Agent Card

The JSON document an A2A agent publishes, usually at /.well-known/agent-card.json, describing its identity, skills, service endpoint and the authentication schemes it accepts. It can be signed with JWS over a canonicalised form, so a client can check that the card is untampered and comes from the claimed provider 1. A peer allow-list admits only registered agents with verified cards.

Developed in
ch. 23, Multi-agent systems and delegation chains
Chapters
ch. 23, AI Agents
Source
1 numbered reference, listed below

Where it is used

One chapter of the Body of Knowledge uses the term. Each link opens the first section that does.

Sources

  1. [1] Agent2Agent (A2A) Protocol Specification, v1.0 (v1.0.0 released 2026-03-12 and v1.0.1 on 2026-05-28 in github.com/a2aproject/A2A; Agent Card at /.well-known/agent-card.json, signed with JWS over JCS-canonicalised JSON; servers authenticate every request; authorisation implementation-specific; scope and revocation of in-task authorisation not defined). A2A Project (Linux Foundation). 2026-05-28. https://a2a-protocol.org/latest/specification/ (verified: primary)

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Agent Card. In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/agent-card. CC BY 4.0

BibTeX

@misc{aige2026agentcard,
  author  = {Jorge García Aibar},
  title   = {{Agent Card}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/agent-card}
}