Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Noonlaunch is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
Launch a product on Noonlaunch, search its directory and weekly winners, and find 333 launch sites.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http noonlaunch-mcp https://noonlaunch.com/mcp
# 2 — ask your agent for something these tools do
# search-directory, get-product, get-weekly-winners and 7 more
Noonlaunch costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NOAll 1 server
noonlaunch1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http noonlaunch-mcp https://noonlaunch.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search the Noonlaunch product directory. Returns approved products matching the query, ordered by community votes, with links to their Noonlaunch product pages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Search term matched against product names, taglines and descriptions. |
| category | string | no | Optional category slug or name to narrow results. |
| limit | integer | no | Max results to return (1-25, default 10). |
Get full public details of one Noonlaunch product by its slug (the last part of its noonlaunch.com/product/... URL).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | no | The product slug, e.g. "my-product" for noonlaunch.com/product/my-product. |
Get the Noonlaunch launch board for a week: the top-voted free launches, with the top 3 marked as winners. weeks_ago 0 is the current (still running) week, 1 is the last completed week.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| weeks_ago | integer | no | How many weeks back (0 = current running week, 1 = last completed week, default 1, max 52). |
Browse Noonlaunch's curated list of 333 startup launch directories and communities where founders can submit a product. Filterable by category, cost and minimum domain authority.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by directory category, e.g. "AI", "SaaS", "General". |
| free_only | boolean | no | Only directories that are free to submit to. |
| min_da | integer | no | Minimum domain authority (0-100). |
| limit | integer | no | Max results (1-100, default 50). |
What it costs to launch on Noonlaunch, and what each plan includes. Use this to answer a pricing question on its own. To actually submit a product, call check_product instead: which plans apply depends on the site, because relaunching one that is already listed needs a paid plan.
No parameter schema on file.
Check whether a product can be submitted to Noonlaunch, and get the plans, categories and launch weeks available for it. Always call this first, and always ask the person for their live public website URL rather than guessing it from their code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| website_url | string | no | The live public URL of the product, as given by the person. Never a localhost or development address. |
Submit a product to Noonlaunch. Nothing is published by this call. It returns a claim link to give the person straight away, and for free launches the badge snippet to install. Call check_product first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| website_url | string | no | The live public URL the person confirmed. Never guess this from the codebase. |
| name | string | no | Product name, 2-100 characters. |
| tagline | string | no | One line shown on the board, 10-70 characters. |
| description | string | no | What the product does, 30-600 characters. Longer text is rejected, not trimmed. |
| category | string | no | Category id or slug from check_product. |
| plan | string | no | One of: free, bundle_featured, bundle_spotlight. Ask the person which they want. |
| launch_week | string | no | Optional launch week as a Monday date (YYYY-MM-DD) from check_product. Defaults to the next open week. |
| logo_url | string | no | Optional public URL of the product logo image, which we download. |
| twitter_handle | string | no | Optional X handle, with or without the @. |
Check that the Noonlaunch badge is installed on the product site and publish the listing if it is. Only for free launches, and only after the person has deployed the change. Paid listings are published by payment instead, so use check_status for those.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| submission_token | string | no | The submission_token returned by submit_product. |
Where a submission stands: whether it has been claimed, paid for, verified and published. This is the only way to find out whether a payment has landed. Poll it rather than assuming.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| submission_token | string | no | The submission_token returned by submit_product. |
Report that the badge check is wrong: the badge is installed and visible but we cannot find it. Only use this after verify_badge has failed twice and you have confirmed the badge really is live on the page. A person reviews it within 24 hours.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| submission_token | string | no | The submission_token returned by submit_product. |
| message | string | no | Where the badge is on the page and what you have already checked, so a human can resolve it without asking. 20-1500 characters. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Noonlaunch or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 2.0.0 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 3 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest029bb261d98ff0d94ceefcfa20c9052a2a5a2bc53da74a2cdce8737f6a88d392
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search-directory | no tags | |
| get-product | no tags | |
| get-weekly-winners | no tags | |
| list-launch-directories | untrusted-input | untrusted-input: keyword "browse" |
| get-plans | no tags | |
| check-product | no tags | |
| submit-product | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| verify-badge | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| check-status | no tags | |
| report-badge-problem | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest029bb261d98ff0d9
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 2.0.0.
2.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Noonlaunch can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.