Skip to content

Learn

Learn MCP and AI agents, one track at a time

Short guides in reading order. Each one explains one idea in plain words, shows it in L2M, and most link to something you can run.

Start here

  1. GuideWhat is MCP?

    MCP explained: hosts, clients and servers, the tools, resources and prompts a server offers, how a tool call travels, and a runnable agent to try.

  2. GuideWhat is an AI agent?

    An AI agent is a model in a loop that calls tools until it can answer. See the loop step by step, where it fails, and run one locally with no API key.

  3. RecipeBuild an MCP agent with no API key in 5 minutes

    Import a ready MCP agent that runs on a fresh L2M install with a built-in echo model and a mock MCP server, then swap in a real model and server.

  4. GuidePrompt injection

    Direct and indirect prompt injection explained with agent examples, why filters alone fail, and the layered defenses OWASP and recent research recommend.

  5. GuideRegression testing agents

    Catch a prompt, model or tool change that breaks your agent before users do: save known-good runs, replay changes against recordings, gate CI.

Tracks

  1. MCP fundamentals

    Beginner6 guides · about 52 min

    What MCP is, its host, client and server roles, tools, resources and prompts, the transports, OAuth for remote servers, and tool annotations.

    1. What is MCP?MCP explained: hosts, clients and servers, the tools, resources and prompts a server offers, how a tool call travels, and a runnable agent to try.
    2. Hosts, clients and serversThe three MCP roles in plain terms: what the host app, each client connection and each server own, local vs remote servers, and where credentials live.
    3. Tools, resources and promptsWhen an MCP server should offer a tool, a resource or a prompt, who decides each is used, and what output schemas, tool errors and elicitation add.
    4. MCP transportsHow MCP messages travel: stdio for local servers, Streamable HTTP for remote ones, sessions, Origin checks, and what the stateless 2026-07-28 spec changes.
    5. MCP authorizationHow a remote MCP server asks for OAuth: the 401 challenge, resource metadata, PKCE, the resource parameter, and why tokens must never be passed through.
    6. MCP tool annotationsWhat readOnlyHint, destructiveHint, idempotentHint and openWorldHint mean, why the spec calls them untrusted, and how to use them in tool rules safely.
    Start the track: MCP fundamentals
  2. How AI agents work

    Beginner6 guides · about 53 min

    The tool-calling loop, when a fixed workflow beats an agent, supervisor and worker agents, memory, long tool lists and human approval.

    1. What is an AI agent?An AI agent is a model in a loop that calls tools until it can answer. See the loop step by step, where it fails, and run one locally with no API key.
    2. Workflows vs agentsFixed workflows and model-driven agents compared: cost, control and testability, the common patterns between them, and how to mix both in one graph.
    3. Supervisor and workersHow a supervisor agent delegates to worker agents exposed as tools: when it helps, what it costs, how to test it, and a sample that runs with no API key.
    4. Agent memoryShort-term history, session memory and cached tool results: what each is for, how much to keep, and how agent memory meets retention and erasure.
    5. Too many toolsWhy long MCP tool lists hurt agents (context, wrong picks, cost), and practical fixes: shortlisting, toolsets, per-agent servers and rules that hide tools.
    6. Human in the loopWhere a person belongs in an agent's path: before risky tool calls, on a draft, or as a question. Which actions need it, timeouts, and approval fatigue.
    Start the track: How AI agents work
  3. Agent security

    Intermediate6 guides · about 56 min

    Prompt injection, the OWASP Top 10 for LLM apps, the lethal trifecta, MCP risks, least privilege, and keeping personal data out of prompts.

    1. Prompt injectionDirect and indirect prompt injection explained with agent examples, why filters alone fail, and the layered defenses OWASP and recent research recommend.
    2. OWASP Top 10 for LLM appsThe ten OWASP LLM risks for 2025, one by one, with what each looks like in an agent that calls tools and a concrete control for each one.
    3. The lethal trifectaWhy an agent with private data, untrusted content and a way to send data out is one prompt injection from a leak, and how to break the combination.
    4. MCP security risksThe main MCP security risks from the spec and OWASP: tool poisoning, rug pulls, shadowing, confused deputy, token passthrough, SSRF and their controls.
    5. Least privilege for agentsWhy AI agents drift to more access than they need, the layers to narrow (servers, tools, arguments, data, people, keys) and how to keep them narrow.
    6. Sensitive data in promptsWhere personal data and secrets leak in an AI app (prompts, tool arguments, logs, answers) and how masking, tokens and a controlled reveal contain them.
    Start the track: Agent security
  4. Testing and shipping agents

    Intermediate4 guides · about 34 min

    Evals, regression tests built from recorded runs, testing MCP tool calls, and release gates that ship only what passed.

    1. Agent evalsWhat an agent eval is: tasks, trials, graders and transcripts, capability vs regression evals, pass@k vs pass^k, and how to write your first 20 cases.
    2. Regression testing agentsCatch a prompt, model or tool change that breaks your agent before users do: save known-good runs, replay changes against recordings, gate CI.
    3. Testing MCP toolsWhy live MCP calls make agent tests flaky, and what recorded replays, schema-built mocks and breaking-change checks each catch and miss.
    4. Release gatesA release gate lets a workflow version reach production only after its tests pass on that exact version. How gates, drafts, overrides and rollback work.
    Start the track: Testing and shipping agents
  5. Running AI in production

    Intermediate6 guides · about 45 min

    LLM and MCP gateways, cost caps, self-hosting, retention and erasure, audit trails, and identity: SSO, MFA, roles and keys.

    1. LLM gateway vs MCP gatewayAn LLM gateway sits between apps and models; an MCP gateway sits between agents and tools. What each controls, where they overlap, and when you need both.
    2. LLM and agent cost controlWhy agent costs run away (loops, long tool lists), where to put spend and token budgets (user, project, client), warn vs block, and estimating usage.
    3. Self-hosting AI agentsWhat a self-hosted agent platform runs (API, workers, database, models), the trade-offs against hosted tools, and a checklist for a first production setup.
    4. Data retention and erasureWhere an AI app keeps personal data, how retention purges it, how to answer access and erasure requests, and how legal holds stop deletion.
    5. Audit trails for agentsWhat an agent audit trail should record (inputs, tool calls, approvals, versions), how a signed run manifest proves it is intact, and offline checks.
    6. Identity for AI platformsWho may build, run, approve and call agents: single sign-on with OIDC or SAML, MFA per role, project roles, service accounts and scoped API keys.
    Start the track: Running AI in production

Try it and look things up

  • Live demo

    The real studio with recorded runs, in your browser. No install, no sign-up.

  • Recipes

    Working workflows to download and import, with a diagram of every node.

  • Glossary

    Short, plain definitions of the terms the guides use.

This website (not the L2M product) uses Google Analytics, only after you accept cookies. Cookie settings