Growwer MCP server
Growwer MCP server lets an MCP client operate a Growwer marketplace account in natural language, covering catalogue discovery, buying/selling sponsored articles and link additions, orders, wallets, and managed-service campaigns.
Start with setup/guide/vocabulary/account tools, including anonymous guide access.
Discover media: search/list catalogue and flash offers, view media details, manage favourites/discarded/requested media, and use saved filters.
Manage projects: create, edit, delete projects and save catalogue filters.
Buy orders: estimate, create, cancel, approve delivery, request draft/delivery changes, and download briefings/drafts.
Sell: register/edit/delete media, apply competitive fees, set holiday, accept/reject/deliver seller orders, handle update requests, and upload draft files.
Track money: read buyer/seller wallets, transactions, invoices, withdrawals, and download related documents.
Managed service: list/get campaigns and proposals, estimate/review proposals, and request managed-service campaigns or info.
Writes are scoped by read/write permission, use idempotent requestId, and guarded actions ask for confirmation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Growwer MCP server find tech media where I can buy a sponsored article under $300"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Growwer is a marketplace of sponsored articles and link additions on third-party media, for brands,
agencies and publishers. The MCP server exposes it to any MCP client, for buyers and for sellers, as
78 tools (39 that read, 39 that change something) and 6 prompts. One tool,
growwer_get_guide, answers questions about Growwer itself and works without signing in, and so do
the prompts.
The server is hosted. Most clients should connect to it directly:
https://tool.growwer.com/mcpThis repository holds the public metadata for that server plus a small stdio bridge
(@growwer/mcp) for hosts that can only launch a local process. It does not contain the
Growwer application source.
Connect
Clients that speak remote MCP (recommended)
No install, no local process. Sign in with OAuth, or paste an API key as a header.
Client | How |
Claude (web, Desktop, mobile) | Customize → Connectors → + Add → Add custom connector, name it Growwer, paste the URL, choose Continue and sign in. |
ChatGPT | Open chatgpt.com/plugins, choose the plus button → Add custom MCP server, name it Growwer, paste the URL and sign in. |
Claude Code |
|
Cursor | |
OpenAI Codex | |
VS Code | |
Gemini CLI |
Clients that can only spawn a local process
Hosts that only start a local process, such as Claude Desktop's manual configuration and older stdio-only clients, need a bridge. That is what this package is:
npx -y @growwer/mcp// claude_desktop_config.json
{
"mcpServers": {
"growwer": {
"command": "npx",
"args": ["-y", "@growwer/mcp"],
"env": { "GROWWER_API_KEY": "gw_sk_your_key" }
}
}
}The key goes through the environment rather than an argument, so it does not appear in ps output
and does not have to survive the host's argument splitting.
Related MCP server: byline
Authentication
Two ways in. Neither can ever do more than your own Growwer account allows:
Permission | Allows |
Read | Every read tool. Always granted. |
Read and write | Also creating projects, placing and cancelling orders, approving deliveries, delivering orders and everything else that changes something. |
OAuth 2.1: the one-click path. Supported by Claude, ChatGPT, Claude Code and any client that
implements the MCP authorization spec. Nothing to copy or paste; revoke it from your account's MCP
page. The scopes are read and write, and write implies read. The server advertises PKCE
(S256), Client ID Metadata Documents, Dynamic Client Registration and RFC 9728 resource metadata,
so clients discover everything they need from
https://tool.growwer.com/.well-known/oauth-protected-resource/mcp. Calling a tool the connection
lacks the scope for answers 403 insufficient_scope naming the scopes to request, so a client that
supports step-up authorization asks you to approve the extra permission.
API key: for CLI clients, config files and this bridge. Create one on the
buyer keys page or the
seller keys page. It is shown once, starts with
gw_sk_, and is either read-only or read and write. Send it as Authorization: Bearer gw_sk_….
ChatGPT cannot send a custom
Authorizationheader to a remote connector, so use OAuth there.
Client configuration
Each client below signs in with OAuth by default; the second block, where there is one, uses an API key instead.
Claude Code
claude mcp add --transport http growwer https://tool.growwer.com/mcp
# Then run /mcp to sign in. With an API key instead, read from GROWWER_API_KEY when Claude Code starts:
claude mcp add --transport http growwer https://tool.growwer.com/mcp --header 'Authorization: Bearer ${GROWWER_API_KEY}'The single quotes keep ${GROWWER_API_KEY} as written: Claude Code stores the reference and expands
it from its own environment, so the key is never on a command line or in its configuration.
Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"growwer": {
"url": "https://tool.growwer.com/mcp"
}
}
}{
"mcpServers": {
"growwer": {
"url": "https://tool.growwer.com/mcp",
"headers": {
"Authorization": "Bearer gw_sk_YOUR_KEY"
}
}
}
}OpenAI Codex (~/.codex/config.toml), then codex mcp login growwer to sign in
[mcp_servers.growwer]
url = "https://tool.growwer.com/mcp"With an API key, read from the environment:
[mcp_servers.growwer]
url = "https://tool.growwer.com/mcp"
bearer_token_env_var = "GROWWER_API_KEY"VS Code (.vscode/mcp.json)
{
"servers": {
"growwer": {
"type": "http",
"url": "https://tool.growwer.com/mcp"
}
}
}With an API key, which VS Code asks for once and stores for you:
{
"inputs": [
{
"type": "promptString",
"id": "growwer-api-key",
"description": "Growwer API key",
"password": true
}
],
"servers": {
"growwer": {
"type": "http",
"url": "https://tool.growwer.com/mcp",
"headers": {
"Authorization": "Bearer ${input:growwer-api-key}"
}
}
}
}Gemini CLI (~/.gemini/settings.json), then /mcp auth growwer to sign in
{
"mcpServers": {
"growwer": {
"httpUrl": "https://tool.growwer.com/mcp"
}
}
}{
"mcpServers": {
"growwer": {
"httpUrl": "https://tool.growwer.com/mcp",
"headers": {
"Authorization": "Bearer gw_sk_YOUR_KEY"
}
}
}
}Tools
Each tool's input schema states what it takes, and catalog.json holds all of them.
Every tool that changes something takes a requestId: calling it again with the same requestId and
arguments returns the first result without writing twice.
Reading
Area | Tools |
Account and reference |
|
Projects |
|
Catalogue |
|
Orders |
|
Managed service |
|
Buyer wallet and billing |
|
Selling |
|
Seller wallet |
|
Webhooks |
|
Changing things
Tools in bold are guarded: they spend money, pay a seller, cancel, refuse or delete something for good, decide a campaign's proposals, send text, a URL or a file to the other party of an order, or choose where Growwer sends your webhook events. The server asks you to confirm in your client before anything happens. See Limits.
Area | Tools |
Projects |
|
Catalogue |
|
Orders |
|
Managed service |
|
Media you sell on |
|
Orders you sell |
|
Webhooks |
|
Prompts
Prompts are guided flows your client can offer as commands. They are static text with no account data, so they answer without signing in, and each one stops for your approval before it changes anything.
Prompt | Workflow |
| Search the catalogue for media that fit one of your projects and compare the best candidates. |
| Estimate an order, then place it with its confirmed price, without charging anything by surprise. |
| See where your orders stand and act on the drafts and deliveries that wait for you. |
| Work through the orders placed on your media: accept them, deliver them and answer update requests. |
| Compare the media Growwer proposed for a campaign, see the cost and decide on each one. |
| Summarise your wallet balances, recent movements, invoices and, if you sell, your earnings. |
Skills
Six optional skills turn the tools into reusable workflows, one per prompt, for hosts that do not surface MCP prompts:
Each folder holds SKILL.md and agents/openai.yaml, which declares the Growwer MCP connection.
They need no additional backend endpoint or local executable.
The bridge
Run it
read -rs GROWWER_API_KEY && export GROWWER_API_KEY # paste the key: not echoed, not kept in history
npx -y @growwer/mcp # serve on stdio
npx -y @growwer/mcp doctor # check the endpoint, the key, and list the toolsDocker
docker run --rm -i -e GROWWER_API_KEY ghcr.io/viralitymedia/growwer-mcp-e GROWWER_API_KEY with no value passes on the variable exported above, so the key stays out of the
command line, ps and your shell history. -i is required and -t must be omitted: the MCP
transport is this process's stdin and stdout.
Options
| API key. Without it the bridge still starts and still advertises the full catalogue; |
| Upstream endpoint. Defaults to |
| Same, as an argument. |
| Extra HTTP header, repeatable. An |
| Connect once, print the server version, negotiated protocol, tool and prompt catalogue, then exit. |
|
What it actually does
It splices your client's stdio transport onto a Streamable HTTP transport and forwards every JSON-RPC frame verbatim, in both directions. The only frame it looks inside is the handshake, enough to echo the negotiated protocol version back upstream and to rebuild the session if the server evicts it, which a deploy or a scale-down will do. It knows no other method, so it cannot drift from the server: tools, prompts, guarded writes on either protocol, progress notifications and anything added later all pass straight through.
The bridge never leaves a request unanswered:
Every request gets a reply. A status such as 429 or 503, a refused connection, a wrong content type or a stream that ends with no result reaches your client as a JSON-RPC error on that request's id, naming the status, or the error's class and code. No error message is repeated, an upstream body included, in that error or on stderr. When the request had already been sent and the failure came after the connection was made, such as a dropped connection, a proxy's 502 or a stream with no result, the error also says it may have run. Notifications and responses have no one to answer, so a failure of theirs is logged.
Only a 404 rebuilds the session, once however many requests hit it at the same time, and a 400 never does. The request that got the 404 never ran, so it alone is sent again, once. A response is never sent again.
A request that was open when the session died gets an error, not a retry, because it may have run. That includes a guarded write waiting for your confirmation: your answer to it is dropped, and never reaches the new session. The write's
requestIdmakes a repeat safe.A failed rebuild keeps the bridge up. A rebuild fails when it is refused or gets no answer within 15 seconds. The request that needed it gets an error, and the next one rebuilds first.
A rejected key ends the bridge. On a 401, the rejected request and those not sent yet get the explanation, one already sent gets an error saying it may have run, then the process exits.
Without a credential
The bridge starts anyway, serving catalog.json, a committed copy of what the hosted
server advertises, plus a growwer_setup tool. So npx -y @growwer/mcp introspects to the same
tools and prompts a credentialed run does, and anything that scans the package sees a real catalogue
rather than a server that looks empty. Calling one of those tools returns the setup instructions as
an error; it never returns invented data. The exceptions read only published material:
growwer_get_guide and prompts/get go to the hosted server's anonymous endpoint, with no
credential, and return the real answer.
npm run sync:catalog refreshes the file from that endpoint, and npm run check:catalog fails if
the committed copy has fallen behind. A scheduled workflow runs the check weekly, because the
catalogue it mirrors lives in another repository and nothing in a pull request here would notice it
drifting. A release runs the same check first, so a stale catalogue publishes nothing.
Limits
Access |
|
Confirmation | Seven writes need your confirmation in a client that can show a form (MCP form elicitation). A client without it gets |
Money | Spending comes from your Growwer wallet. Top-ups happen on growwer.com, never through a tool. |
Catalogue | The full catalogue opens after a recent delivered order; until then a small daily trial quota applies ( |
Protocols | MCP 2025-11-25 and 2026-07-28 over Streamable HTTP. |
Rate limiting | Tool calls share a per-minute budget with the REST API, per user and per key ( |
Result size | Large result sets are paginated; each tool's input schema states its limits. |
Repository contents
| The stdio bridge published as |
| What the hosted server advertises, served by the bridge when it has no credential. |
| Manifest and catalogue checks run by CI, and the end-to-end host driver. |
| The MCP registry manifest. |
| Glama directory ownership metadata. |
| Six reusable Growwer workflows, one per prompt. |
| The image published to |
| Brand assets used by directory listings. |
| The steps that publish the first release. |
Development
npm ci
npm run typecheck
npm test # builds first, then runs the suite
npm run check:manifests
npm run check:catalog # asks the hosted server whether catalog.json is still currentTests run the TypeScript sources directly through Node's type stripping, so development needs Node 22.18 or newer. The published package targets Node 20.19+, which CI verifies separately against the built artifact.
scripts/e2e-host.mjs drives the built bridge as a real host would, against a running Growwer stack,
on both protocols: a read, a plain write, and a guarded write declined and accepted. It deletes
projects, so point it at a development stack, with a read and write key of that stack in
GROWWER_API_KEY whose account owns two disposable projects named bridge-e2e:
npm run build
node scripts/e2e-host.mjs --url http://localhost:<stack port>/mcpReleases are cut by tagging. npm version <patch|minor|major>, mirror the new version into
server.json (.version, the npm package entry, and the image tag), run
npm run check:manifests, then push the tag and approve the npm-release and mcp-registry
deployments it asks for. CI publishes to npm through trusted publishing, GHCR and the MCP registry,
in that order, then creates the GitHub release, which is what Glama builds a new version from. If a job
fails after npm has published, use "Re-run failed jobs": "Re-run all jobs" stops at npm publish,
since a version cannot be published twice. The first
release has owner steps of its own, in RELEASING.md.
Support
Product and account questions: support@growwer.com
Bugs in this package: open an issue
Security: see SECURITY.md
About the server: growwer.com/link-building-mcp
Privacy policy: growwer.com/legal/privacy-policy
Terms of use: growwer.com/legal/terms-of-use
Licence
MIT. See LICENSE.
The Growwer name, logo and brand assets in assets/ are trademarks of Virality Media, S.L. and are
not covered by that licence.
Available Tools
70 toolsgrowwer_accept_seller_orderAccept an orderBDestructiveIdempotent
Use this when a seller takes an order placed on one of their medias that waits for acceptance: accepts it and the buyer is told.
Inputs: id (required), requestId (required).
growwer_apply_seller_media_competitive_feesApply the suggested competitive feesADestructiveIdempotent
Use this when a seller wants the fees Growwer suggests for one of their medias: sets its post fees to the competitiveFees growwer_get_seller_media answers.
Inputs: id (required), requestId (required).
growwer_approve_orderApprove an order's deliveryADestructiveIdempotent
Use this when the user has checked the delivery of an order that waits for their review and accepts it: the order finishes and the seller is paid. It cannot be undone. The user is asked to confirm first.
Inputs: id (required), requestId (required).
growwer_approve_order_draftApprove an order's draftADestructiveIdempotent
Use this when the user has read the draft of a post order that waits for their review and accepts it: the seller then publishes it.
Inputs: id (required), requestId (required).
growwer_cancel_orderCancel an orderADestructiveIdempotent
Use this when the user wants to cancel an order the seller has not accepted yet: cancels it, its price returns to their wallet and the seller is told the reason. The user is asked to confirm first.
Inputs: id (required), reason (required), requestId (required).
growwer_count_saved_filter_mediasCount the medias of a saved filterARead-onlyIdempotent
Use this when you need how many catalogue medias one saved filter of a project matches, without listing them: the total growwer_search_project_medias answers with that savedFilterId.
Inputs: id (required), filterId (required).
growwer_create_orderPlace an orderADestructive
Use this when the user has decided to buy an article or a link addition on a catalogue media for one of their projects: places the order, and its price leaves their wallet. Send the price growwer_estimate_order answered as expectedPrice. The user is asked to confirm the purchase first, and nothing is charged unless they accept.
Inputs: type (required), mediaId (required), briefing (required), projectId (required), +5 more.
growwer_create_projectCreate a projectB
Use this when the user wants to buy links for a website that has no project yet: creates the project, which Growwer then analyses in the background to recommend medias.
Inputs: topics (required), rootUrl (required), language (required), requestId (required), +5 more.
growwer_create_saved_filterSave a catalogue filterA
Use this when the user wants to keep a catalogue search of a project to reuse it, here or on the web: saves the filters growwer_search_project_medias takes, optionally with notifications of new matching medias.
Inputs: id (required), name (required), filters (required), requestId (required), +1 more.
growwer_create_seller_mediaRegister a media to sell onA
Use this when a seller wants to offer a new website of theirs on Growwer: registers the media with its fees and offer, and Growwer reviews it in the background.
Inputs: topics (required), country (required), rootUrl (required), language (required), +8 more.
growwer_delete_projectDelete a projectADestructiveIdempotent
Use this when the user no longer wants one of their projects: deletes it for good. A project with an order in progress cannot be deleted. The user is asked to confirm first.
Inputs: id (required), requestId (required).
growwer_delete_saved_filterDelete a saved filterADestructiveIdempotent
Use this when the user no longer wants one of the saved filters of a project, including one saved on the web: deletes it and stops its notifications.
Inputs: id (required), filterId (required), requestId (required).
growwer_delete_seller_mediaDelete a media you sell onADestructiveIdempotent
Use this when a seller wants to stop offering one of their medias for good: deletes it, as the web's delete button does. A media with an order in progress cannot be deleted. The user is asked to confirm first.
Inputs: id (required), requestId (required).
growwer_deliver_seller_orderDeliver an orderBDestructiveIdempotent
Use this when a seller has published an accepted order: delivers a post order with the URL of the post and publicationDateConfirmed, and a link addition with neither, for the buyer to review.
Inputs: id (required), requestId (required), url, publicationDateConfirmed.
growwer_deliver_seller_order_draftDeliver a draftADestructiveIdempotent
Use this when a seller who writes the draft of a post order has it ready: delivers it from a file uploaded with growwer_upload_file.
Inputs: id (required), fileId (required), requestId (required).
growwer_deliver_seller_order_draft_updateDeliver a draft updateADestructiveIdempotent
Use this when a seller has changed the draft of a post order as the buyer asked: delivers the new draft from a file uploaded with growwer_upload_file.
Inputs: id (required), fileId (required), requestId (required).
growwer_deliver_seller_order_updateDeliver an updateADestructiveIdempotent
Use this when a seller has changed a delivered order as the buyer asked: delivers a post order with the URL of the post and publicationDateConfirmed, and a link addition with neither, for the buyer to review again.
Inputs: id (required), requestId (required), url, publicationDateConfirmed.
growwer_discard_mediaDiscard a media for a projectADestructiveIdempotent
Use this when the user does not want a catalogue media for one of their projects: discards it for that project, as the web does. Discarding it again changes nothing.
Inputs: id (required), mediaId (required), requestId (required).
growwer_download_buyer_transaction_documentDownload a buyer wallet documentARead-onlyIdempotent
Use this when the user needs the document Growwer attached to a movement of their buyer wallet: returns the file. Find the movement with growwer_list_buyer_transactions.
Inputs: id (required).
growwer_download_order_briefingDownload the draft attached to an orderBRead-onlyIdempotent
Use this when the user needs the file they attached to the briefing of one of their post orders: returns the file.
Inputs: id (required).
growwer_download_order_draftDownload the draft of an orderARead-onlyIdempotent
Use this when the user needs the current draft file of one of their post orders, to review it before publishing: returns the file.
Inputs: id (required).
growwer_download_seller_order_briefingDownload the draft a buyer attachedCRead-onlyIdempotent
Use this when the user, as a seller, needs the file the buyer attached to the briefing of a post order they sell: returns the file.
Inputs: id (required).
growwer_download_seller_order_draftDownload the draft of an order you sellBRead-onlyIdempotent
Use this when the user, as a seller, needs the current draft file of a post order they sell: returns the file.
Inputs: id (required).
growwer_download_seller_transaction_documentDownload a seller wallet documentARead-onlyIdempotent
Use this when the user needs the document Growwer attached to a movement of their seller wallet: returns the file. Find the movement with growwer_list_seller_transactions.
Inputs: id (required).
growwer_download_withdrawal_invoiceDownload a withdrawal invoiceARead-onlyIdempotent
Use this when the user needs the invoice they uploaded for one of their withdrawals: returns the file.
Inputs: id (required).
growwer_estimate_managed_service_proposalsEstimate accepting proposalsARead-onlyIdempotent
Use this when the user considers accepting proposals of a managed service campaign: totals the accepted proposals still awaiting their order and the proposed ones named in accept, and compares the total with the available wallet balance. Changes nothing.
Inputs: id (required), accept.
growwer_estimate_orderEstimate an orderARead-onlyIdempotent
Use this when the user considers buying an article on a media: checks and prices the order these arguments describe and compares the price with the available wallet balance. Changes nothing.
Inputs: type (required), mediaId (required), briefing (required), projectId (required), +3 more.
growwer_favourite_mediaAdd a media to a project's favouritesAIdempotent
Use this when the user likes a catalogue media for one of their projects: marks it as a favourite of that project, as the heart on the web does. Adding it again changes nothing.
Inputs: id (required), mediaId (required), requestId (required).
growwer_get_buyer_walletGet your buyer walletARead-onlyIdempotent
Use this when the user asks how much they can spend: answers the balance of their buyer wallet and the page where they top it up.
Inputs: no named parameters.
growwer_get_catalogue_mediaGet a catalogue mediaARead-onlyIdempotent
Use this when you need the full details of one media of the catalogue, such as its prices, metrics and conditions, before estimating or recommending an order on it.
Inputs: id (required).
growwer_get_guideGet the Growwer guideARead-onlyIdempotent
Use this when you start working with Growwer, or when a tool answer is unclear: explains the buyer and seller profiles, the order states, paging, the error codes and where the vocabulary ids come from. Needs no sign-in or API key.
Inputs: no named parameters.
growwer_get_invoice_pdfDownload an invoiceARead-onlyIdempotent
Use this when the user needs the PDF of one of their top-up invoices: returns the file. Find the invoice id with growwer_list_invoices.
Inputs: id (required).
growwer_get_managed_service_campaignGet a managed service campaignARead-onlyIdempotent
Use this when you need one managed service campaign in full: its budget, targets, state and progress.
Inputs: id (required).
growwer_get_managed_service_proposals_summaryDownload a campaign's proposals summaryBRead-onlyIdempotent
Use this when the user wants the PDF summary of a managed service campaign's proposals, as the campaign page offers it; extended adds the details of each media. Returns the file.
Inputs: id (required), extended.
growwer_get_meGet your accountARead-onlyIdempotent
Use this when you start working with an account, or need its profiles, balances or access: answers the profile basics, the buyer and seller balances, whether the seller account is restricted, whether the catalogue is open to it, and whether it has a managed service.
Inputs: no named parameters.
growwer_get_orderGet an orderARead-onlyIdempotent
Use this when you need one order the user bought in full: its briefing, its draft and its state history.
Inputs: id (required).
growwer_get_projectGet a projectARead-onlyIdempotent
Use this when you need one of the user's projects in full, such as its domain, its topics and its state.
Inputs: id (required).
growwer_get_seller_mediaGet a media you sell onARead-onlyIdempotent
Use this when you need one of the user's seller medias in full: its fees, extras, the competitive fees Growwer suggests and its performance.
Inputs: id (required).
growwer_get_seller_orderGet an order you sellARead-onlyIdempotent
Use this when you need one order placed on one of the user's medias in full: its briefing, its draft and its state history.
Inputs: id (required).
growwer_get_seller_walletGet your seller walletARead-onlyIdempotent
Use this when the user asks what their sales earned: answers the balance they can withdraw now and what is held until orders settle.
Inputs: no named parameters.
growwer_get_vocabularyGet the codes and namesARead-onlyIdempotent
Use this when a filter or an answer takes a country, language, topic, product type or link type: lists every code with its English name, so the ids are never guessed.
Inputs: no named parameters.
growwer_list_buyer_transactionsList your buyer wallet movementsARead-onlyIdempotent
Use this when the user asks about the movements of their buyer wallet: lists top-ups, order debits and their refunds, gifts and manual corrections, newest first.
Inputs: limit, offset.
growwer_list_flash_offersList flash offersBRead-onlyIdempotent
Use this when the user looks for discounted medias: lists the medias on a time-limited flash offer in the catalogue of one of their projects.
Inputs: projectId (required), new, sort, limit, +32 more.
growwer_list_invoicesList your invoicesARead-onlyIdempotent
Use this when the user asks about the invoices of their top-ups: lists them, newest first, with their amounts and dates.
Inputs: limit, offset.
growwer_list_managed_service_campaignsList your managed service campaignsARead-onlyIdempotent
Use this when the user asks about the campaigns Growwer's team runs for them: lists their managed service campaigns, newest first. Empty without a managed service.
Inputs: limit, offset.
growwer_list_managed_service_proposalsList the proposals of a campaignARead-onlyIdempotent
Use this when the user reviews what Growwer's team proposes for a managed service campaign: lists the proposed medias, newest first, with their state and price.
Inputs: id (required), limit, state, offset.
growwer_list_ordersList your ordersARead-onlyIdempotent
Use this when the user asks about the orders they bought, or to follow them: lists them with filters on state, project and dates; sort by updatedAt with updatedSince to see only what changed.
Inputs: sort, limit, state, offset, +3 more.
growwer_list_projectsList your projectsARead-onlyIdempotent
Use this when you need the user's projects (the websites they buy for), for example to pick the project id the catalogue and order tools take: lists them, newest first.
Inputs: limit, offset.
growwer_list_saved_filtersList the saved filters of a projectARead-onlyIdempotent
Use this when the user refers to a catalogue search they saved, on the web or here: lists the saved filters of one project, newest first, to apply one with savedFilterId in growwer_search_project_medias.
Inputs: id (required).
growwer_list_seller_mediasList the medias you sell onARead-onlyIdempotent
Use this when the user asks about the medias they sell articles on: lists them in every state with their fees and performance.
Inputs: sort, limit, state, offset.
growwer_list_seller_ordersList the orders you sellARead-onlyIdempotent
Use this when the user, as a seller, asks about the orders placed on their medias, or to follow them: lists them with filters; sort by updatedAt with updatedSince to see only what changed.
Inputs: sort, limit, state, offset, +2 more.
growwer_list_seller_transactionsList your seller wallet movementsARead-onlyIdempotent
Use this when the user asks about the movements of their seller wallet: lists earnings from orders, withdrawals and manual corrections, newest first.
Inputs: limit, offset.
growwer_list_withdrawalsList your withdrawalsARead-onlyIdempotent
Use this when the user asks about the withdrawals they requested from their seller wallet: lists them, newest first, with their state.
Inputs: limit, state, offset.
growwer_put_seller_holidaySet your seller holidayBDestructiveIdempotent
Use this when a seller wants to start, change or end their holiday: while on holiday their medias take no orders. Setting the holiday they already have changes nothing.
Inputs: onHoliday (required), requestId (required), endDate.
growwer_refute_seller_order_draft_updateRefuse a draft updateADestructiveIdempotent
Use this when a seller will not change a draft as the buyer asked: refuses the update with a reason the buyer is told.
Inputs: id (required), reason (required), requestId (required).
growwer_refute_seller_order_updateRefuse an updateADestructiveIdempotent
Use this when a seller will not change a delivered order as the buyer asked: refuses the update with a reason the buyer is told.
Inputs: id (required), reason (required), requestId (required).
growwer_reject_seller_orderReject an orderADestructiveIdempotent
Use this when a seller will not take an order placed on one of their medias that waits for acceptance: rejects it, the buyer gets the price back and is told the reason. The user is asked to confirm first.
Inputs: id (required), reason (required), requestId (required).
growwer_request_managed_service_campaignRequest a managed service campaignBDestructive
Use this when a user with a managed service wants Growwer's team to run a new campaign: asks their account manager for it, and the team emails them to agree on it.
Inputs: goal (required), country (required), duration (required), requestId (required), +3 more.
growwer_request_managed_service_infoAsk about the managed serviceBDestructive
Use this when a user without a managed service wants Growwer's team to run their link building: asks the team about it for their website, and the team contacts them.
Inputs: goal (required), country (required), duration (required), requestId (required), +3 more.
growwer_request_mediasRequest specific domains for a projectADestructiveIdempotent
Use this when the user wants medias on particular domains the catalogue does not offer for a project: asks Growwer to find them, as the web's "request specific domains" form does.
Inputs: id (required), domains (required), requestId (required).
growwer_request_order_draft_updateRequest changes to a draftADestructiveIdempotent
Use this when the user wants the seller to change the draft of a post order that waits for their review: sends the seller the reason.
Inputs: id (required), reason (required), requestId (required).
growwer_request_order_updateRequest changes to a deliveryADestructiveIdempotent
Use this when the user wants the seller to change the delivery of an order that waits for their review: sends the seller the reason.
Inputs: id (required), reason (required), requestId (required).
growwer_review_managed_service_proposalsAccept or reject proposalsADestructiveIdempotent
Use this when the user has decided on every proposal of a managed service campaign that awaits their review: accepts or rejects each one; the team then places the orders of the accepted ones, which their wallet pays. growwer_estimate_managed_service_proposals says what they cost. The user is asked to confirm first.
Inputs: id (required), reviews (required), requestId (required).
growwer_search_project_mediasSearch the catalogue for a projectARead-onlyIdempotent
Use this when the user wants media to publish on for one of their projects: searches the catalogue with filters on price, metrics, topics, languages, countries and more, and answers each media with its state in the project.
Inputs: id (required), new, sort, limit, +34 more.
growwer_setupGrowwer setup instructionsARead-onlyIdempotent
Explain how to finish connecting this bridge to Growwer. The bridge has no API key, so no project, order, wallet or seller data can be read until one is configured.
Inputs: no named parameters.
growwer_undiscard_mediaRestore a discarded mediaADestructiveIdempotent
Use this when the user wants back a media they discarded for one of their projects: removes the discard. Restoring one that is not discarded changes nothing.
Inputs: id (required), mediaId (required), requestId (required).
growwer_unfavourite_mediaRemove a media from a project's favouritesADestructiveIdempotent
Use this when the user no longer wants a media among the favourites of one of their projects: removes it. Removing one that is not a favourite changes nothing.
Inputs: id (required), mediaId (required), requestId (required).
growwer_update_projectEdit a projectADestructiveIdempotent
Use this when the user wants to change the settings of one of their projects, such as its name, language, country, topics or promoted products: changes only the fields sent.
Inputs: id (required), requestId (required), name, topics, +5 more.
growwer_update_seller_mediaEdit the offer of a mediaADestructiveIdempotent
Use this when a seller wants to change the fees, extra services, typology or post offer of one of their medias: replaces each field sent and keeps the rest.
Inputs: id (required), requestId (required), typology, postOffer, +2 more.
growwer_upload_fileUpload a fileA
Use this when a later write needs a document, such as a seller delivering a draft: uploads an odt, doc, docx or txt file of at most 3 MB, sent as its name and base64 content, and answers its id for that write. The file expires after 24 hours.
Inputs: name (required), content (required), requestId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 70 tools
Most tools target a clearly distinct resource and action, and descriptions explicitly separate buyer vs seller flows, drafts vs delivered orders, and campaign proposal review steps. The large number of closely related seller/buyer and draft/update variants still creates some misselection risk, so it is not quite perfect.
The tool names consistently use the growwer_ prefix and snake_case verb_noun phrasing such as list_orders, create_project, approve_order, and download_seller_order_draft. Buyer/seller qualifiers are generally applied consistently where needed.
Seventy tools is far beyond a manageable surface for an agent, even for a broad two-sided marketplace domain. Many operations are granular and legitimate, but the overall count is an extreme mismatch for practical tool selection.
The surface covers projects, catalogue search, favourites/discards, buyer and seller orders, seller media, wallets, invoices, transactions, withdrawals listing, managed services, saved filters, and file uploads. Notable gaps remain, such as actually requesting a seller withdrawal or topping up a buyer wallet through the MCP surface.
Related MCP Connectors
AI agents that research, write and publish SEO articles on your website, from your AI assistant.
Enables AI assistants to natively interact with the Serpzilla link-building marketplace.
Search, price and order press placements across 1,600+ publications. Free AI-visibility audits too.
Track AI visibility and SEO performance, monitor publications and manage link-building orders.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to create, analyze, and optimize ad campaigns across Google Ads, Meta Ads, TikTok Ads, LinkedIn Ads, Amazon Ads, and ChatGPT Ads through natural language using 400+ tools.108MIT
- AlicenseAqualityBmaintenanceEnables AI tools to research, write, and publish finished blog posts to Ghost and WordPress in the user's voice, supporting multiple author personas and destinations through natural language.142MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to automate social media content generation, approval, and publishing, along with blog management, SEO/GEO audits, and ad operations through natural language.3AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceLets AI assistants manage a self-hosted content hub: create, edit, publish, and update articles across nine platforms, refresh account article lists, and sync changes through natural language.MIT