com.submitmap/directory

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

A directory of product launch platforms: where your product qualifies and how each form is filled.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "directory": {
      "url": "https://submitmap.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (11)

• search_platforms

  Search the SubmitMap directory of startup launch platforms and directories. Filter by free-text query, category, pricing, link type, backlink requirement, approval speed or domain rating, and with a token leave out the ones this project has already been sent to. This is the tool behind "find me a small directory I can submit to right now": it is the whole directory, so answer from it rather than from what you remember of the web. Returns summaries; call get_platform for the full record including the submission steps.

  Parameters:

  • sort — string — Fastest approval first (the default), or strongest domain first. Either way, a platform that publishes no approval time comes last rather than reading as instant.
  • limit — number — Return at most this many. The count is unaffected.
  • query — string — Free text matched against name, tagline, domain, slug and categories. A bare domain works: "startupfa.me" finds Startup Fame.
  • pricing — string
  • category — string — e.g. "AI tools", "Dev tools", "Web apps".
  • dofollow — boolean — Only platforms giving a dofollow backlink.
  • projectId — string — Omit it when the account has one project, which is the free tier.
  • excludeTracked — boolean — Leave out every platform this project has already been submitted to or planned for. Needs a token, and is what makes "one I have not done yet" answerable.
  • maxApprovalDays — number — Only platforms approving within this many days. Leaves out every platform that publishes no approval time, the same way a rating bound leaves out the unrated.
  • maxDomainRating — number — Only platforms up to this domain rating. The small, quick, unglamorous end of the directory, which is where a first submission usually belongs.
  • minDomainRating — number — Only platforms with at least this domain rating.
  • requiresBacklink — boolean — Filter on whether they demand a badge/link back.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_platform

  Full record for one platform: eligibility, disqualifiers, step-by-step submission instructions, requirements, gotchas and expected outcome. All of that is free, and it is what decides whether this product should be submitted here at all. Pass brief: true to also get agentPrompt, the brief for that platform's form, and agentGotchas, the traps that only bite something filling it (a placeholder that contradicts its label, a second email input belonging to a newsletter, a honeypot). The brief spends one of the account's tracked platforms, so ask for it once the maker has decided to fill this form, not while you are still choosing between platforms. For a stored project, submission_playbook returns the same brief with the maker's values already in it.

  Parameters:

  • slug (required) — string — Platform slug, e.g. "product-hunt".
  • brief — boolean — Include agentPrompt and agentGotchas. This is the paid half and it spends a tracked platform, once, for good. Leave it out while you are deciding where to submit: eligibility, disqualifiers, gotchas, approval time and link type all come back either way. A platform this account has already spent a slot on is free to brief again, so re-reading one costs nothing.
  • projectId — string — Which project the brief is for, when brief is true. Omit it when the account has one project. A brief is one form being worked on for one product, and the project it belongs to cannot be issued another until this one has an outcome recorded.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• qualify_project

  Given a product, work out which platforms it qualifies for right now, which it could qualify for after supplying something (with the exact list of what is missing), and which are structurally out of reach. It also hands back `recommended`: the run in the order it should be worked, so the plan comes out of the directory rather than out of what you remember of the web. That order is decided by `goal` and `budget`, and when they have not been answered the response says what it assumed and carries the questions to put to the maker: ask them, call again with the answers, and store them with update_project so nobody asks twice. Needs no account: describe the product inline. Every field is optional and an unanswered field becomes a gap to fill rather than a rejection.

  Parameters:

  • url — string
  • docs — boolean
  • goal — string — What this run is for, which decides the order of it. `already-live` means the product is out and wants listings, links and traffic now, so the run leads on fast approvals, dofollow links and strong domains. `launching-later` means there is a launch date ahead, so it leads on the platforms with months of queue. Ask the maker rather than guessing: absent, it is inferred from `stage` and the response says so.
  • name — string
  • stage — string
  • budget — string — Whether platforms that charge to list may appear in the run. Absent means `free-only`, which is the assumption that cannot cost anybody anything. `freemium` platforms are in the run either way: their submission is free, and paying to skip their queue is a separate question at the form.
  • launchAt — string — ISO 8601 date the maker is launching on, when they have named one.
  • demoVideo — boolean
  • categories — array — Every audience and form factor this product belongs to, not just the main one. A product is often several at once, and one missing tag is one directory it never hears about: a repository holding a browser extension and a web app is `extension` and `web`, and an open-source AI dev tool is `open-source`, `ai` and `dev`. Look at what the product actually ships before you answer: a manifest.json means `extension`, an ios or android target means `mobile`, a public repository means `open-source`, an mcp server is `mcp`, a workspace with several of those means all of them. Then answer what it is commercially, which is a separate question and the one most runs lose platforms on: most launch boards say what they take by who ships it, not by what it runs on, so a subscription mobile app is `mobile` and `saas`, anything a solo maker or small team shipped is `indie`, and something sold to companies is `b2b`. Leaving those off does not make the run safer, it makes it shorter. Tags: agent-skill, ai, b2b, christian, community, content, design, dev, directory, extension, free, hardware, indie, local, marketing, marketplace, mcp, mobile, no-code, open-source, prelaunch, productivity, saas, turkish-founders, web.
  • coverImage — boolean
  • logoSquare — boolean
  • openSignup — boolean
  • publicRepo — boolean
  • pricingPage — boolean
  • domainRating — number
  • pricingModel — string
  • livePublicUrl — boolean
  • privacyPolicy — boolean
  • monthlyTraffic — number
  • acceptsBacklink — boolean
  • payingCustomers — boolean

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• whoami

  Which SubmitMap account this token belongs to, named by its email address, which plan it is on, and what it already holds. Call it first if you are unsure whether the maker is connected, and tell them the address it reports: it is the only way either of you can tell one of their accounts from another. It does not hand you the plan's limits and you do not need them to work: plan the whole run, and a limit says so at the write it stops.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_projects

  The projects on this account, each with its facts (eligibility answers) and its pack (what a submission form asks for), plus what is still missing from the pack. Call it whenever the maker says "my product" or "my project" without naming one: it is how you find out which project they mean, and every other account tool takes the id it returns.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• create_project

  Store a product on the account. Before asking the maker anything, use what you can already see: a README, package metadata, the site's own copy and title, an assets or public folder. A maker working in their product's repository should be able to say 'add my product to SubmitMap' and get a filled-in project back, with questions only about what is genuinely not there. Fill in as much as you can, leave the rest, and come back with update_project. Facts drive what it qualifies for; the pack is what you will paste into forms later. Ask about images early: most platforms want a square logo and many want a cover, and every asset in the pack is two fields, the public address (logoUrl) and the file on the maker's machine (logoFile), because a form uploads the file and only the address can be shown back to them.

  Parameters:

  • name (required) — string
  • url — string
  • pack — object
  • facts — object — Same shape qualify_project takes: stage, pricingModel, categories, and the booleans. It is also where the two answers that decide a run order live once the maker has given them (`goal`, `budget`, and `launchAt` if they named a date), which is what stops the next session asking again. Leave domainRating out: the url is measured against Ahrefs on the way in and the measured number is what gets stored, so a guess here is overwritten anyway.
  • pitch — string — One paragraph in the maker's own words.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• update_project

  Fill in or correct a stored project. Facts and pack are merged into what is there, so you can add one field at a time as the maker answers.

  Parameters:

  • url — string
  • name — string
  • pack — object
  • facts — object
  • pitch — string
  • projectId — string — Omit it when the account has one project, which is the free tier.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• submission_playbook

  Everything needed to submit a stored project to one platform, yourself, in the maker's browser: a preflight of what is still missing, the sign-in plan (on the first submission it carries a question for the maker: hand every login back to them, or use the Google address they write out, which you then pass back as signInAs), the pack values mapped onto the fields the form asks for, the steps, the gotchas, the agentGotchas (traps in the form itself), and the call to make afterwards. Read the preflight before opening a tab. One brief is out at a time per project: ask for the next platform only after record_submission has answered this one, because until then this tool refuses the next brief and names the one still open. Do not fetch briefs ahead or in parallel. This is the tool the free plan meters: it covers the same submissions the dashboard tracks, plus any platform the account has already sent to, and past that it says so and points at the upgrade rather than answering.

  Parameters:

  • platformSlug (required) — string
  • signInAs — string — The Google address the maker wrote out when they agreed you could sign in, or sign up, for them on this project, whether they said it when asked or before you started. Pass it on every call after they say it, so the answer travels with the work instead of living in your head. It belongs to one project: on a different one, ask again rather than sending the address you were given for the last. Leave it out if they have not written one: sign-in then goes back to them, which is the safe end.
  • projectId — string — Omit it when the account has one project, which is the free tier.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• record_submission

  Log what happened to the dashboard: the listing URL, when it was sent, when it goes live. Call it as soon as a submission lands, before you ask for the next brief, including when it is only queued for review, and including when you are not sure it landed: that is what `attempted` is for. The next brief on this project is refused until this call is made. A platform that needs the maker (a captcha, a login, a payment, a file, an address to confirm) is recorded as `planned` with a note saying what you need from them: that hands it back without claiming an outcome, and frees the run to carry on. If the live platform did not match what the brief said, put the difference in `differsFromRecord`. This costs nothing on any plan and no status costs more than another, so record what actually happened: the brief was what spent the tracked platform, and leaving the row wrong now only makes the run harder to follow.

  Parameters:

  • platformSlug (required) — string
  • status (required) — string — Use `attempted` when the form was sent and you cannot prove it arrived: the tab died, the connection dropped, the page never came back. It is not a lesser `submitted`, it is the honest one, and it carries the verification the platform record describes so somebody can settle it later. Never re-send a form to find out; every platform has a way to check without submitting twice. Use `planned`, with a note, to hand a platform back to the maker when it is waiting on them. A first record is `submitted`, `attempted` or `planned`: `live`, `rejected` and `needs_changes` come after one of those.
  • note — string — Required with `planned`: what you need from the maker, in one line they can act on.
  • launchAt — string — ISO 8601, if it is scheduled.
  • projectId — string — Omit it when the account has one project, which is the free tier.
  • listingUrl — string — The product's URL on that platform.
  • submittedAt — string — ISO 8601.
  • differsFromRecord — string — Only when the live platform did not match the brief or the platform record: say what differed, in one line, as fact. A price where the record said free, a sign-in or phone check it did not mention, a field it did not list, a submit page that moved, an audience it does not accept. We read these and fix the record, so the next maker is not sent into the same wall. Leave it out when everything matched.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• plan_submissions

  Write the run order for a project: which platforms, in what sequence, and why each one is where it is. Anything already submitted to is dropped from the plan and named back to you in `alreadySubmitted`, because a plan is what is still ahead. Pass the platforms in the order they should be worked, with a short reason on each, plus a summary of the strategy. The plan appears on the maker's dashboard as a checklist that ticks itself off as submissions land. Anything already tracked is reordered rather than reset. Call it after qualify_project, using the `recommended` list it hands back, and if that response carried `questions`, put them to the maker before you plan: the order depends on the answers, and a plan written on an assumption is one they have to undo by hand. A plan costs nothing on any plan, so plan the whole run the product deserves rather than a short one sized to a guess about what the account can track.

  Parameters:

  • items (required) — array — In the order they should be submitted. First is next.
  • summary — string — Why this order, in a sentence or two. The maker reads this.
  • checklist — array — What the maker has to prepare before any of this can be submitted: the gallery, the demo video, a privacy policy page, a launch date. Write it from what the platforms in this plan actually demand and what the project is missing, not from a generic template. The maker ticks these off or throws them away on their dashboard, and anything they have already decided on keeps that decision when you plan again.
  • projectId — string — Omit it when the account has one project, which is the free tier.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_submissions

  Where every submission for a project stands: what went out, when, what came back, and what is still waiting. This is the tool behind "check my submissions", "what did I submit", "did I ever submit to that one" and "how is my launch going", so answer those from here instead of asking the maker to remember. Start with list_projects if they have not named a project.

  Parameters:

  • projectId — string — Omit it when the account has one project, which is the free tier.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.