Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Status: Informative in full.
A202 is verifiable commerce for agent-to-agent or agent-led transactions: an open specification of commercial authority, negotiation state, and verifiable conformance for transactions between independent organisations, including transactions conducted on their behalf by software agents.
It defines typed objects for delegated commercial authority, a state machine for the transaction and for each bilateral session inside it, rules for what may be disclosed to whom, and an executable conformance suite that turns each of those into a check an implementation either passes or fails.
The full statement of purpose, scope, and non-goals is in CHARTER.md.
Created and developed by A. A. Musse. See MAINTAINERS.md.
Pre-release.
v0.1 working documents, not a tagged release of the set. See RELEASES.md.202 is HTTP 202 Accepted, which A202-0017 makes the status an accepted submission returns, because acceptance is the primitive the rest of the specification is built on. The A202- reason-code prefix, the A202-NNNN proposal identifiers, and the a202-commercial/0.1 specification version string all follow from the name.$id values resolve under https://schemas.a202.org. Fixture hosts use reserved .invalid names, because test data must never resolve.| Path | Contents |
|---|---|
CHARTER.md | Purpose, scope, non-goals, design principles |
GOVERNANCE.md | How the project is run, and what the sponsor does and does not control |
MAINTAINERS.md | Who maintains this repository |
CONTRIBUTING.md | Contribution status, and the terms a contribution is accepted under |
SECURITY.md | Private coordinated disclosure |
THREAT-MODEL.md | Adversaries assumed, properties defended, and what is deliberately not defended |
CODE_OF_CONDUCT.md | Expected conduct |
TRADEMARK.md | The A202 name, and what use of it is and is not permitted |
RELEASES.md | Versioning, what a release consists of, compatibility policy |
CHANGELOG.md | What changed, and where the release notes required by RELEASES.md accumulate |
.github/ | Review routing, the pull request and issue forms, and the workflow that runs the suite on every change |
proposals/ | The A202 change proposal process |
schemas/ | Canonical commercial model, transaction profile extension model, and the JSON schemas |
authority/ | Commercial mandate: delegated authority, constraints, delegation, approval, revocation |
discovery/ | Counterparty invitation: how an unregistered party enters one named transaction |
negotiation/ | Transaction and session state machines, and auction event semantics |
conformance/ | Fixtures, manifest, normative runner, and the conformance grade definitions |
Each specification document carries a status header stating which of its sections are normative and which are informative.
The runner validates every fixture named in the manifest against the schemas, then applies the invariants that JSON Schema cannot express. Schema validity is not conformance, which is the reason the runner exists.
It needs jsonschema>=4.18. If that is not on the system interpreter, a virtual environment is enough:
Run it from the repository root:
The expected result is every fixture passing and none failing, with the totals the manifest carries: the manifest is the single source for the count, and the runner prints it on every run. The runner also asserts that each negative fixture is refused for the reason code the manifest declares for it, wherever the normative layer raises codes at all. Run it before and after any schema change.
Every negative fixture is minimal: removing the single offending element must leave a document that validates cleanly. A negative fixture that fails for an incidental reason tests nothing, so verify that when adding one.
The suite does not depend on anyone remembering to run it. It runs, together with the reference implementation tests and the MCP server tests, on every pull request and on every push to the default branch, under .github/workflows/checks.yml. GOVERNANCE.md section 3.4 requires the suite to pass for any change to schemas, fixtures, the manifest, or the runner, and that workflow is what turns the requirement into a gate.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/a202)<a href="https://allmcps.com/mcp/a202"><img src="https://allmcps.com/api/badge/a202?style=directory" alt="A202 on AllMCPs" /></a>