{
  "markdown": "# Deploy to Agents SDK\n\nPublic JavaScript client and registry metadata for the [Deploy to Agents](https://deploytoagents.com) remote MCP server.\n\nThe remote server is published in the official MCP Registry as `com.deploytoagents/server` and is served from `https://deploytoagents.com/mcp`. The JavaScript client and authenticated agent-first CLI are published as `deploytoagents@0.4.1` on npm, with an equivalent `deploytoagents==0.1.1` client on PyPI.\n\n## Agent-first CLI\n\n```bash\nnpx deploytoagents login\nnpx deploytoagents whoami\nnpx deploytoagents portfolio --json\nnpx deploytoagents discovery --json\nnpx deploytoagents discovery-record --input observation.json --json\nnpx deploytoagents audit https://example.com --json\n```\n\nThe package installs both `deploytoagents` and the shorter `d2a` command. Google login uses Authorization Code with PKCE and a temporary loopback callback. On Windows the refresh credential is encrypted for the current OS user with DPAPI; CI can provide a short-lived identity token through `DEPLOYTOAGENTS_TOKEN`. Discovery Lab can be read or supplied with a JSON observation file (or stdin via `--input -`). All command results and errors have stable JSON forms for agent use.\n\n```json\n{\n  \"hostname\": \"example.com\",\n  \"surface\": \"claude\",\n  \"model\": \"model label shown by the surface\",\n  \"prompt\": \"Exact generic, unbranded prompt\",\n  \"outcome\": \"not-mentioned\",\n  \"freshSession\": true,\n  \"responseExcerpt\": \"Optional relevant excerpt\",\n  \"citations\": [\"https://example.org/source\"]\n}\n```\n\nValid outcomes are `recommended`, `mentioned`, `not-mentioned`, and `error`. The server verifies that the signed-in organization owns the target hostname.\n\nDeploy to Agents currently audits public agent-facing surfaces, returns unlisted evidence receipts, and creates prioritized technical and external-authority distribution plans. It does **not** yet claim to publish every customer artifact or guarantee recommendation by any model.\n\n## Connect directly through MCP\n\nUse this Streamable HTTP endpoint in any compatible MCP client:\n\n```text\nhttps://deploytoagents.com/mcp\n```\n\nAvailable tools:\n\n- `audit_app`\n- `get_audit_result`\n- `create_distribution_plan`\n- `get_customer_zero_evidence`\n\n## JavaScript client\n\n```bash\nnpm install deploytoagents\n```\n\n```js\nimport { DeployToAgentsClient } from \"deploytoagents\";\n\nconst client = new DeployToAgentsClient();\n\ntry {\n  const queued = await client.auditApp(\"https://example.com\");\n  console.log(queued.receipt_url);\n\n  const result = await client.getAuditResult(queued.audit_id);\n  if (result.status === \"completed\") {\n    console.log(await client.createDistributionPlan(queued.audit_id));\n  }\n} finally {\n  await client.close();\n}\n```\n\n## Python client\n\n```bash\npip install deploytoagents\n```\n\n```python\nfrom deploytoagents import DeployToAgentsClient\n\nasync with DeployToAgentsClient() as client:\n    queued = await client.audit_app(\"https://example.com\")\n    print(queued[\"receipt_url\"])\n```\n\n## Customer Zero\n\nDeploy to Agents uses its own system as its first customer. The current [100/100 receipt](https://deploytoagents.com/audits/89db3fa0-d7d8-4201-97fd-790727586a14) verifies technical surfaces only. Independent, unbranded discovery remains explicitly `not-yet-proven`.\n\n## Development\n\n```bash\nnpm install\nnpm test\nnpm run smoke\n```\n\n## Evidence policy\n\nThis project distinguishes owned evidence, externally verified artifacts, and independent recommendations. It does not create fake testimonials, automated community posts, coordinated votes, or links intended primarily to manipulate rankings.\n\n## License\n\nMIT\n",
  "bytes": 3597,
  "sha": "a6bbd7476f13f88462e6db078a38061a1a5f5a85d5a9945a1aff96fb84b636e6",
  "repo_slug": "saezbaldo/deploytoagents",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_deploytoagents_server_5d3a6148/readme"
}