Подборка — 14 032

Inspect, author, validate, and run high-content microscopy workflows.

AI-powered OSINT agent & MCP server. 16 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.

Robots-aware website audits, pre-crawl quotes, and structured evidence for people and agents.

Agent bookkeeping, sanctions, KYB, VAT and e-invoice checks - pay per call in USDC

Guideline-cited biomarker analysis for chronic conditions (diabetes, lupus, cancer). Synthetic.

Unpaid qualification-gated operational_context canary. Staging data. No wallet.

Paid KYC, AML, and regulatory risk assessment over MCP via x402 USDC micropayments on Base.

SIP trunking, numbers, porting, messaging, billing, and CDR analytics on the Ringer WARP platform

Real-time NSE/BSE stock sentiment, news NLP, technical analysis & RAG search via MCP.

Fixed-fee P2P term loans (no oracles) and flash loans on Ethereum, Base, Arbitrum and Sepolia.

project-summarizer

smithery.ai

x402 Text Summarizer compresses text, Markdown, or JSON into structured summaries using Claude AI. Part of the x402 micropayment task market — pay per call with $0.005 USDC on Base mainnet, no subscriptions or API keys required. Two tools included: summarize_text — full access. Four output formats (prose, bullets, headline, tldr), three length presets (brief ~30 words, medium ~80 words, detailed ~200 words), optional exact target word count (1–500), and an explain mode that

Gifi

smithery.ai

Inspect hidden Unicode for free. Paid rewrite for published statistical text watermarks (Claude, Gemini). Strip C2PA and file metadata. We will not certify a detector. Contact: support@gifi.ai

Proctor AI

smithery.ai

Proctor AI is a free AI grading tool built for teachers who lose evenings to marking. Upload a single PDF of the whole class and the agent splits the papers, reads handwritten answer sheets, grades each one against your rubric, runs integrity analysis for copying and AI-written text, and drafts personalised feedback for every student. The teacher reviews and approves every mark. Now with a Claude MCP so you can grade a class by chatting with Claude. Trusted by 2,000+ teachers

Humanizer PRO

smithery.ai

Humanizer PRO is a text humanizer and MCP writing assistant for Claude, Cursor, ChatGPT, and other AI agents. Rewrite authorized drafts in Stealth, Academic, or SEO mode, scan writing naturalness, and check word balance through the hosted OAuth MCP service.

Pagr

smithery.ai

# HTML is the new Markdown. Share it just as easily. ## Upload a HTML file, get a public URL you can send to anyone. No configuration, no build step, no GitHub Pages setup.

CiteRank

smithery.ai

Search is moving from ten blue links to AI-generated answers. ChatGPT, Perplexity, Gemini, and Google AI Overviews now answer questions directly and cite a handful of sources. If your brand is not one of them, you are invisible to a growing share of your market. Citerank shows you exactly why. It audits 35+ on-site and off-site signals that decide whether AI engines can read, trust, and quote your site, from schema markup and entity consistency to passage-level citability an

ScanToBill MCP-Server

smithery.ai

MCP server for ScanToBill — extract structured data from invoices and business documents. Use with Claude Desktop or any MCP-compatible AI client.

MainBook Bank Statement Converter

smithery.ai

Convert customer-supplied PDF bank statements to checked JSON, Excel, or CSV with balance validation. The official MainBook MCP server runs as a hosted Streamable HTTP endpoint you sign in to with your MainBook account, or locally over stdio with uvx mainbook-mcp. It validates arithmetic against opening and closing balances, reports reconciliation issues, and does not connect to bank accounts. Conversions spend page credits on your own MainBook account; the server cannot buy

Blackbook Protocol Advisor

smithery.ai

Blackbook Protocol Advisor is the portable Architect for verified purchasers of Blackbook Protocol. Connect Claude, ChatGPT, or Cursor. After order-email OAuth, the model coaches the Protocol sequence rather than generic UK company-law chat: Search cited Protocol passages before answering Follow module playbooks: Vault, TRS, 95/5, PSC, banking, IP Load workflow skills (establish Vault, register TRS, implement 95/5, update PSC, portal co-pilot) Self-serve official GOV.UK / C

Keelen

smithery.ai

Autonomous dev team steered from chat: connect a GitHub repo and your own Claude/Codex/GLM/Kimi key; plain-English requests become tested, merged PRs. Signup works over MCP: paste SETUP.md from github.com/jamie7893/keelen-mcp and say "set me up".

Inxy SEO Audit

smithery.ai

Free SEO & AI-search (AEO/GEO/LLMO) audits for any website or Shopify store: 12-signal AI-readiness score, full SEO audit, emailed reports with weekly score tracking, and one-click inxy subscription links. Tools: ai_search_diagnostic, full_seo_audit, email_seo_report, subscribe_to_inxy, get_my_store_audit.

fine-structure

smithery.ai

Build and host full-stack apps from a prompt, with agents that reach you on WhatsApp and email. Pages, a managed database, authentication, publishing, custom domains with automatic TLS, restorable saved versions, traffic analytics, and autonomous agents that message their verified owner on WhatsApp through a platform number, with no WhatsApp Business account needed.

BrainTube

smithery.ai

Save once. Query anywhere. BrainTube turns everything you save — YouTube, articles, podcasts, PDFs, Notion, Obsidian, web — into a personal knowledge base any AI can search. Semantic search, knowledge graph, expertise profiles, and ingest tools, from Claude, Cursor, or any MCP client.

sync

smithery.ai

**Your agent doesn't ask for memory. It uses it.** The moment Sync connects, Claude, Cursor, VS Code, and Zed start checking it before every task — and writing to it after every decision. No *"look it up."* No *"remember this."* The protocol handles it. What that means in practice: - Decisions made on Tuesday survive Friday's new chat - A teammate's agent picks up exactly where yours left off - The same context follows you across every editor you use - A new person on the

ai-screening

smithery.ai

Screen BPO candidates and search your call center documents directly from Claude. screen_candidate returns a score (0–100), a hire decision (HIRE / INTERVIEW / HOLD / REJECT), a rationale for the hiring manager, plus the candidate's strengths, skill gaps, and improvement tips — all in one call. Works for appointment setters, CSRs, collections agents, non-voice roles, and supervisory positions. - 9 tools total: • screen_candidate — single CV scoring with employer + candidat

Iridium - LinkedIn for AI Agents

smithery.ai

LinkedIn outreach, commenting, scheduling, and data via Claude and human approval gates.

aiscreeningtools

smithery.ai

● AI Screening Tools — MCP Server Screen candidates, generate job descriptions, and search HR knowledge — all from your AI client. Built for BPO companies, staffing agencies, and HR teams hiring at volume across Southeast Asia. Connect once and get 22 tools covering every stage of pre-interview screening. What you can do: - Score a CV 0–100 with a HIRE / INTERVIEW / HOLD / REJECT decision in seconds - Screen a batch of candidates and get a ranked shortlist -

DataForB2B

smithery.ai

DataForB2B is a people and company search API powering live data from public sources across LinkedIn, GitHub, job boards, and web sources. Search by job title, company size, tech stack, funding stage, hiring signals, or past experience across 60+ filters with verified email enrichment. GDPR and CCPA compliant.

StudioMeyer-GEO

smithery.ai

AI visibility monitoring across 8 LLM platforms (ChatGPT, Gemini, Perplexity, Claude, Grok, DeepSeek, Copilot, Meta AI). 23 MCP tools + 5 expert workflows. 19 tools free without API keys. EU hosted Frankfurt.

mempalace memory

smithery.ai

https://mempalace-mcp.vercel.app/ — Register or sign in here first to create your API key (mpk_...). mempalace memory is the hosted MCP layer from the mempalace (Memory Palace) project: per-user memory drawers (wing/room), semantic search on Cloudflare (D1 + Vectorize + Workers AI embeddings). MCP endpoint: https://glidepath.dpdns.org/mcp . Authenticate with Authorization: Bearer <key> or X-Mempalace-Api-Key (for Smithery Session Config / gateways). MIT license. In-server do

companyscope-mcp

smithery.ai

Company intelligence MCP server. 11 tools aggregating 12 free data sources (Wikipedia, GitHub, SEC EDGAR, OpenCorporates, USPTO patents, Brave Search, RDAP, DNS, web scraping). Full company profile in one tool call.

TestMu AI MCP Server

smithery.ai

TestMu AI MCP Server lets developers run, debug, and triage tests using natural language directly from their IDE (Cursor, Claude, GitHub Copilot & other MCP clients). **Tools:** - **HyperExecute** — test orchestration + YAML config - **Automation** — debug test failures via logs - **SmartUI** — visual regression analysis - **Accessibility** — WCAG / a11y checks - **Test Manager** — AI test-case generation Endpoint: https://mcp.lambdatest.com/mcp (OAuth). Docs: https://www.t

Simple PDF API

smithery.ai

Generate and manipulate PDFs from Claude Desktop, Cursor, and Windsurf. 9 tools: HTML-to-PDF, URL-to-PDF, merge, split, watermark, compress, password-protect, rotate, and extract text. Free tier on RapidAPI.

Newsmind

smithery.ai

RSS for ChatGPT, Claude & Gemini: semantic search, story clustering, keyword watches with scheduled email digests, OPML import. Hosted — works on web, desktop, and mobile.

czechia-payments

smithery.ai

Let AI agents accept payments in Czechia (CZK) — cards, Apple Pay / Google Pay — via Stripe Checkout . Stateless, bring-your-own credentials (x-stripe-secret-key), never holds funds. Owner policy guardrails: x-agentpay-max-amount / x-agentpay-approval-above.

Strunk

smithery.ai

Strunk publishes a draft you wrote in Claude, ChatGPT, or Codex out to Google Docs, then brings your reviewers' comments back with the exact spans they anchored to. You triage and revise inside the AI tool that already holds your repo and data context, while your reviewers keep commenting in Google Docs. There is no copy and paste, no pull request, and nobody has to adopt a new tool to leave feedback. Existing comments and their anchors survive a re-publish. Revisions land a