Elfsight MCP Server
OfficialThis server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Elfsight — MCP Server
This repository holds the documentation and the registry manifest (
server.json) of the Elfsight MCP server. The server itself is hosted by Elfsight; there is nothing to build or run here. For help, contact Elfsight Help Center.
A remote Model Context Protocol server over your Elfsight workspace. Point an MCP-capable AI agent at it and it can browse your apps, projects and widgets, create widgets from templates, change their settings, publish them and hand you the install code — without you clicking through the Dashboard.
The server is workspace-scoped: when you sign in, you pick one Elfsight workspace, and the agent can reach only the apps, projects and widgets of that workspace.
Server URL: https://mcp.elfsight.com/mcp (Streamable HTTP).
Connect
Sign-in is OAuth. Add the server URL to your MCP client; the client opens a browser window, you sign in to Elfsight, choose the workspace and approve access. There is no key to copy.
Claude (claude.ai, Desktop, mobile)
In Claude, open Settings → Connectors, choose Add custom connector and enter the server
URL https://mcp.elfsight.com/mcp, then sign in to Elfsight and approve access. On Team and
Enterprise plans an organization Owner may need to add the connector first.
Claude lists nine tools as read-only and six as write tools; on the connector's page you choose for each group whether Claude asks before calling it.
Claude Code
claude mcp add --transport http elfsight https://mcp.elfsight.com/mcpThen run /mcp inside Claude Code and choose Authenticate for elfsight.
Cursor
This repository is also a Cursor plugin: the manifest
is in .cursor-plugin/plugin.json, the server connection in
mcp.json, and a rule with usage notes for the agent in rules/.
To connect without the plugin, add the server to .cursor/mcp.json and authenticate it when
Cursor prompts:
{
"mcpServers": {
"elfsight": {
"url": "https://mcp.elfsight.com/mcp"
}
}
}Cline
In Cline, open MCP Servers → Remote Servers and add:
Server Name:
elfsightServer URL:
https://mcp.elfsight.com/mcpTransport: Streamable HTTP
Then choose Authenticate for the server and sign in to Elfsight in the browser.
The same in Cline's own settings file, cline_mcp_settings.json. Recent versions keep it in
~/.cline/data/settings/, older ones in the editor's
User/globalStorage/saoudrizwan.claude-dev/settings/. Keep type: without it Cline falls
back to the legacy SSE transport. .vscode/mcp.json belongs to VS Code's built-in MCP
support; Cline does not read it.
{
"mcpServers": {
"elfsight": {
"type": "streamableHttp",
"url": "https://mcp.elfsight.com/mcp"
}
}
}Other clients
Any client that supports remote MCP servers with OAuth (dynamic client registration and PKCE) should connect with the server URL alone.
VS Code:
or add it to
.vscode/mcp.json:
{
"servers": {
"elfsight": {
"type": "http",
"url": "https://mcp.elfsight.com/mcp"
}
}
}Windsurf (mcp_config.json):
{
"mcpServers": {
"elfsight": {
"serverUrl": "https://mcp.elfsight.com/mcp"
}
}
}Related MCP server: Taskade MCP Server
What you can ask it
Reads:
list_app_catalog— "Which Elfsight apps are there?"list_account_apps— "Which apps do I have in my workspace?"list_projects— "List my projects."list_widgets— "Show my Instagram Feed widgets in theLandingproject."get_widget— "What are the current settings of widget<id>?"get_widget_limit— "How many more Google Reviews widgets can I create?"list_widget_templates— "What templates does the Pricing Table app have?"get_install_code— "Give me the embed code for this widget."get_widget_edit_links— "Give me the link to edit this widget in the Dashboard."
Writes:
create_widget— "Create a Countdown Timer from the Black Friday template."duplicate_widget— "Make a copy of this widget."rename_widget— "Rename it toHomepage reviews."update_widget_settings— "Change the header text and the accent color."publish_widget— "Publish the changes."discard_widget_changes— "Throw away the unpublished changes."
How widget changes work
Widgets are created from templates.
create_widgetneeds an app alias and an active template of that app (fromlist_widget_templates). The new widget is published right away; when the app's widget limit is reached it is saved as a draft (status: DRAFT).Settings changes are drafts until published.
update_widget_settingsapplies a JSON Merge Patch to the unpublished revision: objects merge,nullremoves a key, arrays are replaced as a whole. The site keeps showing the published version untilpublish_widgetis called;discard_widget_changesdrops the draft. The draft is shared with the Dashboard editor, so publishing or discarding also covers any unpublished edits you made there.The publish link publishes on open.
get_widget_edit_linksreturnseditUrlandpublishUrl; openingpublishUrlin a browser where you are signed in to Elfsight publishes the draft immediately.Sensitive settings are protected. Each app declares restricted settings (secrets, connected accounts and similar). Changes to them are rejected; edit those in the Dashboard.
Nothing is deleted. The server has no tool that deletes widgets or projects.
Privacy
Everything a tool returns can be sent to your AI provider (Anthropic, OpenAI, etc.) as part of your conversation with the agent. Widget settings contain whatever you put in your widgets — texts, links, images and, for some apps, contact details. Treat tool results accordingly.
Limits and rate limiting
list_widgetsandlist_widget_templatesreturn pages of up to 100 items (page,itemsPerPage).Requests are rate-limited per client: 60 tool calls per minute. Going over the limit returns a
429with aRetry-Afterheader — wait and retry.
Support
Questions or issues — contact Elfsight Help Center or your account manager.
This server cannot be deployed
Maintenance
Related MCP Connectors
List, read, edit, and deploy your GenMB AI-generated apps from any MCP client.
Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.
1
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to read and modify Mendix application models through MCP tools for creating modules, entities, pages, microflows, deploying, and querying runtime data.1ISC
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants like Claude, Cursor, VS Code, and Windsurf to manage workspaces, projects, tasks, and AI agents through natural language, with a hosted OAuth server or a local stdio package. Also supports generating MCP tools from any OpenAPI spec.1,834 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI clients such as Claude, Cursor, VS Code, and Windsurf to list and manage workspaces, projects, tasks, AI agents, and automations through a hosted OAuth-secured endpoint or a local stdio package. Also generates MCP tools from any OpenAPI spec.1,834 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants and IDEs to manage workspaces, projects, tasks, and AI agents through natural language, including creation, updates, completion, assignment, and automation. It also supports generating MCP tools from arbitrary OpenAPI specs for broader API integration.1,834 npmMIT