.

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

March 26, 2025 · Dublin

agents.txt

Explore how the MCP protocol enables Business‑to‑Agent APIs, addressing discovery challenges and proposing an open, marketplace‑free method for publishing and locating endpoints.

Overview
Links
Tech stack
  • MCP protocol
    MCP (Model Context Protocol) is the open standard, introduced by Anthropic in November 2024, that enables Large Language Models (LLMs) to securely access and interact with external systems and real-time data.
    The Model Context Protocol (MCP) is an open-source standard designed to solve the 'N×M' data integration problem for AI agents: it replaces custom connectors with a single, universal interface. Developed by Anthropic and released in November 2024, MCP standardizes secure, two-way communication between an LLM application (the MCP client) and external data sources or tools (the MCP server). This architecture allows models to move beyond static training data, enabling real-time actions like querying a Postgres database or sending a Slack message via a structured JSON-RPC 2.0 transport layer. Major industry players, including OpenAI and Google DeepMind, have already adopted the protocol, with official SDKs available in languages like Python and TypeScript to accelerate ecosystem development.
  • Anthropic
    Anthropic is a frontier AI safety and research company, developing the Claude family of large language models (LLMs) via its Constitutional AI framework.
    Anthropic is an AI safety and research company, founded in 2021 by former OpenAI executives Dario and Daniela Amodei, and structured as a Public Benefit Corporation (PBC) . The core mission is building reliable, steerable AI systems, with a focus on interpretability and long-term alignment . Its flagship product is the Claude family of LLMs, which are highly capable models designed for complex reasoning and coding tasks . A key technical innovation is Constitutional AI (CAI), a training method that aligns the models with a set of ethical principles to ensure helpful, harmless, and honest outputs . The company has secured significant backing, including up to $4 billion from Amazon and a $2 billion commitment from Google .
  • AGENTS
    Autonomous software entities using large language models to reason, select tools, and execute complex workflows independently.
    Agents shift the focus from conversation to execution: they use frameworks like LangGraph or CrewAI to break down complex objectives into actionable tasks. These systems leverage external tools (Tavily for search, GitHub for code, or Salesforce for CRM) to operate across digital environments. Current benchmarks show agents can automate up to 80% of routine knowledge work by managing their own reasoning loops. These entities deliver finished outputs (validated data, resolved tickets, or deployed software) with minimal human intervention.

Related projects