covers Legislative — bills, tramitação, votes, vetoes, committees, plenary sessions & agendas Speeches — senator speeches, shorthand notes, transcripts & session videos Senators — directory, mandate history, leaderships, blocs & parties Transparency — CEAPS expenses, payroll, contracts, biddings & budget execution e-Cidadania — public consultations, legislative ideas & events Sourced from the official Senate open-data APIs (legis.senado.leg.br, adm.senado.gov.br) and the e-Cidadania portal.
Pay-per-call compliance API for OFAC screening, vendor diligence, and audit-ready document output. No subscription, no API keys — settle each call in USDC on Base
Agent Personas for Claude. 14 MCP tools, 8 built-in personas (CEO, CFO, CMO, CTO, PM, Analyst, Support, Creative), custom personas, chained workflows. Zero extra API cost. Free tier.
Official MCP server for the Sugra API: one connector for 1,500+ data endpoints across 36 domains (markets, macroeconomics, company fundamentals, government data, news, climate, maritime, trade, entity screening), backed by 160+ primary sources - mostly sovereign statistics agencies, central banks, and intergovernmental bodies. Hosted at app.sugra.ai/mcp (Streamable HTTP). Catalog search and describe run against a bundled endpoint catalog; data calls hit the API. Source attribution and freshness on every result; structured errors instead of silent failures. Free tier: 50 requests/day. MIT package: pip install sugra-api-mcp. Docs and keys: https://sugra.ai
The Nimble MCP Server gives AI agents the ability to search, extract, map, crawl, and structure data from any website in real time. It exposes Nimble’s full web data platform as MCP tools that any compatible AI client can use.
Brazilian Central Bank (BCB): SGS time series, Focus market expectations (Olinda API) and PTAX exchange rates — read-only tools with statistics (variation, correlation, deflation) and a provenance block on every response.
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
Real-time direct access to unmodified data and raw filings of 30 official government registries via MCP. Tools: search companies, get profiles, officers, shareholders, filings, and financial statement documents. Covers UK Companies House, Ireland CRO, France RNE, Spain BORME, Italy InfoCamere, Norway Brreg, Poland KRS, Netherlands KVK, Belgium KBO, Switzerland Zefix, Finland, Czechia, Korea, Taiwan, New Zealand, Cayman Island, Australia, Canada and a lot more. Free tier; paid keys for higher quota.
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.
UNESCO Institute for Statistics (UIS) with full provenance on every response: search ~5,000 indicators on education (enrolment, completion, literacy, out-of-school, expenditure), science and R&D (SDG 9.5), culture (SDG 11.4) and communication, and retrieve them by country, region and year — with source URL, data release, retrieval timestamp, licence and UIS citation. Everyday and US wording (enrollment, spending, preschool, university) is resolved to the UIS's own terms. Remote (Streamable HTTP, no auth) or local stdio.