#agentic

Execute one-off or scheduled tasks within a virtual computer that can spin up a real browser, a full coding agent, an email inbox and more. OpenHelm unlocks the ability for your agent to carry out all sorts of tasks, such as: • Deep research on a topic • Emailing + handling responses • Coding work • Updating files What makes OpenHelm the best solution for this: • Underpinned by a powerful AI that monitors work and ensures goals are actually achieved • Browser is SUPER stealthy, meaning it can access more of the web than other bots • Work is managed by a powerful agentic system, facilitating multi-step flows For performing complex, one-off or recurring work, OpenHelm provides a secure, remote environment to make it all possible.

HemmaBo verifies and books host-owned vacation rental domains. Use it when the user wants a direct, host-domain verified stay offer. HemmaBo + VRP, 13 tools, host-domain signed verified stay offers. Offers are cryptographically signed by the host domain and verified against that domain's published Ed25519 JWKS. Not an OTA. Not a marketplace.

Read-only MCP server giving any AI assistant access to CallSphere's voice-AI (short) knowledge base, ROI calculator, industry case studies, and product facts. Works in every MCP-capable client.

Live TikTok creator intelligence for AI agents. Hooklayer pulls real performance data from any TikTok handle in seconds: viral DNA scoring, replicability analysis, top-performing video breakdowns, format fingerprints, hook patterns, and a stealable steal_map. 7 MCP tools that chain automatically — analyze_account returns a recommended_chain that pre-fills the next 3 tool calls (voice match, trend pulse, viral remix), no prompt engineering. Score hooks, predict virality, remix viral scripts scene-by-scene. Free tier: 100 lifetime credits, no card.

France Data MCP lets AI agents query, cross-reference and automatically enrich multiple French public registries through a unified MCP interface. France Data MCP provides a French territorial intelligence layer designed for multi-source reasoning and agentic orchestration. The server combines territorial data, geocoding, public health, administrative registries and multi-source enrichment to enable complex geospatial and territorial reasoning workflows. Unlike simple API wrappers, the tools are designed to be chainable by AI agents to autonomously solve complex business questions.

DataGrout is the connectivity and intelligence layer that lets AI agents actually operate inside your enterprise, automating complex multi-step workflows, connecting to any system through a single endpoint, and doing it all with built-in guardrails, persistent memory, and full observability. From data preparation to LLM cost tracking to prompt injection defense, DataGrout turns agents from sandboxed experiments into systems your business can actually depend on.

AI travel agent over MCP — live flights, hotels, activities, and events worldwide, then completes the booking on autonomad.ai (free signup at checkout, first month of Premium included).

MuntuAI is an outbound for AI agents. Your agent can now launch and manage large scale personalized email campaigns with its own email accounts.

The first payment-contingent FX protection server on MCP. Price a Guard (invoice-linked FX protection for SME invoices and payables), get live spot and forward rates, model 25 years of historic FX stress scenarios, and resolve settlement dates — all via natural conversation. Public endpoint, no authentication required. Designed for PSPs, accounting platforms, and agentic cross-border payment workflows.

pentestMCP: AI-Powered Penetration Testing via MCP pentestMCP provides a powerful bridge between Large Language Models (LLMs) and practical penetration testing tools through the Model Context Protocol (MCP). This project functions as an MCP Server, exposing a curated suite of over 20 standard security assessment utilities (Nmap, Nuclei, ZAP, SQLMap, etc.) as callable 'tools'. This allows AI agents within MCP-compatible clients (like Claude Desktop or specific VS Code setups) to leverage these utilities for automated and interactive security analysis tasks.

Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.

HTTP 402 + USDC pay-per-call API for AI agents. 16 endpoints (QR codes, screenshots, OG images, PDFs, web scraping, WHOIS, YouTube transcripts, AI summarization, plus a 4-endpoint crypto cluster — wallet balances, ENS resolution, gas, coin prices). Two payment rails: x402 (autonomous USDC on Base mainnet, no signup, no API key, server holds zero private keys) or pre-paid credits ($1 = 5 calls via NowPayments). Hosted MCP server included.

MCP server for the Pepesto's Grocery Shopping API - give your agent the ability to turn any recipe (a URL, plain text, or a photo) into a matched basket of real supermarket products with live prices, across 26 European supermarkets. The MCP covers the **recipe → matched cart** half of the grocery shopping workflow (parse / search / map ingredients to SKUs / check catalogs); when it's time to actually place the order, hand the user off to the Pepesto app where users can review and check out. Supported European Supermarkets: Sainsbury's - sainsburys.co.uk ASDA - asda.com Morrisons - groceries.morrisons.com Waitrose - waitrose.com Tesco - tesco.com Albert Heijn - ah.nl Jumbo - jumbo.com Plus NL - plus.nl Rewe - shop.rewe.de Coop CH - coop.ch Migros - migros.ch Farmy - farmy.ch Aldi CH - aldi-now.ch Colruyt - colruyt.be Delhaize - delhaize.be Tesco IE - tesco.ie SuperValu - shop.supervalu.ie Dunnes - dunnesstoresgrocery.com Esselunga - spesaonline.esselunga.it Conad - spesaonline.conad.it Nemlig - nemlig.com Meny - meny.no Frisco - frisco.pl Auchan PL - zakupy.auchan.pl Bulmag - bulmag.org eBag - ebag.bg

Coordination protocol for real-world tasks (cleaning, plumbing, painting, gardening, repair) in the Netherlands. AI agents create tasks via natural language through POST /do endpoint. AstraNL handles provider matching, transparent pricing, Stripe Connect escrow (99% to provider, 1% AstraNL fee), evidence chain, dispute resolution. Free first 3 tasks per agent. KvK 88449335, EU AI Act compliant. Supports 10 languages.

109 MCP servers for agentic commerce across LATAM (Brazil, Mexico, Argentina, Colombia, Chile, Peru). Stripe ACP, x402, AP2, Google UCP + 100 regional providers covering payments, fiscal, banking, communication, logistics, ERP, identity. 2,289 tools. stdio + Streamable HTTP. Published as @codespar/mcp-* on npm.

Read-only doctrine and example access for the Agentic AI Blueprint — the industry standard reference for safe, observable, and steerable AI agent UX. Browse and search 10 principles across principle clusters, access curated implementation examples, retrieve application guides for security and evaluation challenges, and download agent asset artifacts. 13 public tools require no credentials. Auth-gated tools for learning path and coaching context require a Firebase Bearer token.

MCP adapter for x402station.io — infrastructure for x402 agentic commerce. Brand umbrella across 6 capability directions: Discover (Catalog), Evaluate (Preflight, the active flagship), Pay (Credits), Monitor (Watch), Recover (Alternatives), Analyze (Forensics). Preflight by x402station.io is the pre-payment evaluation layer: agents call it before every paid x402 request to detect decoys (price ≥ $1000 USDC honeypots), zombie services (100% erroring), dead endpoints, slow responses, and new providers. Auto-signs PAYMENT-SIGNATURE via AGENT_PRIVATE_KEY. Tools exposed: preflight ($0.001), forensics (7-day report, $0.001), catalog_decoys (full blacklist, $0.005), alternatives (routing fallback, $0.005), whats_new (catalog diff, $0.001), buy_credits ($0.50 = 1000 prepaid preflights), watch_subscribe ($0.01 = 30-day webhook alerts), plus free credits_status / watch_status / watch_unsubscribe. Wallet must hold Base mainnet USDC.

Polish-language dictionary of the Agentic Web — terms covering MCP, agent-readiness, new SEO standards (GEO, AIO, LLMO) and emerging protocols (WebMCP, UCP, AP2).

Access Versium's B2B2C identity graph directly through your AI agent. Generate targeted lead lists, enrich records with contact and firmographic data, validate emails, and size audiences — all through natural language. No manual exports or API coding required. Requires an active Versium REACH subscription with API access.

Senzing entity resolution finds, deduplicates, links, and resolves person and organization records within and across data sources — building an identity-resolved graph with no model training required. Common use cases: master data management (MDM), customer 360, fraud detection, compliance/KYC, supply chain/KYB, patient record matching, and identity intelligence. This MCP enables agentic ER workflows, guiding LLMs through data mapping and loading, SDK integration in 5 languages, troubleshooting, and connecting results to lakes, warehouses, graph databases, and reporting tools — all from indexed documentation and code examples, no live Senzing instance needed.

37 MCP servers for agentic commerce and Brazilian services. Stripe ACP, x402 (Coinbase), AP2 (Google), Google UCP, plus 14 Brazilian payment rails, fiscal, banking, communication, logistics, ERP, identity, and crypto APIs. ~480 tools. Supports stdio and Streamable HTTP. Published on npm as @codespar/mcp-*.

Arithym eliminates LLM math hallucinations and reduces wasted tokens on throwaway code generation. Instead of letting your model predict what math looks like, Arithym provides exact fraction arithmetic through a single MCP tool call — no code generation, no rework. 209 methods across 22 domains: basic arithmetic, algebra, statistics, trigonometry, unit conversions, combinatorics, number theory, and system modeling. Every result is exact — fractions stay as fractions through entire computation chains with zero floating-point drift. Includes a curated reference knowledge layer with physics constants (NIST-sourced), periodic table data, unit conversion factors, and exact trigonometric values for common angles — all queryable as part of the math pipeline. Free explorer tier, no credit card required. Connect via OAuth at arithym.xyz/mcp.

Persistent memory for AI agents, important things stick, forgotten things fade, outdated facts get pruned automatically using the Ebbinghaus forgetting curve.

Supercharge your AI agents without sacrificing privacy. AgenticStore provides 31+ open-source tools—including real-time web search, secure prompt filtering, and token optimization—all in one locally hosted package. Zero accounts, zero tracking, zero friction. Connect to Claude, Cursor, or Windsurf in less than a minute.

HemmaBo verifies and books host-owned vacation rental domains. Use it when the user wants a direct, host-domain verified stay offer. HemmaBo + VRP, 13 tools, host-domain signed verified stay offers. Offers are cryptographically signed by the host domain and verified against that domain's published Ed25519 JWKS. Not an OTA. Not a marketplace.

The only native Solana staking platform purpose-built for AI agents. 30 REST endpoints, 26 MCP tools, A2A agent card with 13 skills, and custom OpenAPI 3.1 spec. Zero-custody architecture returning unsigned transactions for client-side signing. On-chain memo attribution, SHA-256 source verification, and ~6% APY with Jito MEV boost. Compatible with Claude, LangChain, CrewAI, ElizaOS, OpenClaw, and any HTTP-capable agent.

Agentic AI instruction encoding. 86.8% smaller than JSON. Inference-free decode by table lookup. 342 opcodes, 26 namespaces, three conformant SDKs. Confirmed over LoRa mesh radio. Apache 2.0 with express patent grant.

Connect to InFlow to register, access, and pay for services directly within your AI workflows. Keep onboarding, authorization, and payments for paid services in-context and in-line so your workflows never stop.

AI shopping agents need structured product data to compare prices, check availability, and make decisions. Shopify Catalog covers Shopify merchants. Google UCP covers Google Shopping. ShopGraph covers everything else — the DTC brands, independent retailers, and niche suppliers that platform catalogs miss. Send any product URL, get structured JSON back. $0.01-$0.02 per call.

Control real robots and IoT devices through AI agents. Self-register with wallet authentication, pay with ETH for tier upgrades, and execute Vision-Language-Action commands. Features robot control, sensor monitoring, multi-agent coordination, and autonomous payments.

MCP server for 402 Index: discover 15,000+ paid API endpoints across the L402, x402, and MPP protocols

Local MCP server that gives AI agents eyes and hands on running Uno Platform apps. Agents can capture screenshots, inspect the visual tree, simulate pointer clicks, type text, send key presses, invoke automation peer actions, and query DataContext, enabling agentic UI development and testing across WebAssembly, iOS, Android, macOS, and Linux. Works with Visual Studio Copilot, VS Code, Claude Code, Codex, and any MCP-compatible agent

Open-source on-chain USDC payment gateway connecting AI agents to merchants. Agents make secure x402 payments; merchants accept agent payments with zero card fees. 20 MCP tools for paywall CRUD, agent management, webhook observability, and transaction monitoring on Solana, Base, and Polygon.

Fast, sub millisecond, local on device long term memory for LLMs, Coding Tools and AI Agents. Recall exact details from yesterday of five years ago. Install in 5 minutes.

OrionBelt Semantic Layer is an API-first engine that transforms declarative YAML model definitions into optimized SQL for Postgres, Snowflake, ClickHouse, Dremio, and Databricks. It provides a unified abstraction over your data warehouse, so analysts and applications can query using business concepts (dimensions, measures, metrics) instead of raw SQL. Every capability — model loading, validation, query compilation, and diagram generation — is exposed through a REST API and an MCP server, making OrionBelt easy to integrate into any application, workflow, or AI assistant.

The payment protocol for people and agents. One MCP server, any payment rail. Multi-provider routing (Woovi/Pix, Stripe, Belvo), spending guardrails, human-in-the-loop confirmation, and audit logging.

MCP server for [1ly.store](https://1ly.store) — Enable AI agents to discover, pay for, and sell APIs using crypto.

Ultra-fast to deploy agentic-first mcp-ready semantic layer. Let your data be like water. Bonnard is a CLI for building and deploying semantic layers. Define metrics and dimensions in YAML, deploy a governed MCP server, and serve AI agents and BI tools. Supports Snowflake, BigQuery, Databricks, PostgreSQL, and more. Ships with native integrations for Claude Code, Cursor, and Codex. GitHub: https://github.com/meal-inc/bonnard-cli Docs: https://docs.bonnard.dev/docs/ npm: https://www.npmjs.com/package/@bonnard/cli

Memory with integrity for AI coding agents. SAME tracks provenance, flags stale knowledge, and surfaces contradictions; so your AI trusts what's current, not what's outdated. 17 MCP tools: semantic search, cross-vault federation, session handoffs, decision logging, knowledge graph, trust-aware retrieval, consolidation, health analysis. Provenance on every write. Stale notes rank lower automatically. SQLite + vector search. Ollama, OpenAI, LM Studio, or keyword-only. One 12MB Go binary. No cloud, no API keys, no telemetry. Your notes never leave your machine. Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and any MCP client.

ShellGuard is an MCP server that lets LLM agents securely SSH into remote Linux hosts with read-only shell access. Instead of copy-pasting terminal output, your AI can run safe diagnostics, inspect logs, query systems, and troubleshoot production, staging, or dev environments autonomously. All commands are parsed, validated against a strict allowlist, and executed with timeouts and output limits—blocking destructive operations while guiding the LLM to safe alternatives.

mcp-probe-kit is a protocol-level toolkit designed for developers who want AI to truly understand their project's intent. It's not just a collection of 21 tools—it's a context-aware system that helps AI agents grasp what you're building.

Check if any domain supports Universal Commerce Protocol (UCP). Returns verification status, manifest version, capabilities, response latency, and AI bot access policies (GPTBot, ClaudeBot, Google-Extended). Enables agent-to-tool compatibility for agentic commerce workflows.

An enterprise-grade Oracle Database connector for MCP. Features built-in self-healing connection retries, TypeScript-based architecture, and AI-guided SQL error handling for autonomous agent workflows.

Turn messy text into clean output fast—GUI for humans, MCP tools for AI IDEs (Cursor/Claude). 33+ deterministic text utilities.

The Databox MCP server empowers your AI tools to talk to your data, enabling agentic analytics, automated data ingestion, and real-time conversational analytics. It transforms Databox into an intelligent backend for your LLMs, allowing tools like ChatGPT, Claude and Cursor to query metrics and KPIs across 130+ platforms using natural language with zero SQL required. Unlike standard read-only connectors, this server supports bidirectional workflows: your agents can autonomously ingest structured or unstructured data and trigger real-time decisions based on your business performance.

Turn Claude or Cursor into your personal AI Financial Analyst. FinancialData.Net API provides end-of-day and intraday stock market data, company financial statements, key financial ratios and metrics, insider and institutional trading data, sustainability data, earnings releases, and much more. Over 20 years of historical data is available, including information on 17,000+ stocks, 20,000+ funds, 3,000+ ETFs, 13,000+ OTC securities, and 200,000+ derivatives.

Agentic Long Term Memory based on a proprietary pattern engine. Faster recall than vector databases and more deterministic.

MCP server that enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.

Pantheon-MCP enables agents to match each task with a tailored instructions set (agent definition) automatically.

Agentic assistant that handles the complexity while you focus on results. With MCP support and advanced Orchestrator/Agent capabilities, BB connects to hundreds of external data sources & tools and breaks down complex tasks for maximum efficiency.

A short summary of what the server does. Example: Modular agentic AI workflows for dataset cleaning and orchestration.

A remote-hosted and fully-controllable browser for your AI agent.

A powerful, intelligent shell assistant powered by local AI models through Ollama. Shell AI brings advanced AI capabilities directly to your terminal, enabling natural language interaction with your file system, shell commands, and development workflow.

Remote browser instances for your AI agents. Reliably complete any browser-based task at scale. Fully-control agentic browsers that spin up in seconds.

Model Context Protocol server for kwrds.ai keyword research and SEO tools.

Intelligent Data Analysis & Reporting Agent

AgenticMaid is a Python library designed to interact with one or more Multi-Capability Protocol (MCP) servers.

Demo application showcasing how to build and secure MCP servers and clients with Pomerium using contextual access policies.

Atlassian (Jira/Confluence) AI Agent powered by 1st Party MCP Server using OpenAPI Codegen, LangGraph and LangChain MCP Adapters. Agent is exposed on various agent transport protocols (AGNTCY ACP, Google A2A, MCP Server)

a light weight version of mcp sdk inspired by official model context protocol sdk, NOW focus on sse only no stdio

ArgoCD AI Agent powered by 1st Party MCP Server using OpenAPI Codegen, LangGraph and LangChain MCP Adapters. Agent is exposed on various agent transport protocols (AGNTCY ACP, Google A2A, MCP Server)

AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.

The unified MCP server platform for production AI agents. Enterprise-grade authentication, monitoring, and deployment in minutes.

rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7

Official AI SDK by Ampersand

A Telegram MCP Server designed for agentic applications to manage and interact with Telegram efficiently

This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite AI coding assistant to vibe-code Strands Agents.

A Model Context Protocol (MCP) server implementation that exposes Pearl's AI and Expert services through a standardized interface

MCP server example for Agentic AI demo

OpenAPI to MCP Server Code Generator

MCP Gateway and Registry

Model Context Protocol server for Anbani

MCP server empowering AI assistants with real-world capabilities: Gmail, Calendar, Tasks, Git integration, and note management. Bridges AI assistants to external services through standardized protocol with secure authentication.

Django MCP Server is a Django extensions to easily enable AI Agents to interact with Django Apps through the Model Context Protocol it works equally well on WSGI and ASGI

This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, CrewAI, RAG, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama

DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.

DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.

DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns. DevContext leverages sophisticated retrieval methods, focusing on keyword analysis, relationship graphs, and structured metadata to deliver highly relevant context during development, understanding both your conversations and your codebase at a deeper level. The server operates with a database instance dedicated to a single project, eliminating cross-project complexity and ensuring performance with minimal resource requirements. DevContext builds a comprehensive understanding of your codebase - from repository structure down to individual functions - while continuously learning from and adapting to your development patterns.

This project demonstrates how to build a minimal MCP server using the `mcp` Python SDK and connect it to Claude Desktop as a client. It simulates a simple Travel Desk system with tools to submit, view, and track employee travel requests — all accessible directly from Claude's interface.

Cline MCP Server - Internal workflow orchestration for agentic tasks

A FastAPI application that integrates with Telegram using webhooks and OpenAI Agents SDK for AI-powered stock trading assistance, utilizing MCPHub for multiple MCP server management.

Agent network builder for communicating with openapi apis. Based in autogen

Pixelize the real world on-chain

MCP server to empower your agent with enterprise-grade Gemini integration for codebase analysis, live search, text/PDF/image processing, and more on your favorite MCP clients.

Build AI Agents MCP-based

MCP server to query clinicaltrial.gov to identify mutation specific trials

This repository provides an implementation of a Model Context Protocol (MCP) server for AWS S3, enabling AI models, particularly Large Language Models (LLMs), to securely interact with S3 buckets. The server offers a standardized interface to list S3 buckets, list objects within buckets, and download file contents.

MCP server that execute applescript giving you full control of your Mac

Repository creates or uses various MCP Servers to integrate with Agentic Frameworks and Microsoft Copilot Studio

MCP Agent Graph (MAG) is an agent development framework for rapidly building agent systems. This project is based on graphs, nodes, and MCP to quickly construct complex Agent systems.

MCP for Root Signals Evaluation Platform

Basic remote SSE MCP server for Tavily Search.

Dremio MCP server

Preference Editor MCP server

Branch-Thinking MCP Tool A TypeScript-powered MCP server for managing parallel branches of thought, semantic cross-references, and persistent tasks. Features dynamic scoring, AI-generated insights, batch operations, and visual graph navigation for advanced agentic workflows.

Autoapprove support for claude

An MCP server that runs AI-driven venture capitalist agents (Fred Wilson, Peter Thiel, etc.), whose thinking is continuously enriched by Octagon Private Markets' real-time deals, valuations, and deep research intelligence. Use it to spin up programmable "VC brains" for pitch feedback, diligence simulations, term sheet negotiations, and more.

Digimon Engine — Multi-Agent, Multi-Player Framework for AI-Native Games and Agentic Metaverse

AI agent that controls computer with OS-level tools, MCP compatible, works with any model

A security scanner for your LLM agentic workflows

Japanese Vocab Anki MCP Server

An innovative Model Context Protocol hub that seamlessly connects your client with intelligent agents, enabling powerful cross-platform communication across multiple MCP ecosystems

SentinelCore is an advanced AI agent powered by Model Context Protocol. It can browse the web, interact with local file systems, and is designed to keep evolving with new features. Whether you're looking for a smart assistant, a system manager, or a knowledge guide, SentinelCore adapts to your needs seamlessly.

A minimal agentic app to interact with OLLAMA models leveraging multiple MCP server tools using BeeAI framework.

Containerized versions of hundreds of MCP servers 📡 🧠

A RAG-ready MCP server for semantic PDF search with OCR, FAISS, and transformers—plug into any MCP client and retrieve intelligent answers within your MCP client.

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independently (via SSE or STDIO), offering modularity and cloud-deployable execut

An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for authorized cybersecurity research workflows.

API de gerenciamento de tarefas via WebSocket com execução modular de comandos e suporte a ferramentas, desenvolvida em TypeScript com banco SQLite. Projetada para integração com agentes de inteligência artificial.

Instead of dumping 1000+ tools into a model’s prompt and expecting it to choose wisely, the Unified MCP Tool Graph equips your LLM with structure, clarity, and relevance. It fixes tool confusion, prevents infinite loops, and enables modular, intelligent agent workflows.

About This repository features a collection of agentic AI projects across various domains, showcasing practical applications of AI agents with different frameworks, techniques, and tools.

An MCP ( Model Context Protocol ) Server for Grafana Tempo

A TypeScript library that enables AI agents to leverage MCP (Model Context Protocol) servers for enhanced capabilities. This library integrates with the AI SDK to provide a seamless way to connect to MCP servers and use their tools in AI-powered applications.

🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS Bedrock, and Ollama.

An MCP ( Model Context Protocol ) Server for Grafana Loki