Grona MCP
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., "@Grona MCP create a campaign for my homepage and generate the install snippet"
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.
Grona MCP
A TypeScript MCP server for all 10 operations in the captured Grona Public API contract, including the separate mobile grants API. It exposes 10 API tools plus 9 agent helpers, reference resources and reusable prompts over stdio. It uses the official MCP TypeScript SDK v2.
Campaign helpers support discovery, duplicate-safe creation, preview summaries, fresh installation checks, launch, A/B split updates, page-targeting simulation and snippet generation. Direct tools keep Grona's original response envelopes and extension fields.
Features
Direct API tools
Tool | Feature |
| List workspace campaigns. |
| Create general or A/B campaigns with page targeting, optional visitor variables and traffic splits. |
| Retrieve a campaign by Grona ID or external ID. |
| Update supported campaign fields. |
| Permanently delete a campaign. |
| Publish ( |
| Generate a fresh visual editor link for a variation. |
| Validate/refresh an existing editor link. |
| Check for the Grona installation snippet on a page. |
| Request mobile grants for a customer using the separate mobile service and credential. |
Workflow and local tools
Tool | Feature |
| Search names, IDs, external IDs and domains; filter campaign properties, sort and paginate locally. |
| Create with a stable external ID, conservatively reconcile duplicate conflicts and refresh editor links on verified recovery. |
| Summarize campaign targeting, derived page URL, preview links, blockers and suggested next steps. |
| Check usable variations, A/B split membership and fresh snippet presence; report blockers and manual checks. |
| Recheck readiness and publish after caller edit/preview attestations; report uncertain outcomes for reconciliation. |
| Resolve Control/Test variation IDs and set integer traffic percentages totaling 100%. |
| Locally simulate specific/multiple-page URL targeting, inclusion/exclusion rules and visitor-variable eligibility. |
| Generate escaped installation HTML, optional visitor-variable assignment and installation instructions. |
| Report credential availability, endpoints, authentication mode, timeouts and retries without exposing secrets. |
Reference resources
Resource | Contents |
| API route-to-tool mapping. |
| Campaign lifecycle, targeting, installation, links and mobile guidance. |
| Error codes, replay rules and recovery guidance. |
| Captured Grona OpenAPI specification. |
Guided prompts
Prompt | Purpose |
| Installation, creation, editing, preview and launch checklist; accepts an optional campaign ID. |
| Diagnose snippet installation issues for a supplied URL. |
| Explain customer identity, separate credentials and grant handling obligations. |
Prompts provide guidance; they do not perform API operations themselves.
Server capabilities
MCP stdio transport using the official TypeScript SDK v2.
Validated input schemas, JSON text and structured results, and tool annotations for reads, mutations and destructive actions.
Structured errors, recovery guidance and partial-workflow reporting.
Configurable endpoints, authentication mode, timeouts and retries, with separate Embed/mobile credentials.
Local tools and static reference resources usable without API credentials.
TypeScript exports for the server, client, configuration, schemas, workflows and types.
Related MCP server: Google Ads MCP Worker
Grona web app coverage
Public API coverage does not mean full web app coverage. The following describes this server against the API contract captured in this repository; it does not claim that no additional Grona APIs exist.
Web app section | MCP support |
Home | No dashboard summary endpoint. |
Recommendations | Not exposed. |
Business | Not exposed. |
Journey | Not exposed. |
Website | Partial: generate installation snippets and verify snippet presence on a URL. |
Campaigns | List, create, read, update, delete, publish/pause, editor links, preview summaries, readiness checks and A/B traffic splits. Visual editing happens in Grona's editor. |
Site health | Partial: snippet verification only; no general site health reports. |
Heatmaps | Not exposed. |
Audiences | Partial: campaign targeting using page-variable names/values; no audience management or discovery. |
Pages | Partial: campaign URL targeting and local targeting simulation; no page inventory or management. |
Self-optimizing | No dedicated controls or results exposed. |
Leads | Not exposed. |
Analytics | Not exposed, including campaign performance and conversion metrics. |
Integrations | No integration management. |
Settings | Local MCP configuration diagnostics only; no Grona account/workspace settings management. |
Mobile grant issuance is supported separately from these dashboard sections. The server does not perform visual edits, prove browser script execution, verify shopper identities or redeem grants. Snippet generation does not install it, and readiness checks still require manual browser checks. Supporting additional dashboard sections requires additional documented APIs or another authorized integration mechanism.
Run locally
Requires Node.js 22.12 or newer, npm and a Grona API key for network tools. Request an Embed workspace from Grona, then generate the workspace secret under Settings → Secrets. Mobile grants access and its key are provisioned separately by Grona.
npm ci
npm run buildConfigure an MCP client to spawn the built executable. Replace the absolute path and configure secrets using the client's environment/secret settings:
{
"mcpServers": {
"grona": {
"command": "node",
"args": ["/absolute/path/to/grona-mcp/dist/index.js"],
"env": {
"GRONA_API_KEY": "your-embed-workspace-secret",
"GRONA_MOBILE_API_KEY": "your-separate-mobile-secret"
}
}
}
}Omit GRONA_MOBILE_API_KEY if you only use Embed. See example client configuration. Local tools, resources and prompts work without credentials; an attempted API call reports which key is missing.
For direct launch from a shell with a protected local environment file:
cp .env.example .env
# Edit .env locally; never commit it.
node --env-file=.env dist/index.jsThe process speaks MCP JSON-RPC on stdin/stdout and waits for a client; it does not print an interactive prompt. Environment files are loaded by Node's --env-file option, not implicitly by the server. The MCP client's env settings also work. To develop, use npm run dev.
Documentation
Complete API → MCP reference: every route, input field, cross-field rule, response field and HTTP status, generated from the captured OpenAPI contract.
Agent guide: all helper tools, resources, prompts and workflows, with example arguments.
Operations and troubleshooting: every configuration variable, credentials, retries, errors, privacy, packaging and Docker.
Architecture and development: module structure, verification, contract maintenance and Foundry work orders.
API coverage
HTTP method | Route | MCP tool |
GET |
|
|
POST |
|
|
GET |
|
|
PATCH |
|
|
DELETE |
|
|
PATCH |
|
|
POST |
|
|
POST |
|
|
POST |
|
|
POST |
|
|
Embed requests use https://services.grona.ai/api/public/v1. Mobile requests use https://api.grona.ai, always with the mobile credential. Workspace selection comes from each key, never from a tool argument.
Typical agent use
Start with grona_configuration and the workflow reference resource. Search existing campaigns before creating one. Use a stable business externalId with grona_create_campaign_once. Open the visual editor, save the changes, and check the preview. Then use readiness and launch helpers. New campaigns start paused.
The API exposes no analytics, campaign-result reports, visual-content editing, grant redemption, or key-management endpoints. The server does not invent those operations. Preview/editor links and mobile grants are sensitive; use only trusted MCP clients. See the Grona reference and operations guide.
Verify
npm run verify
npm run test:coverage
npm pack --dry-runTests exercise HTTP behavior through deterministic fakes/local services and MCP protocol calls through the official client. Production credentials are not required. Live Grona account behavior requires a provisioned workspace and is not claimed by these tests.
The verification record includes the final checks and live-account validation boundary.
Workorder management is bootstrapped from ~/trabalho/foundry-protocol, with the queue in docs/ORCHESTRATION.md and results under docs/work-orders.
Copyright (c) 2026 Guilherme da Silveira and contributors.
This implementation is free software under the GNU General Public License, version 3 or (at your option) any later version (SPDX: GPL-3.0-or-later). It is provided without warranty; see LICENSE.
The Foundry scripts are also licensed under GPL-3.0-or-later, with their original author attributions retained. Third-party dependencies retain their respective licenses, as recorded in package-lock.json.
Grona reference material in docs/upstream, including the proprietary API contract, is excluded from this GPL grant and remains subject to Grona's terms. Redistribution permission for that material must be established separately. This license grants no rights to Grona's service or branding.
Available Tools
19 toolsgrona_campaign_overviewExplain campaignARead-onlyIdempotent
Read campaign and summarize targeting, previews, variation health and next steps. Does not mint editor links or claim analytics exist.
Inputs: campaignId (required). Returns: object
grona_check_campaign_readinessCheck launch readinessARead-onlyIdempotent
Read campaign and freshly verify its actual page from stored url or preview URL. Report observable blockers and manual checks. Cannot inspect saved edits or previews.
Inputs: campaignId (required). Returns: object
grona_configurationInspect configurationARead-onlyIdempotent
Show credential-presence flags, hosts and timeout/retry settings without secrets. Makes no upstream request.
Inputs: no named parameters. Returns: object
grona_create_campaignCreate campaignB
Create a paused campaign and variations with 15-minute editor links. Use externalId for duplicate protection. Requires Embed snippet and page variable. Creation never publishes.
Inputs: url (required), name (required), segmentId (required), segmentValue (required), +7 more. Returns: object
grona_create_campaign_onceCreate campaign onceB
Require externalId; on 409 fetch and compare existing campaign identity before recovering with fresh editor links. Conflict never patches or publishes an existing campaign.
Inputs: campaign (required). Returns: object
grona_create_edit_linkCreate editor linkA
Mint a secret 15-minute editor link by variationId (preferred) or page url. variationId wins; url chooses most recently updated match. Editor trust covers the workspace. Open immediately; do not store, log or share.
Inputs: url, variationId. Returns: object
grona_delete_campaignDelete campaignADestructive
Permanently delete campaign and unshared variations. Frees externalId for reuse. Retry only by immutable Grona id. Propagation to visitors is asynchronous.
Inputs: campaignId (required). Returns: object
grona_evaluate_page_targetingSimulate page targetingBRead-onlyIdempotent
Locally evaluate URL rules and optional page-variable value. Multiple-page exclusions still require exact origin and segment count. Predicts eligibility, not execution or traffic allocation.
Inputs: url (required), urls (required), list, slug, +6 more. Returns: object
grona_generate_snippetGenerate Embed snippetARead-onlyIdempotent
Generate escaped Embed HTML and optional page-variable assignment. Dashboard snippet may include anti-flicker; this helper installs nothing.
Inputs: workspaceId (required), segmentId, segmentValue. Returns: object
grona_get_campaignGet campaignARead-onlyIdempotent
Get by opaque Grona id or workspace-unique externalId. Grona id wins on ambiguity. No editor links return.
Inputs: campaignId (required). Returns: object
grona_issue_grantsFetch mobile grantsARead-onlyIdempotent
Fetch current signed grants from separate mobile service/credential. customerId must come from authenticated shopper session, never app input or PII. Return tokens unchanged; this does not verify or redeem them.
Inputs: customerId (required). Returns: object
grona_launch_campaignLaunch reviewed campaignADestructive
Require edited=true and previewed=true attestations, freshly verify actual campaign page, then set live by immutable id. Refuse absent snippet/unusable variations. Direct tools remain unguarded.
Inputs: edited (required), previewed (required), campaignId (required). Returns: object
grona_list_campaignsList campaignsARead-onlyIdempotent
Return every workspace campaign with variations and previews. No upstream pagination or specified order; editor links are omitted.
Inputs: no named parameters. Returns: object
grona_search_campaignsSearch campaignsARead-onlyIdempotent
Fetch full list once; filter locally by text/status/type/domain/script state/externalId and sort deterministically. offset/limit are local presentation controls.
Inputs: type, limit, order, query, +6 more. Returns: object
grona_set_ab_splitSet traffic split by roleADestructive
Read A/B campaign; map Control/Test to current variation ids, validate integer percentages total 100, update by immutable campaign id.
Inputs: Test (required), Control (required), campaignId (required). Returns: object
grona_set_campaign_statusSet campaign statusADestructive
Set live or paused. live affects real visitors after propagation. Prefer grona_launch_campaign for readiness guards; this direct route has none.
Inputs: status (required), campaignId (required). Returns: object
grona_update_campaignUpdate campaignADestructive
Patch mutable fields; returns full campaign. url/type/pageTargeting are fixed at creation. Retry only by immutable Grona id. trafficSplit keys are variation ids totaling 100.
Inputs: changes (required), campaignId (required). Returns: object
grona_validate_edit_linkValidate or refresh editor linkA
Send the whole editor URL; receive original or refreshed link. Always open returned data.editUrl. valid=false/refreshed=true is successful.
Inputs: editUrl (required). Returns: object
grona_verify_scriptVerify Embed installationARead-onlyIdempotent
Check exact page for this workspace’s Embed snippet. absent also means inaccessible page. Does not verify execution, anti-flicker, consent, CSP or whole site. Can take several seconds.
Inputs: url (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 19 tools
Most tools have clearly distinct purposes, and the descriptions do unusually explicit boundary work (e.g. grona_launch_campaign vs grona_set_campaign_status, grona_verify_script vs grona_check_campaign_readiness). There are still overlapping read surfaces (list_campaigns / search_campaigns / get_campaign / campaign_overview) and two create paths, so a few pairs require reading descriptions carefully before selection.
All tools share a grona_ prefix plus snake_case verb_noun naming (create_campaign, set_campaign_status, validate_edit_link, evaluate_page_targeting), which is highly predictable. The only deviations are noun-only names like grona_configuration and grona_campaign_overview, which break the verb pattern slightly but remain readable.
At 19 tools the set sits at the heavy end for a campaign/experiment domain, with several near-siblings (two creates, four read variants, two status paths) that could arguably be consolidated. Each tool does have a defensible role, but the surface feels larger than the core workflow strictly requires.
Core lifecycle is well covered: create/get/update/delete/list/search, status and guarded launch, idempotent create, editor links, snippet generation and verification, A/B split, targeting evaluation, readiness and overview. The notable gap is results/analytics reading (explicitly out of scope) and no direct variation-content or variation-delete operation, though editor links provide a workaround.
Maintenance
Related MCP Connectors
Read and update your Rawa brands, creatives, calendar and performance; generate and publish.
Manage Kajabi from any MCP client — products, pages, contacts, offers, emails, analytics.
Send transactional email and manage domains, audiences, and broadcasts from any MCP client.
Google Ads MCP server — manage campaigns, keywords, and metrics.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables reading and mutating Google Ads campaigns via MCP tools, and includes structured marketer workflows for search term mining, budget optimization, and weekly reviews.6MIT
- FlicenseNot gradedqualityCmaintenanceEnables management of Google Ads accounts via MCP, providing read and write tools for campaigns, ad groups, keywords, assets, and more, with support for reporting and mutations.-
- AlicenseNot gradedqualityDmaintenanceEnables MCP-capable agents to create, edit, pause, archive campaigns, and pull advertising reports from the Gravity Ads platform directly, without the API key leaving the local machine.17 npmMIT
- AlicenseBqualityBmaintenanceEnables MCP clients to read and analyze Pinterest advertising data, with optional guarded write tools that preview changes before applying them, all while keeping your token on your own machine and protecting lead records.26374 npmApache 2.0