Deploy to Agents SDK

MCP serverCloud & infra

Get a distribution plan for your AI agent that is based on real findings rather than guesswork. This app audits the surfaces where AI agents are distributed, then turns the results into an evidence-based distribution plan.

Available today. Use it from your connected AI after setup.

After adding it, ask your AI to audit your agent's distribution surfaces and build the plan from what it finds.

Then ask your AI: use the audit app tool from Deploy to Agents SDK

What your AI can do with it

  • Audit the surfaces where AI agents are distributed
  • Map the places where your agent could be distributed
  • Create a distribution plan grounded in the audit findings
  • Support each part of the plan with evidence from the audit

From the project's README

As published by saezbaldo/deploytoagents in README.md.

Public JavaScript client and registry metadata for the Deploy to Agents remote MCP server.

The 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.

Agent-first CLI

npx deploytoagents login
npx deploytoagents whoami
npx deploytoagents portfolio --json
npx deploytoagents discovery --json
npx deploytoagents discovery-record --input observation.json --json
npx deploytoagents audit https://example.com --json

The 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.

{
  "hostname": "example.com",
  "surface": "claude",
  "model": "model label shown by the surface",
  "prompt": "Exact generic, unbranded prompt",
  "outcome": "not-mentioned",
  "freshSession": true,
  "responseExcerpt": "Optional relevant excerpt",
  "citations": ["https://example.org/source"]
}

Valid outcomes are recommended, mentioned, not-mentioned, and error. The server verifies that the signed-in organization owns the target hostname.

Deploy 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.

Connect directly through MCP

Use this Streamable HTTP endpoint in any compatible MCP client:

https://deploytoagents.com/mcp

Available tools:

  • audit_app
  • get_audit_result
  • create_distribution_plan
  • get_customer_zero_evidence

JavaScript client

npm install deploytoagents
import { DeployToAgentsClient } from "deploytoagents";

const client = new DeployToAgentsClient();

try {
  const queued = await client.auditApp("https://example.com");
  console.log(queued.receipt_url);

  const result = await client.getAuditResult(queued.audit_id);
  if (result.status === "completed") {
    console.log(await client.createDistributionPlan(queued.audit_id));
  }
} finally {
  await client.close();
}

Python client

pip install deploytoagents
from deploytoagents import DeployToAgentsClient

async with DeployToAgentsClient() as client:
    queued = await client.audit_app("https://example.com")
    print(queued["receipt_url"])

Customer Zero

Deploy to Agents uses its own system as its first customer. The current 100/100 receipt verifies technical surfaces only. Independent, unbranded discovery remains explicitly not-yet-proven.

Development

npm install
npm test
npm run smoke

Evidence policy

This 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.

License

MIT

Tools it offers (4)

What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • audit_app
  • get_audit_result
  • create_distribution_plan
  • get_customer_zero_evidence

Signals

Last commit
Jul 2026
Advanced
Delivery
server MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
com-deploytoagents-server
Source
github.com/saezbaldo/deploytoagents
Hosted endpoint
https://deploytoagents.com/mcp