yanifend-mcp
Hosted MCP server for YaniFend, a WordPress feedback widget. Manage your questionary (list/create/update/delete questions and options) and read collected answers via natural language.
README
YaniFend MCP Server
Manage your YaniFend feedback questionary and read collected answers directly from Claude (Desktop, Code, or claude.ai) via the Model Context Protocol.
YaniFend is a WordPress-native feedback widget that lets visitors leave structured feedback on your site. This MCP server lets an LLM client work with the YaniFend backoffice on behalf of a logged-in site owner — list personages, manage questions, and pull in collected answers — without leaving the chat.
Recommended: hosted endpoint
https://app.yanifend.com/mcp
Streamable HTTP transport, OAuth 2.1 (PKCE + RFC 7591 Dynamic Client Registration). No pre-registration — Claude Desktop / claude.ai auto-register on first connect, then prompt you to log in to YaniFend (Google / GitHub / Facebook / LinkedIn / email).
Claude Desktop / claude.ai
Add a custom connector:
- Name: YaniFend
- URL:
https://app.yanifend.com/mcp
Claude Code
claude mcp add --transport http yanifend https://app.yanifend.com/mcp
Alternative: local stdio wrapper (this repo)
This repository ships a tiny stdio MCP wrapper, mainly so the server can be introspected by registries like Glama and mcp.directory. It advertises the same tool surface as the hosted endpoint but delegates actual execution there — calling a tool returns a hint to use the hosted URL, because tool calls need an authenticated YaniFend account.
npx -y yanifend-mcp
# or
docker build -t yanifend-mcp . && docker run --rm -i yanifend-mcp
Tools
| Tool | What it does |
|---|---|
list_personages |
List the feedback personages defined on the connected YaniFend site |
list_questions |
Read the current questionary |
create_question |
Add a new question |
update_question |
Edit an existing question's text, type, or order |
delete_question |
Remove a question |
list_question_options |
List options for a multiple-choice question |
create_question_option |
Add an option to a question |
update_question_option |
Edit an option |
delete_question_option |
Remove an option |
list_answers |
Pull the latest collected answers |
Every tool is scoped to the authenticated YaniFend account — you only see and edit your own site's data.
About YaniFend
yanifend.com — a WordPress plugin that lets HR / recruiter / SaaS sites collect structured visitor feedback with personage-based segmentation. The MCP server is the LLM-native way to manage your YaniFend instance.
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.