Let Agents In

Agent readiness · Domain registration and DNS

openprovider.com

4 of 9 measurable points under formula 9.57, measured on 2026-09-03. 16 checks exist; each is one HTTP request with a published rule, so every sentence below can be rerun and argued with. 2 of them could not be measured from where we ask, and those are left out of the denominator rather than counted as failures.

A · Discovery

  • PASS
    Answers an agent user-agentAnswered 200 to LetAgentsIn/1.0 (+https://letagentsin.com/bot)
  • N/A
    Price or entry condition in the search snippetNot applicable: we found no pricing page and no signup page of theirs, so there is no price for a search result to carry
  • FAIL
    llms.txt publishedNo llms.txt at any of the 5 locations probed: https://www.openprovider.com/llms.txt, https://www.openprovider.com/llms-full.txt, https://docs.openprovider.com/llms.txt, https://developer.openprovider.com/llms.txt, https://developer.openprovider.com/llms-full.txt
  • PASS
    Docs readable without JavaScript2,539 characters of text without JS
  • PASS
    On-demand agents not blockedExplicitly allowed: ChatGPT-User, Claude-User, Perplexity-User
  • N/A
    Paths robots.txt points at answerrobots.txt names no concrete path, only patterns or nothing, so there is no claim to check
  • PASS
    No punishing crawl delayNo Crawl-delay applies to the agents we check

B · Agent entry

  • UNMEASURED
    Agent entry pointUnmeasurable: 4 of the 10 agent entry paths we asked on your site answered with a refusal rather than a file or a 404, and 1 more never answered us at all, which is our own timeout rather than anything you did, so what you publish there is not something we measuredLet ordinary HTTP reach these paths and this becomes measurable.
  • N/A
    OAuth dynamic client registrationNot applicable: we found no pricing page and no signup page of theirs, so there is no client for an agent to registerIf you do issue tokens, publish /.well-known/oauth-authorization-server on the host that issues them and we will rescan.
  • FAIL
    MCP surfaceNo MCP surface: nothing spoke MCP at mcp.openprovider.com, mcp.openprovider.com/mcp, mcp.openprovider.com/v1/mcp, api.openprovider.com/mcp, api.openprovider.com/v1/mcp, /mcp or /api/mcp, and any address you publish in the MCP registry, and no file mentions MCP

C · Registration

  • N/A
    No CAPTCHA in the signup HTMLNot applicable: we found no pricing page and no signup page of theirs, so there is no gate to measureIf accounts are created somewhere else, tell us where and we will rescan.
  • N/A
    Signup reachable without a browserNot applicable: we found no pricing page and no signup page of theirsA product with no accounts cannot fail this. If yours has them elsewhere, point us at the page.

D · Provisioning

  • FAIL
    Programmatic key provisioningNone of the 7 provisioning phrases appears in the 4 documentation pages we read, including https://developer.openprovider.com/api-keys.html
  • N/A
    Free tier or no-card trial stated in textNot applicable: we found no pricing page and no signup page of theirs, so there is no tier to stateIf there is a paid tier, link its pricing from your home page and we will rescan.

E · Integration

  • UNMEASURED
    Typed SDK on the registryUnmeasurable: we could not identify the package a developer installs to use you, from your site, your docs or a registry searchName your package once in your docs, or link it from your repository, and we stop guessing. If your product is not something a developer installs, this check does not apply to you: unmeasured is out of the score and out of the denominator, so it costs you nothing.
  • FAIL
    Machine-readable API descriptionNo OpenAPI spec at the 5 usual paths on your site or on your documentation host, none declared by https://developer.openprovider.com, and no markdown negotiationPoint at your spec from your docs page with rel="service-desc" and an agent finds it without guessing.

Tell me when this changes

The failures here are the kind nobody notices. An edge rule that starts refusing agents changes nothing a person sees in a browser, so the first sign is usually an integration that quietly stopped working. We rescan weekly and write only when a verdict moves.

Free while we are building this, and we will ask before it ever costs anything. No card, no account, and one link in every email that stops it.

The address and the domain are the only things you give us. We keep them with what the watch needs to run: when it was created and confirmed, when it was last checked, and the score it was last compared against. Who holds it and how to have it deleted.

This page is the newest scan we hold for openprovider.com and changes when we rescan. It is not a judgement of the product: we measure whether an unattended run can get through, not whether the thing is any good. The whole corpus is published as JSON and CSV.

If a line here is wrong, rescan it first, because most of what we get told is already fixed and the page is only as new as the last scan. If it is still wrong after that, write to hello@letagentsin.com with the check and what you see instead. A verdict we cannot reproduce comes down, and the rule that produced it gets fixed for everybody rather than only for you.

Scan a domain yourself