[Glossary](/glossary) · [Agents and protocols](/glossary/area/agents-and-protocols)

# A2A

Agent-to-Agent, a protocol for one agent to discover another's capabilities through an agent card and delegate tasks to it over HTTP.

## What A2A does not show

It standardises the handshake between agents, not what they may do; an agent card is a claim about capability that a caller still has to test.

## Where A2A comes up on this site

- [How an AI agent should verify a website before it acts](/guides/how-an-ai-agent-verifies-a-website-before-it-acts)A site declares itself in several places: agent manifests , robots.txt and its Content Signals, llms.txt, structured data, an A2A agent card, MCP listings.

## Terms this definition uses

[agent card](/glossary/agent-card)

## Definitions that name A2A

[A2A client](/glossary/a2a-client)

## Related terms in Agents and protocols

How autonomous agents plan, remember, call tools and talk to each other, including MCP and A2A, and where each step can go wrong.

[OpenSearch description](/glossary/opensearch-description) · [traceparent](/glossary/traceparent) · [JSON Schema](/glossary/json-schema) · [protected-resource metadata](/glossary/protected-resource-metadata) · [token audience](/glossary/token-audience) · [PKCE](/glossary/pkce) · [refresh token](/glossary/refresh-token) · [default scope request](/glossary/default-scope-request) · [tool poisoning](/glossary/tool-poisoning) · [tool lockfile](/glossary/tool-lockfile) · [MCP rug pull](/glossary/mcp-rug-pull) · [tool shadowing](/glossary/tool-shadowing) · [MCP preflight](/glossary/mcp-preflight) · [agent manifest](/glossary/agent-manifest) · [stapled verdict](/glossary/stapled-verdict) · [verdict over DNS](/glossary/verdict-over-dns) · [agentic web](/glossary/agentic-web) · [preflight](/glossary/preflight) · [decision receipt](/glossary/decision-receipt) · [receipt header](/glossary/receipt-header) · [action assurance](/glossary/action-assurance) · [resolve answer](/glossary/resolve-answer) · [freshness window](/glossary/freshness-window) · [AI agent](/glossary/ai-agent) · [Agent loop](/glossary/agent-loop) · [Planner](/glossary/planner) · [Executor](/glossary/executor) · [Agent memory](/glossary/agent-memory) · [Working memory](/glossary/working-memory) · [Long-term memory](/glossary/long-term-memory) · [Episodic memory](/glossary/episodic-memory) · [Semantic memory](/glossary/semantic-memory) · [Agent orchestration](/glossary/agent-orchestration) · [Multi-agent system](/glossary/multi-agent-system) · [Agent handoff](/glossary/agent-handoff) · [Delegation](/glossary/delegation) · [Tool result](/glossary/tool-result) · [Tool schema](/glossary/tool-schema) · [Tool description](/glossary/tool-description) · [Tool selection](/glossary/tool-selection) · [Tool permission](/glossary/tool-permission) · [Human-in-the-loop](/glossary/human-in-the-loop) · [Human-on-the-loop](/glossary/human-on-the-loop) · [Approval gate](/glossary/approval-gate) · [Agent sandbox](/glossary/agent-sandbox) · [Agent identity](/glossary/agent-identity) · [Agent authorization](/glossary/agent-authorization) · [Agent discovery](/glossary/agent-discovery) · [Capability negotiation](/glossary/capability-negotiation) · [MCP server](/glossary/mcp-server) · [MCP client](/glossary/mcp-client) · [MCP host](/glossary/mcp-host) · [MCP resource](/glossary/mcp-resource) · [MCP prompt](/glossary/mcp-prompt) · [MCP tool](/glossary/mcp-tool) · [MCP transport](/glossary/mcp-transport) · [JSON-RPC](/glossary/json-rpc) · [A2A protocol](/glossary/a2a-protocol) · [A2A client](/glossary/a2a-client) · [A2A server](/glossary/a2a-server) · [Agent skill](/glossary/agent-skill) · [Agent task](/glossary/agent-task) · [Agent artifact](/glossary/agent-artifact) · [WebMCP](/glossary/webmcp)

## Questions about A2A

### What is A2A?

Agent-to-Agent, a protocol for one agent to discover another's capabilities through an agent card and delegate tasks to it over HTTP.

### What does A2A not show or guarantee?

It standardises the handshake between agents, not what they may do; an agent card is a claim about capability that a caller still has to test.

### Which area of the glossary does A2A belong to?

Agents and protocols: How autonomous agents plan, remember, call tools and talk to each other, including MCP and A2A, and where each step can go wrong.

← [WebMCP](/glossary/webmcp)

[See it in the full glossary](/glossary/a2a) · 792 terms across 19 areas.

Free browser extension

See this on any site you visit, **in one click.**

CrawlCheck for Chrome grades every site you visit A–F and shows, from your own browser, what search engines and AI assistants are actually served. Free, no account.

[Add to Chrome — free](https://chromewebstore.google.com/detail/plgjengobhbdmbgckiiaaflgiepdbcpi?utm_source=crawlcheck.io&utm_medium=glossary)
[What it does](/extension)

Written by

[Emmanuel Orta](/author) · VSNARY

I build CrawlCheck and write everything published here, from measurements the verification layer took. Where a post got something wrong, the correction stays in the post.

[Every post, and where I got it wrong →](/author) · [Follow on LinkedIn →](https://www.linkedin.com/in/emmanuelorta)

We read your site the way crawlers do, from our own network, and every report says exactly what was asked for and what came back. [Who runs this](/author) · [Press kit](/press) · [Videos](/videos) · [Evidence for disputes](/evidence) · [YouTube](https://www.youtube.com/@crawlcheck) · [hello@crawlcheck.io](mailto:hello@crawlcheck.io)

#### How we measure, and our own machine files

CrawlCheck reads every site as itself. Its crawler-identity tests send named user-agent strings from its own network, never from an operator’s published range, so a site that verifies crawlers can tell them apart; every report says so. Results reflect what an anonymous non-browser client receives. [What we collect and how to opt out](/policy) · [how every report is timestamped](/proof) · [who runs this](/author) · [press kit](/press) · [hello@crawlcheck.io](mailto:hello@crawlcheck.io).

**Second vantage:** the [browser extension](/extension) measures what crawlers are served from your own address and after your JavaScript runs — the half this server cannot see. From 1.0.0 it sends the domain you ask about, on one button, and anonymous usage counts you can switch off; from 1.0.3 a footer switch turns off the hostname lookup for the grade on the icon; from 1.0.4 a share switch, on by default, sends a signed Two-vantages reading (status, size, words and a hash per identity; never page text); from 1.0.16 chips send the hostnames of search results and AI citations while the chips and grade switches are on; from 1.0.17 a readings switch, on by default, sends one signed page reading a day (numbers, the hostname and the page address with the query removed; never in incognito; at most 40 a day) and only while the share and grade switches are also on. Earlier versions send nothing.

**Our own machine layer for the agentic web:** [llms.txt](/llms.txt) · [llms-full.txt](/llms-full.txt) · [agents.md](/agents.md) · [SKILL.md](/SKILL.md) · [entitymap.json](/entitymap.json) · [media kit](/.well-known/media-kit.json) · [MCP server card](/.well-known/mcp/server-card.json) · [API catalog](/.well-known/api-catalog) · [OpenAPI](/openapi.json) · [robots.txt](/robots.txt) · [sitemap.xml](/sitemap.xml) · [security.txt](/.well-known/security.txt) — every one named in robots.txt, which is exactly what we check for on yours.

**Registry:** [MCP: Operator](/registry/mcp/operator) · [MCP](/registry/mcp) · [AI policy](/registry/aipolicy) · [infinitechoice.com](/registry/infinitechoice.com) · [nolawriting.com](/registry/nolawriting.com) · [vercel.com](/registry/vercel.com) · [Trade: Landscaping](/registry/trade/landscaping) | **Pages:** [IP ranges](/data/ip-ranges) · [Demo](/mcp/demo) | **Datasets:** [Kansas](/datasets/state/kansas) · [Technologies: Gatsby](/datasets/technologies/gatsby) · [Problems: Staging leak](/datasets/problems/staging-leak)

[Contact](/contact) · [Partnerships](/partnerships) · [Terms of service](/terms) · [Refund policy](/refunds) · [Trust center](/trust) · [Subprocessors](/subprocessors) · [Changelog](/changelog) · [Report an error](/report-error)
