Kleap
MCP server by Kleap
Create, edit and publish websites and web apps with an AI agent on the Kleap builder.
Connect to Kleap
Kleap needs sign-in. Connect with its own URL:
Your client opens Kleap’s sign-in the first time you use it. The token stays between your client and Kleap.
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/kleapAbout
Connects an AI assistant to Kleap, an AI builder for websites, web apps and internal tools. Granted scopes cover apps, messages, tasks, forms, analytics and database read and write access, so an agent can create and change projects and look at their data.
The server is hosted at https://kleap.co/api/mcp and uses the streamable HTTP transport. Access needs a Kleap account and credentials from Kleap. Kleap's OAuth server supports dynamic client registration.
What you can do
- Create, update and delete Kleap apps and sites
- Send build messages to the AI builder
- Read task status
- Read form submissions
- Read analytics for published projects
- Read and write project database data
Tools 35
create_appWritesCreate Website
modify_appCan deleteModify Website
write_filesCan deleteWrite Files Directly
edit_filesCan deleteEdit Files In Place
generate_imageCan deleteGenerate Image
delete_filesCan deleteDelete Files
list_app_filesRead-onlyList App Files
read_filesRead-onlyRead File Contents
list_appsRead-onlyList My Websites
get_appRead-onlyGet Website Details
seo_auditRead-onlySEO Audit
find_appRead-onlyFind Website by Address
Show 23 more tools
rename_appWritesRename Website
get_screenshotWritesScreenshot Website
check_taskWritesCheck Build Status
retry_taskCan deleteRetry Build
get_creditsRead-onlyCheck usage
upgrade_planRead-onlyUpgrade Plan
wake_appWritesWake Website
publish_appCan deletePublish Website
get_publish_statusRead-onlyCheck Publish Status
search_domainsRead-onlySearch Domains
check_domainWritesCheck Domain
connect_domainWritesConnect Domain
get_form_submissionsRead-onlyGet Form Submissions
get_analyticsRead-onlyGet Site Analytics
get_search_consoleRead-onlyGet Google Search Performance
connect_search_consoleWritesConnect Google Search Console
get_database_schemaRead-onlyGet Database Schema
query_database_rowsRead-onlyQuery Database Rows
insert_database_rowsWritesInsert Database Rows
update_database_rowsCan deleteUpdate Database Rows
delete_database_rowsCan deleteDelete Database Rows
run_database_sqlCan deleteRun Database SQL
buy_domainWritesBuy Domain
Read from the live server on 18 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.
Example prompts
Create a landing page for my pottery studio on Kleap
Update the hero text on my Kleap portfolio site
Show analytics for my Kleap project
List the form submissions from my Kleap site
Set up
Every client connects to kleap.co, and Kleap asks you to sign in the first time. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http kleap https://kleap.co/api/mcp- Start Claude Code, type
/mcp, pick kleap and choose Authenticate. A browser window opens for the Kleap sign-in.
Add --scope user to make it available in every project, not just this one.
Claude Desktop
- Open Customize → Connectors, click + Add, then Add custom connector.
- Name it Kleap and paste this URL:
https://kleap.co/api/mcp- Click Add, then Connect, and sign in when Kleap asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://kleap.co/api/mcpand click Add. - Click Connect and sign in when Kleap asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
ChatGPT
- On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
- Enter a name for the server.
- Under Connection, paste
https://kleap.co/api/mcpas the server URL, then for authentication choose OAuth. ChatGPT sends you to Kleap to sign in. - Check I understand and want to continue, then select Create as a plugin.
Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"kleap": {
"url": "https://kleap.co/api/mcp"
}
}
}Cursor shows Needs authentication next to the server. Click the button beside it to sign in.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"kleap","type":"http","url":"https://kleap.co/api/mcp"}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"kleap": {
"type": "http",
"url": "https://kleap.co/api/mcp"
}
}
}VS Code asks you to sign in the first time the server starts.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"kleap": {
"serverUrl": "https://kleap.co/api/mcp"
}
}
}- Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.
Codex
codex mcp add kleap --url https://kleap.co/api/mcp
codex mcp login kleapOr edit ~/.codex/config.toml directly:
[mcp_servers.kleap]
url = "https://kleap.co/api/mcp"Gemini CLI
gemini mcp add --transport http kleap https://kleap.co/api/mcpThen, inside Gemini CLI, run /mcp auth kleap to sign in.
This adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"kleap": {
"type": "http",
"url": "https://kleap.co/api/mcp"
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://kleap.co/api/mcp.
Embed
Show Kleap in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/kleap)<a href="https://mcp.tc/i/kleap"><img src="https://mcp.tc/i/kleap/badge.svg" alt="Kleap on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/kleap.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/kleap" title="Kleap on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/kleap.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Kleap card to your site.
Add the mcp.tc card for Kleap, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/kleap.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="kleap"><a href="https://mcp.tc/i/kleap">Kleap on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/kleap)
```
Reference: https://mcp.tc/embedChange history
We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 05:39 UTC.
-
1 tool changed. Server instructions changed.
New server instructions
Details, 12 Nov 2026, 02:52 UTC
Changed 1
get_publish_statusdescriptionBeforeUse this to checkwhethera websiteisactuallypublished andlive. Returns the published state, theliveproduction URL,and— onceapublish has run — the PUBLISH REPORT of what Kleap checked on the site it just built: broken_links (existing pages that fail), dead_nav_links (menu entries pointing at a page thatwasnever written — 90% of real dead links, /contact most often), incoherent_pages (a page answering 200 with content that contradictsthelink leading to it), checks (sourcefindingsthat didNOTblockthepublish, each with a categoryanda plain sentence:forms that submit into the void,islands with no client directive sobuttons do nothing,broken images,hand-rolledauth or unguarded database access, dead API routes), design_gate (wastherendered homepage looked at), live_verified (was the NEW version confirmed serving), and SEO coverage (JSON-LD pages, sitemap URL count, robots, llms.txt). report.checked:true means the audit RAN, so empty lists mean nothing was found,…AfterCheck whether the site is published and return its live URL and latest report: broken_links, dead_nav_links, incoherent_pages, checks, design_gate, live_verified and SEO coverage. report.checked:true means a report was produced; report.audit_ran:false means the link, form and design audit did not run for this deploy, so findings are unavailable. Do NOT describe a publish as clean unless the audit ran. Read the report and offer fixes for findings, including forms that submit into the void, buttons do nothing, and hand-rolled auth. If audit_ran is false, run seo_audit on production_url. status is one of: published, deploying, not_published, unknown_app. This is the current state; do not poll repeatedly.
Server instructions
BeforeKleap builds, HOSTS and AUDITS real websites (Astro). You have TWO ways to put code on a site: (A) write_files — YOUR model writes the exact file contents and you push them with write_files; Kleap stores, builds and deploys them as-is (deterministic, best when the exact wording, URL or schema matters); (B) modify_app — describe the OUTCOME and Kleap's AI writes the files (best for design and whole sections, and it knows the template's own components, auth, database and form wiring). Either way Kleap HOSTS it (build, deploy, SSL, DB, auth, domains, verified-live) and CHECKS it: publishing audits every internal link on every built page, flags pages whose content contradicts the link leading to them, and measures JSON-LD/sitemap/robots coverage — get_publish_status returns
that as areportfield. Readthereportinstead ofre-auditingthe siteyourself.list_app_files shows the structure (Astro: src/pages/*.astro, src/data/*.json, src/components/*.astro, public/*). EDIT EXISTING FILES SAFELY — never rewrite a file blind. Do: list_app_files → read_files(app_id, [paths]) to get the CURRENT contents → edit_files to change ONLY the lines that must change → publish_app. Use edit_files whenever the file exists: send old_string and new_string, Kleap replaces in place. Resending a 30KB layout to fix one line wastes tokens and risks corrupting the rest. write_files stays for NEW files, wholesale replacement and images. This is the reliable way to fix shared components, headers/footers, wrong numbers, broken links, dead forms. read_files works with a Read-only key, so always read before you change. Prefer this read→edit→write loop over modify_app for precise, verifiable edits. That loop is complete: edit_files changes part of a file, write_files takes encoding:"base64" for IMAGES and binaries (logo, photo, OG image, favicon, font), and delete_filesREMOVES a page or asset — never blank a file to "delete" it, that leaves a URL answering 200 with nothing. WHAT AGENTS ACTUALLY D…AfterKleap builds, HOSTS and AUDITS real websites (Astro). You have TWO ways to put code on a site: (A) write_files — YOUR model writes the exact file contents and you push them with write_files; Kleap stores, builds and deploys them as-is (deterministic, best when the exact wording, URL or schema matters); (B) modify_app — describe the OUTCOME and Kleap's AI writes the files (best for design and whole sections, and it knows the template's own components, auth, database and form wiring). Either way Kleap HOSTS it (build, deploy, SSL, DB, auth, domains, verified-live) and CHECKS it: publishing audits every internal link on every built page, flags pages whose content contradicts the link leading to them, and measures JSON-LD/sitemap/robots coverage — get_publish_status returns the SEO coverage on almost every publish, and the link/form/design audit when the report says audit_ran:true. When audit_ran is false, run seo_audit on the production_url instead of assuming the site is clean. list_app_files shows the structure (Astro: src/pages/*.astro, src/data/*.json, src/components/*.astro, public/*). EDIT EXISTING FILES SAFELY — never rewrite a file blind. Do: list_app_files → read_files(app_id, [paths]) to get the CURRENT contents → edit_files to change ONLY the lines that must change → publish_app. Use edit_files whenever the file exists: send old_string and new_string, Kleap replaces in place. Resending a 30KB layout to fix one line wastes tokens and risks corrupting the rest. write_files stays for NEW files, wholesale replacement and images. This is the reliable way to fix shared components, headers/footers, wrong numbers, broken links, dead forms. read_files works with a Read-only key, so always read before you change. Prefer this read→edit→write loop over modify_app for precise, verifiable edits. That loop is complete: edit_files changes part of a file, write_files takes encoding:"base64" for IMAGES and binaries (logo, photo, OG image, favicon, font), and delete_files RE…
-
3 tools changed.
Details, 9 Nov 2026, 08:52 UTC
Changed 3
get_analyticsdescriptionBeforeUse this when the user asks about traffic, visitors, or which pages/referrers are performing on their PUBLISHED site. Backed by the same analytics as the Kleap dashboard's Visitors view. Returns zeroed data with configured:false if the app has never been published (analytics is set up automatically on publish). Requires the analytics:read scope — sessions connected BEFORE this tool shipped don't have it: on
a 403INSUFFICIENT_SCOPEerror, telltheuser to disconnectandreconnect the Kleap integration (re-authorize)tograntthe scope.AfterUse this when the user asks about traffic, visitors, or which pages/referrers are performing on their PUBLISHED site. Backed by the same analytics as the Kleap dashboard's Visitors view. Returns zeroed data with configured:false if the app has never been published (analytics is set up automatically on publish). Requires the analytics:read scope — sessions connected BEFORE this tool shipped don't have it: on INSUFFICIENT_SCOPE the connection has NOT expired: it was authorized before this tool existed and needs one re-authorization to add the scope. Say that, never that it expired.
get_form_submissionsdescriptionBeforeUse this when the user asks who filled out their contact form, or wants to see/export leads from their live site. Returns submissions from any <form> built with KleapForm on the app, newest first. Empty list is normal for a brand new site with no visitors yet. Requires the forms:read scope (submissions contain visitor PII) — sessions connected BEFORE this tool shipped don't have it: on
a 403INSUFFICIENT_SCOPEerror, telltheuser to disconnectandreconnect the Kleap integration (re-authorize)tograntthe scope.AfterUse this when the user asks who filled out their contact form, or wants to see/export leads from their live site. Returns submissions from any <form> built with KleapForm on the app, newest first. Empty list is normal for a brand new site with no visitors yet. Requires the forms:read scope (submissions contain visitor PII) — sessions connected BEFORE this tool shipped don't have it: on INSUFFICIENT_SCOPE the connection has NOT expired: it was authorized before this tool existed and needs one re-authorization to add the scope. Say that, never that it expired.
get_search_consoledescriptionThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
-
2 tools changed.
Details, 1 Nov 2026, 11:49 UTC
Changed 2
connect_search_consoledescriptionBeforeUse this when the user wants to connect (or reconnect) Google Search Console for a site — typically right after get_search_console reported connected:false. Returns a consent_url: give it to the user as a link and ask them to open it and approve access with the Google account that owns the domain in Search Console. That one approval MUST happen in a browser — Google does not allow it any other way, so never claim you can do it for them. Nothing else is needed afterwards: the Search Console property is bound to the site's custom domain automatically, and get_search_console starts answering. If requires_custom_domain is true the site has no custom domain yet: connecting Google would grant access to nothing, so connect a domain first (connect_domain) and publish.
If it reports the site is already connected, do not send anyone through consent again —just read the numbers.AfterUse this when the user wants to connect (or reconnect) Google Search Console for a site — typically right after get_search_console reported connected:false. Returns a consent_url: give it to the user as a link and ask them to open it and approve access with the Google account that owns the domain in Search Console. That one approval MUST happen in a browser — Google does not allow it any other way, so never claim you can do it for them. Nothing else is needed afterwards: the Search Console property is bound to the site's custom domain automatically, and get_search_console starts answering. If requires_custom_domain is true the site has no custom domain yet: connecting Google would grant access to nothing, so connect a domain first (connect_domain) and publish. Already connected? It returns a consent_url too, but hand that over ONLY to switch Google account; otherwise just read the numbers.
get_search_consoledescriptionBeforeUse this when the user asks how their site
is doingIN GOOGLE SEARCH —keywords/queriesthey rank for, impressions,clicks from search,CTR,oraverage position.Backed bytheir ownGoogle Search Console property (connected per site in Kleap's options), so it is the real Google data,not an estimate. Returns totals plusthetop queries and toppages that produced them. Search Consolelagsreal traffic by~2days —the newest days are alwaysincomplete,say so rather than reporting a drop. If connected isfalse or site_selected isfalse,the site simply has no Search Console hooked up:call connect_search_console(app_id) — it returns a consent_url to hand theuser,and thatisthe wholesetup.Do NOT send them hunting through Kleap'ssettings for it. For visitors and pageviews onthesite itself (all sources,notjust Google), use get_analytics instead. Requirestheanalytics:read scope—ona403 INSUFFICIENT_SCOPE error, telltheuser to disconnectandreconnecttheKleap integration…AfterUse this when the user asks how their site does IN GOOGLE SEARCH — queries they rank for, impressions, clicks, CTR, average position. Real Search Console data from their own property, not an estimate. Returns totals plus top queries and top pages. It lags ~2 days, so the newest days are always incomplete — say so rather than reporting a drop. If connected is false, call connect_search_console(app_id) — it returns a consent_url to hand the owner, and that IS the whole setup: the property matching the site's domain is bound automatically as soon as they approve. Do NOT send them hunting through Kleap's settings. If site_selected is false the message names the cause — read it, do not guess: the site has no custom domain (connect_domain first — a {slug}.kleap.io host can never be a Search Console property), or the Google account has no VERIFIED property for that domain yet (add and verify it, then read again — Kleap binds it). For all-source visitors use get_analytics. Requires the analyt…
-
Tracking started: 35 tools.
FAQ
Can I paste mcp.tc/i/kleap into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://kleap.co/api/mcp, so your client talks to Kleap directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Kleap need an API key or a sign-in?
Yes, you need a Kleap account. The first time your client connects, it opens Kleap’s sign-in page. The token goes straight to the server’s own URL, never through mcp.tc.
Is Kleap a remote or a local server?
Remote. Kleap hosts it at https://kleap.co/api/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Kleap do?
It has 35 tools, including create_app, modify_app and write_files. You can create, update and delete Kleap apps and sites, send build messages to the AI builder and read task status.
Which clients can use it?
Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.
Does mcp.tc track changes to Kleap?
Yes. Kleap’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Kleap’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Kleap. This page was built from Kleap’s public metadata, last checked on 18 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.