Summary
Tilda Publishing website builder, read-only API: projects, project settings, page lists and the published HTML of pages, as markup or prepared for export to your own server. Public key and secret key (Business plan).
Guided setup
Connect Tilda to Claude, ChatGPT or Copilot in 2 minutes
Start a free trial on AnythingMCP Cloud, connect Tilda in the guided setup, then add your MCP URL to your AI assistant. No code and no server to run.
No credit card · 7-day trial · Self-host alternative available
Try asking
Example prompts for Tilda
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Tilda, paste your credentials, mint an MCP API key and you're done. No Docker, no
git clone, no local server.
Tilda
Tilda Publishing website builder, read-only API: projects, project settings, page lists and the published HTML of pages, as markup or prepared for export to your own server. Public key and secret key (Business plan).
Setup
Setting up takes about 3 minutes.
- The API is part of the Tilda Business plan. On the Free and Personal plans the keys cannot be created.
- In Tilda open a project, then Site Settings, Export, API Integration, and generate the keys.
- Copy the Public Key into
TILDA_PUBLIC_KEYand the Secret Key intoTILDA_SECRET_KEY.tilda_list_projectsshows which projects the keys reach.
Every call sends the two keys as the query parameters publickey and secretkey.
Where to start: tilda_list_projects gives the project ids, tilda_list_pages the pages of a project.
Tools: tilda_get_project (domain, export paths, home page), tilda_get_page (body HTML with script and style lists), tilda_get_page_full (complete HTML document), tilda_get_page_export and tilda_get_page_full_export (the same two, with links rewritten to local files and a list of the files to download).
Rate limit: 150 requests per hour for the account. Tilda blocks accounts that poll the API, so read a page once and keep working with that copy; never fetch all pages of a large site in a loop. Listing projects and pages costs one request each.
Reading the answers: every answer has status, which is FOUND on success, and result. Ids are numbers written as text. published is the Unix time of the last publication; date is the creation time as YYYY-MM-DD HH:MM:SS. The API is made for synchronising published pages: publish a page in Tilda before reading its HTML here.
Images and files: img, featureimg and the from entries are addresses on the Tilda servers. The export tools also give the local file name (to) the HTML expects, built from the export paths of the project (tilda_get_project).
Errors: Tilda answers a failed call with status ERROR and a message, usually with HTTP status 409. Wrong public key or a message about the secret key: check the two keys. Other messages name the missing or unknown parameter, such as a project or page id that does not exist in this account.
Prerequisites: TILDA_PUBLIC_KEY, TILDA_SECRET_KEY
Install the connector locally
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Open http://localhost:3000/connectors/store, pick Tilda and paste in the env vars listed under Prerequisites.
Available tools
| Tool | What it does |
|---|---|
tilda_list_projects | List the Tilda projects (websites) of the account: id, title and descr (description). Start here: every other call needs a project id or a… |
tilda_get_project | Read the settings of one project: id, title, descr, customdomain, the export paths for images, scripts and styles (export_imgpath… |
tilda_list_pages | List the pages of a project: id, projectid, title, descr (description), img and featureimg (preview images), alias (the address of the… |
tilda_get_page | Read one page with the HTML of its body: id, projectid, title, descr (description), img and featureimg (preview images), alias (the address… |
tilda_get_page_full | Read one page as a complete HTML document: id, projectid, title, descr (description), img and featureimg (preview images), alias (the… |
tilda_get_page_export | Read one page prepared for hosting on your own server, body only: id, projectid, title, descr (description), img and featureimg (preview… |
tilda_get_page_full_export | Read one page prepared for hosting on your own server as a complete HTML document: id, projectid, title, descr (description), img and… |
Example prompts
- "List my Tilda projects and their domains."
- "Which pages does the project Landing 2026 have, and when was each published?"
- "Get the HTML of the pricing page and check its headings for SEO."
- "Which images and files would I need to download to export the home page?"
- "Compare the meta titles of all pages in project 4512345."
Next steps
Was this guide helpful?