{
  "markdown": "# AT Directory\n\n**Where agents discover OP-verified merchants on the rails Bitcoin and Tether actually use.**\n\nAT Directory indexes merchants that sell products, services, APIs, or content and accept Lightning, BOLT12, L402, or USDT (any chain), with trust attestations issued through [Observer Protocol](https://observerprotocol.org). It is the verified, agent-callable layer on top of the fragmented agent-payment landscape. It is **not** in the payment path — agents discover here and pay merchants directly.\n\n- **MCP server** (primary product) — `@agenticterminal/mcp-server`, hosted at `mcp.agenticterminal.ai`.\n- **Web directory** — [agenticterminal.ai](https://agenticterminal.ai), same data rendered for humans.\n- **SKILL.md** — teaches an agent how to query and complete payment handoff.\n\n## Status\n\nPre-v1, active build. Target: week of 2026-05-18 for a live Tether-meeting demo. v1 ships Tiers 1–2.\n\n## Use it from an agent\n\n```jsonc\n// Hosted (recommended, no install)\n{ \"mcpServers\": { \"at-directory\": { \"url\": \"https://mcp.agenticterminal.ai/mcp\" } } }\n```\n\n```bash\nnpm install -g @agenticterminal/mcp-server   # local alternative\n```\n\nSix tools: `search_merchants`, `get_merchant`, `verify_payment_endpoint`, `list_categories`, `list_rails`, `whoami`. Reads are ungated — anonymous agents see all tiers and can transact with no setup. An Observer Protocol `DirectoryAccessCredential` raises rate limits and unlocks write access (reviews), but is not required to discover or transact. Full reference: [agenticterminal.ai/api-docs](https://agenticterminal.ai/api-docs).\n\n## Repo layout\n\n```\ndata/merchants/         One JSON file per merchant (the source of truth).\ndata/schema/            JSON Schema (Draft 2020-12) for merchant records.\ndata/categories.json    Category taxonomy.\ndata/rails.json         Supported rails + USDT chains.\ndata/LOGO-AUDIT.md      Logo sourcing checklist.\npackages/core/          Types, schema-validated load, search/filter.\npackages/mcp-server/    stdio + hosted HTTP MCP server, rail verification.\npackages/skill/         SKILL.md (canonical).\napps/web/               Next.js static directory + Netlify Functions.\ndeploy/mcp-server/      Dockerfile, systemd unit, DEPLOY runbook.\nscripts/                Data validation (and one-time crawl tooling).\n```\n\n## Development\n\n```bash\npnpm install\npnpm -r test          # core + mcp-server unit/integration tests\npnpm -r typecheck\npnpm validate-data    # schema-validate every merchant record\npnpm -F @at-directory/web dev          # web at localhost:3000\npnpm -F @agenticterminal/mcp-server start:stdio   # MCP over stdio\n```\n\nLocal MCP with the mock verifier (until the real AT route lands):\n\n```bash\npnpm -F @agenticterminal/mcp-server exec tsx src/dev/mock-verifier.ts &\nAT_VERIFIER_URL=http://127.0.0.1:8787 \\\n  pnpm -F @agenticterminal/mcp-server start:stdio\n```\n\n## Data model\n\nEvery merchant carries two **orthogonal** signals — read both:\n\n- **OP trust tier** (the merchant): 1 self-attested · 2 operator-verified. v1 Tier 2 = AT operator transacted and confirmed; the bilateral counterparty-attestation model lands in v1.x.\n- **Agent-callable tier** (the integration): `full-api` · `structured-handoff` · `human-checkout`.\n\n**The trust tier gates nothing.** Reads are ungated, every tier is visible to anonymous agents, and\nan agent can transact with a Tier 1 merchant with no setup. The tier is evidence for a caller to\nweigh, not a decision this directory has made on its behalf. Nothing is refused on the basis of it.\n\nSchema is enforced in CI (`pnpm validate-data`) and on every load. USDT rails require a `chain`; Tier 2+ non-integrated records require an `op_attestation_url`; an `op_trust_tier` of `3` is rejected on ingest, which is why the model above stops at 2.\n\n## Contributing\n\nSee [CONTRIBUTING.md](./CONTRIBUTING.md). Merchants can self-register at [agenticterminal.ai/submit](https://agenticterminal.ai/submit) — submissions open a PR for review and land at Tier 1 until verified.\n\n## Documents\n\n- [Scope](../AT-Directory-v1-Scope.md) — positioning, inclusion criteria, definition of done.\n- [Spec](../AT-Directory-v1-Spec.md) — implementation contract.\n\n## License\n\nMIT.\n",
  "bytes": 4187,
  "sha": "92d5e8dceb4f4edfdb81c83da271c88119cd5d93dd96e6a36923581903d239ec",
  "repo_slug": "observer-protocol/at-directory",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_agenticterminal_directory_708d2352/readme"
}