Which problem does each protocol solve?
These names describe different pieces of a system. The examples show possible roles, not verified support in a particular product.
| Name | Connects | Illustrative use |
|---|---|---|
| MCP | An AI application to tools and context | Read issues through a GitHub connector |
| A2A | Independent agents to one another | Delegate a task to another agent |
| Agent Skills | An agent to reusable task instructions | Load a team's release-review procedure |
| WebMCP | An agent to actions exposed by a website | Use a site's structured search action |
What is MCP?
Model Context Protocol lets AI applications connect to tools and contextual resources exposed by servers. A client chooses what it supports and how permissions work. The published 28 July 2026 specification changes the request model and develops extensions and authorization; support must still be checked in each implementation.
A coding assistant reads an issue through an MCP server, then proposes a patch. The connector supplies access; it does not prove the patch is correct.
Ask before choosing: Which client, server and protocol version were tested? What can the connection read or change?
What is A2A, and how is it different from MCP?
Agent2Agent is a protocol for agents to discover one another and exchange tasks, messages and artifacts. Its Agent Card describes a provider's capabilities and connection details. MCP gives an application tools and context; A2A gives independent agents a way to communicate. Neither guarantees that a delegated task succeeds.
A planning agent asks a separate research agent for a report. That researcher might use MCP tools while doing the work, then return an artifact through A2A.
Ask before choosing: Is communication authenticated, and can you inspect what the other agent did before accepting its result?
Sources: A2A specification
What are Agent Skills?
Agent Skills packages reusable instructions with optional references, assets and scripts. The open format uses a SKILL.md file. Clients can load a short description first and detailed instructions when needed, a pattern called progressive disclosure. A skill can tell an agent how to use an MCP tool.
A release-review skill supplies your checklist and report format; an MCP connection supplies the repository information needed to follow it.
Ask before choosing: Who maintains the skill, does it include executable scripts, and which permissions or dependencies does it require?
Sources: Agent Skills specification · Agent Skills overview
What is WebMCP?
WebMCP lets a website expose structured actions to visiting agents. Chrome describes declarative form integration and imperative JavaScript APIs. This is different from an external MCP server or clicking a screenshot. The 27 October 2026 Community Group draft is not a W3C Standard; implementations are still developing.
A travel site could expose a search action with named date and destination fields. This is an illustrative design, not a claim about a particular live site.
Ask before choosing: Which browser and agent support it today? What happens if the action is unavailable or the visitor declines it?
Sources: WebMCP draft · 27 October 2026 · Chrome WebMCP early preview
What is an agent harness?
The harness is the surrounding software that gives a model tools, context, an execution environment and a way to continue working. It helps turn model output into a working process. Harness design includes feedback and recovery; a model's benchmark result does not describe the whole system.
A coding harness can edit files, run checks, read the failure and attempt a correction. The same model in a simple chat box does not have that entire workflow.
Ask before choosing: Can the agent recover from failures, stop at a limit, and show evidence of what changed?
Sources: OpenAI: harness engineering
What does context engineering mean?
Context engineering means selecting and maintaining the instructions, tools, history and retrieved information available to a model. It goes beyond wording one prompt. The context window is finite: too much irrelevant or stale material can make the task harder. The cited foundational article was published in 2025, not invented this year.
For a support reply, provide the current refund policy and the relevant order facts, rather than an entire document archive and every past conversation.
Ask before choosing: Where does the information come from, when was it updated, and is this user allowed to access it?
What is RAG, and what is agentic retrieval?
Retrieval-augmented generation supplies retrieved information to a model when it answers. Retrieval can use document search, a database or other sources; it is not synonymous with a vector database. With agentic retrieval, the agent decides when to search, what to request and whether another search is needed.
A research agent finds an announcement, notices a missing pricing detail and performs another search before answering. More searches alone do not make the answer better.
Ask before choosing: Can you trace the answer to the retrieved evidence and reproduce a failure on a fixed test case?
Is agent memory the same as context or RAG?
Memory is information retained for later use, such as thread state or facts stored across sessions. Context is what the model can see for its current work. Retrieval can bring stored memories into that context. Saving a fact does not itself update the model's weights or guarantee accurate recall.
An assistant stores a preference for concise reports, then retrieves it for a later session. A correction or deletion needs to reach the stored record too.
Ask before choosing: What persists, who can read it, can you correct or delete it, and does it cross user or workspace boundaries?
Sources: LangChain: memory concepts
What are agent evaluations, or evals?
Evals check whether an agent behaves as intended on representative tasks. Offline evaluation compares versions on prepared cases; online evaluation examines production behavior. Test the actions and final environment state when they matter, not just a plausible final answer. A published benchmark cannot settle performance on your own workflow.
A booking test checks the saved date, budget and approval record. A confident message saying the booking succeeded is insufficient if the underlying record is wrong.
Ask before choosing: Which real tasks and failure cases were tested, and what did the checks actually measure?
Sources: LangChain: evaluation types · LangChain: evaluating agent runs · 15 October 2026
How is observability different from evaluation?
Observability records what happened during a run, such as model requests, tool calls and errors. Evaluation judges whether the behavior met the task's requirements. A trace can help explain a failure without proving quality. OpenTelemetry's GenAI conventions remain active work; inspect the current version before relying on particular fields.
A trace reveals that a tool timed out. An evaluation shows whether the agent handled that timeout correctly and avoided falsely claiming success.
Ask before choosing: Can you inspect useful traces without retaining unnecessary personal information or secrets?
What should agent guardrails actually protect?
Guardrails are controls that limit or check access and actions. OWASP's agentic risk list covers issues including tool misuse, privilege problems and memory poisoning. An agent can produce a useful answer while taking an unauthorized action, so permissions, validation and consequential-action approval need their own checks.
An assistant drafts a refund but needs an authorized person to approve issuing it. A free-text promise to be careful is weaker evidence than an enforced permission boundary.
Ask before choosing: What can the agent change, which actions require confirmation, and how can you stop or recover a failed run?
What is a computer-use agent?
A computer-use agent interacts with application interfaces using information such as screenshots, the DOM or accessibility tree. It differs from calling a purpose-built API. Clear controls and stable layouts help interaction, but interface access alone does not establish reliable task completion or appropriate permissions.
An assistant navigates a web form that has no integration. It still needs to identify the correct fields, handle errors and stop before a consequential submission when approval is required.
Ask before choosing: Does the complete workflow survive an error, a changed layout and the required approval step?
Sources: web.dev: agent-friendly site UX
Two different protocols called ACP.
ACP has two distinct meanings here. Agent Client Protocol connects coding agents and editors; its docs say full remote support remains work in progress. Agentic Commerce Protocol concerns commerce between agents, buyers and businesses. Neither name implies compatibility with the other, and protocol implementation alone does not secure platform distribution.
Sources: Agent Client Protocol introduction · Agentic Commerce Protocol
What about world models and new announcements?
World models can represent or simulate environments. DeepMind's 27 October 2026 Genie 4 announcement describes interactive world simulation as a trusted-tester research preview. Treat a research preview, a public beta and a generally available product as different stages; an announcement does not establish availability or reliability for your task.
Sources: DeepMind: Genie 4 research preview · 27 October 2026
Turn terminology into a useful choice.
Use this editorial checklist for your own workflow. It is not a vendor certification.
- Define one task, its input and what a successful result would change or produce.
- Check the exact product, client, version and release stage against primary documentation.
- Inspect permissions, data destinations, retention and approval for consequential actions.
- Try a representative case, an error case and an ambiguous request in an isolated environment.
- Record actual outputs, actions, limits and total operating costs before expanding use.
Protocol support is a starting point. The useful evidence is whether a specific version completes your task, within your permissions and budget, with failures you can detect and recover from.
AI-assisted drafting and primary-source review by Agent Search Engine. Read our editorial method, report a correction, or read this guide as Markdown.
More practical guides
Everyday AI / Decision guide
How to choose an AI tool for your everyday work
Choose AI tools by the job, setup, data, language and total cost. Compare two candidates with a free worksheet and practical tests, without coding.
Read the guide
Everyday AI / Decision guide
How to research and learn with AI without losing the sources
A practical AI research workflow: define a question, collect sources, verify citations and separate evidence from inference. Includes a worked source-checking exercise.
Read the guideEveryday AI / Decision guide
How to write with AI and keep control of the final draft
Use AI for emails, summaries and first drafts with a clear brief, a fact ledger and a review checklist. Includes practical prompts and a fictional before-and-after exercise.
Read the guide