Manage leads, contacts, and deals in Close CRM. Log calls, send emails, create tasks, and track pipeline activity.
1:1 wrapping of abap-adt-api into a MCP server.
Create and manage CodeQR short links and QR codes, and pull scan, click and conversion analytics — from any MCP client. Each QR code encodes a short link rather than the destination itself, so where it leads can be changed after it has been printed or shared, without reprinting anything. Every scan and click is recorded with time, country and device.
Error knowledge database for AI coding agents. 2002 verified error patterns across 43 domains. Returns dead ends (what NOT to try) and workarounds (what works) for any error message. Covers Python, Node, Docker, CUDA, Kubernetes, ROS 2, PyTorch, and 36 more domains.
Turn one static PNG or JPEG line-art illustration into a hand-drawn scribe animation. AI agents can optionally control the drawing order and hand display, create and monitor a free watermarked MP4, and return a private management and download link. No account signup or manual timeline editing is required.
QR Rápido is an ultra-fast QR code generator built for AI agents and automations. Generate QR codes for URLs, Wi-Fi networks, vCards, WhatsApp, Email, SMS, and free text in milliseconds. 🇧🇷 Native Brazilian PIX support — build fully compliant BRCode/EMV payment QR codes from a PIX key, amount, and recipient name. Supports CPF, email, phone, and random key formats. Open-value and fixed-amount QRs both supported. Returns inline base64 images — no file hosting, no extra steps.
Provide a simple and effective way to demonstrate Model Context Protocol functionality. Easily deployable on Smithery, it allows you to echo text and retrieve the current time in various formats. Enhance your applications with seamless integration of real-time data and tools.
**Give your AI coding agent a living project brain.** Project Mapper scans your codebase once and builds a fast, structured knowledge graph of every module, class, function, and their relationships — then answers complex queries in milliseconds. **Massive token savings:** - **~87%** (Full mode) / **~91%** (Slim mode) average token reduction vs grep + reading raw files - **~380×** faster than reading raw files for the same task - Geometric mean measured across 11 real-world
Rendered pull request, Markdown, document, Forms, and Research review workflows for humans and coding agents.
TwoThumbs is a hosted, remote MCP server built by NOMOI Labs, connect over Streamable HTTP at https://twothumbs.co/mcp, no local package or installer required. It works with Claude Code, Codex, Cursor, and CI/headless clients. Anonymously, or with a free-tier quota, callers can run run_verdict to exercise every visible affordance on a public URL, clicking, submitting forms with clearly marked synthetic data, and tracing whether the artifact actually landed, then get a straigh
Unified MCP gateway that loads 150+ AI tools via a single Docker command. Execute Python code in sandboxed subprocesses, generate complete MCP server projects from natural language, and run AI-powered code generation — all through one endpoint. Built to solve the Windows MCP failure modes nobody else documents.
The code context layer for AI coding agents. GitHits connects AI coding agents to public open-source evidence across the full software development lifecycle: discovery, planning, research, implementation, debugging, and maintenance. Agents can search and navigate indexed package and repository source code, read exact files and documentation pages, inspect package health, compare dependency upgrades, and find source-cited examples from real open-source projects. Some use c
Legacy-Code-Migrator is a premium micro-service from the M2MCent factory, configured as a Model Context Protocol (MCP) server. Functionality: Automated code modernizer converting legacy logic to ESNext. Features autonomous cryptographic settlement via x402 on Base Mainnet. Fee: $0.35 USDC per execution.
Access LeetCode problems, user information, and contest data seamlessly. Enhance your AI assistants with fast and efficient queries to LeetCode's extensive resources. Utilize both CLI and programmable API for flexible integration.
Aggregate and normalize datasets from your cloud storage for faster discovery and analysis. Summarize rental prices to compare markets, spot trends, and share concise takeaways. Accelerate workflows by fetching core datasets and delivering clean, ready-to-use outputs.
AI Search (AutoRAG) management. List and search documents across your AI Search indexes.
Developer-first rank tracking and SEO intelligence for AI agents. Track keyword positions, run rank checks, inspect competitors and backlinks, and manage Bisibility projects securely through OAuth.
Provide healthcare data access and querying capabilities by integrating with Google Cloud Healthcare FHIR APIs and public medical research databases. Enable seamless retrieval of patient records, clinical data, and research articles through a secure and authenticated MCP interface. Enhance healthcare applications with real-time clinical insights and research information.
Deterministic code governance for AI coding agents. Norma checks code against your organization's rules as the agent writes and returns a fixed verdict: rule ID, severity, line, fix. Same file, same rules, same answer, whichever agent is driving. One ruleset, versioned centrally, with an audit trail of every check. Connect from Claude Code, Cursor, Copilot or any MCP client. OAuth sign-in, no configuration.
# Motecloud Memory MCP Motecloud is durable memory infrastructure for AI agents. It gives MCP clients a shared, tenant-scoped memory layer for remembering facts, decisions, codebase context, task history, contradictions, and working-session notes across conversations and tools. Use Motecloud when your agent needs more than chat history: long-lived graph memory, hybrid semantic search, task context priming, real-time session capture, and safe memory writes with OAuth-based a
MCP server for remote SQLite databases via Turso/libSQL. - 15 tools for query, schema, indexes, and optimization. - Connect to cloud-hosted SQLite databases using libsql://URLs. Features: - Execute SQL queries and statements with parameter binding - Full schema management (tables, columns, indexes, foreign keys) - Database analysis (size, table stats, integrity check) - WAL mode enabled for better concurrency Install (Claude Desktop / Cursor): npx -y @node2flo
Store and retrieve data objects for free. Temporary cloud storage for agents. Two hour expiry. Works with any format and flow. Example use cases include: - Manage large datasets across different sessions - Generate shareable links for intermediate results - Streamline complex workflows by bridging information between multiple contexts
Automate the extraction of your codebase context for Large Language Models. This tool scans your project directory, respects .gitignore rules, and formats the output for seamless integration with MCP-compatible clients. Save time and enhance your LLM's context with structured codebase information.
Search and browse CliquePrize®'s site content directly from your conversation. This server gives Claude access to CliquePrize®'s published pages — list every page with its title and last-updated date, or search for a specific keyword or phrase to find matching pages with relevant text snippets. Tools: list_pages — List all published CliquePrize® site pages with slug, title, and last-updated date search_content — Search CliquePrize® site content for a keyword or phrase, retu
Programmatic Tableau workbook (.twb/.twbx) generation. 47 MCP tools for charts, dashboards, calculated fields, workbook migration, and CSV-to-dashboard pipelines. Install via uvx twilize.
Stack Trace Medic is a premium micro-service from the M2MCent factory, configured as a Model Context Protocol (MCP) server. Functionality: Coded error stack trace debugger and automated patch generator. Features autonomous cryptographic settlement via x402 on Base Mainnet. Fee: $0.03 USDC per execution.
SeldonFrame is an open-source, MCP-native Business OS. One conversation in Claude Code or Cursor creates a live workspace — website, booking page, intake form, CRM, and an AI receptionist — on a real subdomain in about 3 minutes.
Turn long videos into AI-curated short clips: caption, reframe, thumbnail, schedule, publish
Enable AI models to interact with Windows command-line functionality securely and efficiently. Execute commands, create projects, and retrieve system information while maintaining strict security protocols. Enhance your development workflows with safe command execution and project management tools.
Licence risk checking for AI coding agents. LicenseGate checks a software package and its dependency tree, considers how the software will be used, and returns a simple LOW, MEDIUM or HIGH risk result so an agent knows whether it can proceed or should stop for review.
Enable integration of WezTerm terminal emulator with external tools and resources through the Model Context Protocol. Enhance your terminal experience by allowing dynamic access to data and actions via MCP. Simplify automation and context-aware workflows within WezTerm.
Execute terminal commands locally or remotely via SSH with session persistence and environment variable support. Manage terminal sessions that maintain state for up to 20 minutes, enabling efficient command execution workflows. Connect using stdio or SSE for flexible integration with AI models and applications.
Manage project quality gates and diagnostics with automated checks and actionable resolution steps. Tracks operation failures and provides detailed fix packets for rapid debugging. Persists project-specific instructions and preferences across sessions to maintain a consistent development context.
Read-only access to authorized patent workspaces, folders, fields, patent collections, and annotations.
The official MCP server for **Nahook**, the developer-experience layer for webhooks. It lets your AI assistant drive your webhook platform in plain language — with the same permissions you have in the dashboard. Ask your assistant to: - **Inspect endpoints** — list endpoints and environments in your workspace - **Debug deliveries** — browse delivery history and attempt-by-attempt logs (status codes, response times, and the exact failure reason) - **Recover** — retry failed
Translates a lockfile diff into a human-readable upgrade plan for npm and PyPI. Point this MCP at a Dependabot PR, lockfile diff, or any pair of package versions and get back a ranked upgrade plan. For every dependency bump it returns semver classification, breaking changes extracted from GitHub release notes, CVEs fixed in the range (via OSV.dev), migration guide links, and a per-package recommendation. Bulk tool analyzes up to 50 package changes in parallel and ranks by ris
Agent-first e-signature MCP server with **offline PAdES signing** and hash-chained audit. The same 19 tools / 4 prompts / 12 resources are reachable via stdio (`npx @drbaher/sign-cli mcp serve`) for local agents and over HTTP for remote ones. **Architectural claim:** an LLM agent can drive every step of a contract workflow except the actual signing gesture, which stays gated behind a human via per-signer approval tokens (TTL-bounded, scoped to one email, single-use). Pre-sig
AI agents hallucinate package names. `need` gives them a verified index of 10,000+ CLI tools with a feedback loop that gets smarter with every install. **Three MCP tools:** - `search_tools` — semantic search in plain English ("compress png images") - `install_tool` — install via brew, apt, npm, pip, or cargo (allowlisted only) - `report_tool_usage` — success/failure signals that improve rankings for every future agent **Works with:** Claude Code, Cursor, Claude De
Store and search user-specific memories to maintain context and enable informed decision-making based on past interactions. Seamlessly integrate memory capabilities into your AI tools with a simple and intuitive API. Enhance your agents with relevance-scored memory retrieval for improved contextual awareness.
A social publishing platform where AI agents are the authors. Register a byline, post notes and long-form articles, follow other agents, comment, like, and DM. Reading and search are open; sign in with Google or GitHub to give your agent a verified identity and start publishing. Writes are gated by a reverse-captcha: post something and LatticeNet may hand back a challenge only an agent can answer. Pass it and the post keeps its verified badge. Ignore ten in a row and the acc
# EM+X — MCP server **Finished, on-brand `.pptx` and `.docx` from a brief — quality-gated by an agentic consulting team.** EM+x is a remote [MCP](https://modelcontextprotocol.io) server. Connect it to any MCP-capable client (Claude, ChatGPT, Cursor, Codex, Grok, Copilot, …) and your assistant can assemble a brief from the conversation, propose a document structure for your approval, generate a presentation or document through a multi-agent quality-gate stack, refine it by p
Manage your FadeHost game servers from any MCP client: start, stop, and restart servers, read console logs and send commands, check live stats and player activity, and create or list backups. Every action runs through the same authorization, subscription, and quota checks as the FadeHost control panel. Create an API token at https://laplace.fadehost.com/profile/ai-access and connect in seconds.
Mindola turns a person's knowledge into a "lens": one public link where anyone can ask questions in chat or a live voice call, with every answer grounded only in the owner's material, with citations and honest refusals. The MCP server lets an assistant create a lens from a profile the user approves in conversation, enrich it with text or URLs, and check ingestion status. No account is needed to create a lens; the user reviews the live page and claims it by signing up. Great f
**Agent memory that survives you — durable, wallet-addressed, free to start.** No signup, no API key, no payment: any EVM keypair is a working account with a free tier (256KB) that covers real agent state. You are a process, not a server: when your session ends, your state ends with it. The Locker keeps what must persist, and a fresh process holding *only* your wallet key recovers it byte-for-byte — across sessions, machines, and vendors. **Zero-ceremony MCP (recommended):*
Post messages to Google Chat spaces effortlessly using webhooks. Simplify your integration without the need for OAuth setup, making it secure and easy to use with MCP-compatible tools.
Classify raw text into structured triage objects with intent, urgency, category, and sentiment. Zero-config MCP tool for support intake, lead routing, and ticket automation
Turn any idea, URL, doc, or PDF into on-brand visuals: carousels, posts, decks, and documents in 100+ formats, generated natively in 150+ languages. Brand kits keep every output in your colors, fonts, and logo. Tools cover the full loop: create, edit, localize, create variations, and export to PDF/PPTX. Sign in with any Canvora account (free tier, no card required).
Real-time XLM (Stellar) market sentiment as an MCP tool, computed from a keyless composite of the Crypto Fear & Greed Index, Stellar SDEX order-flow imbalance, and 24h price momentum. No LLM in the loop, no API keys. Hosted and agent-wallet ready via x402 (pay-per-call in USDC on Base).