IntentWeb Applications and Real-Time agent manifest AI agents web discovery JSON AgentManifest defines a JSON document that websites can publish to describe identity, trusted knowledge, agent-facing capabilities, structured bindings, risk levels, consent requirements, authentication expectations, audit rules, and policies. The goal is to help AI agents understand what a website knows and what it can safely do before scraping, guessing from visual UI, or executing brittle browser automation. Note to Readers This document is an experimental individual Internet-Draft proposal for discussion. It is not an RFC and is not an IETF-approved standard. Source material for this draft is maintained in the AgentManifest repository. The draft is expected to change based on implementation feedback and standards discussion.

Introduction AgentManifest is an experimental open specification. Implementers are encouraged to test the draft, report interoperability issues, and propose improvements. The key words MUST, MUST NOT, REQUIRED, SHALL, SHALL NOT, SHOULD, SHOULD NOT, RECOMMENDED, MAY, and OPTIONAL in this document are to be interpreted as described in and when, and only when, they appear in all capitals, as shown here.

Overview An AgentManifest document declares:

• the manifest version and status,
• the website or organization identity,
• the platform and integration mode,
• discovery locations for the manifest and related resources,
• trusted knowledge sources,
• capabilities with type, risk, consent, state-change, binding, and audit metadata, and
• policy expectations for consent, authentication, data minimization, and audit.

Capabilities describe what a website can do and under which policy. Structured bindings describe how that capability can be accessed or executed, such as through HTML, static resources, HTTP, OpenAPI , MCP , or hosted checkout. OpenAPI operations and MCP tools are binding targets, not the whole capability contract. AgentManifest is vendor-neutral. Implementation frameworks can generate manifests and bindings, but the manifest does not require any specific generator or expose implementation ownership as a normative field.

Discovery Agents SHOULD attempt static discovery at /.well-known/agent.json. Publishers MAY also expose /.well-known/agent-manifest.json, /agent-manifest.json, or an HTML discovery hint: ]]> If no manifest is found, agents SHOULD continue normal web behavior and SHOULD NOT infer that unsupported actions are safe.

Schema The canonical JSON Schema for the repository version of this draft is: The schema uses JSON Schema Draft 2020-12 and keeps additionalProperties: true for forward-compatible experimentation. A conforming manifest for this draft uses the agentManifestVersion value 0.1-draft.

Risk and Consent Capabilities declare a risk level of low, medium, high, or critical. Low-risk capabilities are public and read-only. Medium-risk capabilities submit data or start a workflow. High-risk capabilities modify user or business state. Critical capabilities include payments, orders, legal commitments, destructive actions, or irreversible operations. High and critical actions MUST require explicit confirmation and audit. Critical actions MUST set stateChange to true, requiresConsent to true, and consentMode to explicit, step_up, or human_review. AgentManifest declares authentication, authorization, consent, audit, and policy expectations. Protocol endpoints are responsible for enforcement. Consent must be specific to a capability invocation and must not be treated as broad permanent authorization. Critical actions should use appropriate authentication, explicit confirmation, audit, replay protection, and duplicate transaction controls.

Security Considerations Manifests and related public files MUST NOT expose secrets, private tokens, unpublished data, private customer information, admin-only endpoints, or privileged internal operations. Servers MUST enforce authorization, consent, validation, replay protection, duplicate transaction controls, and policy checks outside prompt text. Prompt instructions are not a security boundary.

Privacy Considerations Publishers should minimize disclosed and collected data. Knowledge sources should include only information intended for public agent use. State-changing actions should collect only fields required for the declared capability. Agents should provide user-visible summaries for submitted data and should avoid logging sensitive user information unless required for audit, compliance, or fraud prevention.

IANA Considerations This document makes no IANA registration request. The media type application/agent-manifest+json is proposed for discussion only and is not registered by this document.

Normative References JSON Schema Informative References OpenAPI Initiative Model Context Protocol