Thin MCP server for GrowthBook — skill loader + authenticated API passthrough
Nothing to run from here
droppage 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.
96/100
trust score
13
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
droppage gives your AI agent a publish button. When it builds an HTML report, dashboard or prototype, it publishes it to a live link on droppage.dev, and you decide who can open it.
- Public, private (only you), or email-gated for named people, who each get an invitation with an access link (Builder)
- Replace the HTML behind the same link (Starter and Builder), or set a page to expire
- Local images and videos in the HTML are uploaded with the page
- List your pages with their unique views, and check your plan's quota before you hit a limit
Sign-in: run droppage login once in a terminal. It emails you a magic link, and a Free account is enough. There is no login tool, because stdin belongs to the protocol: signed out, the tools tell your agent to ask you to sign in. Nobody is ever asked for a key or token.
Safe by default:
- No password mode over MCP, so a password never lands in an agent transcript. Run droppage upload <file> --password yourself for a password page.
- update_page, delete_page, set_page_expiry, remove_recipient and delete_media are marked destructive, so your client asks before running them.
- Hosted images and videos are public to anyone with their URL, even on a gated page.
- Any client you add this server to can publish, change and delete pages as you. Add it only to agents you trust.
Plans: Free (5 pages, 100 views a month, public or private pages). Starter, $4/mo, adds passwords and updates in place. Builder, $12/mo, adds email-gated pages. Details: https://droppage.dev/#pricing
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user droppage-mcp '--' npx -y droppage mcp
# 2 — ask your agent for something these tools do
# publish_page, update_page, list_pages and 11 more
droppage costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts droppage as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user droppage-mcp '--' npx -y droppage mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: 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 your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
14 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Publish an HTML file as a NEW live link and return its URL. Use update_page to change an existing page instead.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access | string | yes | public: anyone with the link (only when the user says so). email: only emails (Builder plan). private: only the owner. |
| emails | array | no | Who can open an email page; each is emailed an invitation with an access link. Only with access "email". |
| invite | boolean | no | Email page only: false publishes without emailing the invitations (send them later with invite_recipients). Default true. |
| expires | string | no | Delete the page after 30m, 12h, 7d, 2w, or on a date like 2026-12-31. |
Replace the HTML behind an existing page. The URL and access settings stay; new local images and videos are uploaded and ones the page no longer uses are deleted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
| expires | string | no | Also set the expiry: 30m, 12h, 7d, 2w, a date, or "never". |
The user's pages, newest first: url, access_mode, allowed_emails, view_count (unique visitors), last_viewed_at, expires_at.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| preview | boolean | no | Also return a temporary preview_url per page that does not count as a view. |
Delete a page for good: its link stops working and its images and videos are deleted. Confirm with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
Set or clear when a page (and its images and videos) is deleted for good, without re-uploading it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
| when | string | yes | 30m, 12h, 7d, 2w, a date like 2026-12-31, or "never". |
The plan, what it allows, and current usage. usage.level "warn" means at least 80% used; "limit" means writes may pause. Existing links stay live.
No parameter schema on file.
Who can open an email page, with their invitation status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
| page | integer | no | Result page, from 1. |
Give more people access to an email page; each new one is emailed an invitation with an access link.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
| emails | array | yes | — |
Email an invitation to everyone on an email page who has not had one yet, e.g. after publish_page with invite: false. People already invited are skipped.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
Take away one person's access to an email page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The page slug (the last part of its URL). |
| string | yes | — |
Upload image or video files to one of the user's pages and return their URLs, for files the HTML did not reference at publish time. PNG, JPEG, GIF, WebP, AVIF, SVG up to 4 MB; MP4, WebM up to 20 MB. Hosted media is public to anyone with its URL, even on a gated page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | string | yes | The page slug the files belong to; they are deleted with it. |
| paths | array | yes | Image or video file paths (absolute, or relative to where the server runs). |
The user's hosted images and videos; with page, only that page's and its media budget.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | string | no | — |
Delete one hosted image or video by id or URL. It stops being served within 5 minutes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id_or_url | string | yes | — |
Send an idea, bug report, review, or other feedback to the droppage team. It is always marked as coming from an agent; include your model name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | yes | — |
| kind | string | no | — |
| model | string | no | Your model name. |
| contact | string | no | A reply-to email, only if the user wants one. |
| rating | integer | no | 1-5, only with kind "review". |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- 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 droppage 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: —
ATrust score 96 / 100
Release 0.5.1 · scanned 8 Nov 2026
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 score99
Client score96
Findings2 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest076fa00a8bb35b1a26caef0b7f21d1f2ed447f6a101496ff33ca7590a5bac122
Score vectorthreat 99 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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 |
|---|---|---|
| publish_page | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| update_page | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| list_pages | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| delete_page | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| set_page_expiry | no tags | |
| get_quota | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_recipients | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| add_recipients | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| invite_recipients | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| remove_recipient | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| upload_media | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_media | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| delete_media | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| send_feedback | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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 digest076fa00a8bb35b1a
Scanned2026-11-08
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.5.1. Pin a release below and the command asks for exactly that one.
0.5.1
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 droppage 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.