Feeduna
MCP connector that lets AI clients read and submit Feeduna customer feedback for your app
- Pricing
- Free trial
- Platforms
- CLI, API, self-hosted
- Runs
- Locally
- Version
- 0.1.1
- Listing updated
- today
About Feeduna
Feeduna is an MCP server for developer tools. It runs locally on your machine and is started by your AI client.
The README describes Feeduna's MCP connector as a local stdio bundle that brings feedback from a Feeduna app into a compatible MCP host. Access is controlled by a scoped, expiring key created in App setup, with separate permissions for reading setup guidance, reading reports, and submitting new feedback.
The connector exposes five tools: one for setup details, two for listing and fetching feedback receipts, one for paginated export, and one for submitting a report. Write access is optional and off unless the key grants it. Submission uses a stable receipt UUID so retries do not create duplicate reports.
The documentation says the connector cannot send issues to Linear, manage keys or change billing. Reporter text is treated as untrusted data. It is aimed at product and development teams who collect feedback through the Feeduna widget and want an assistant to summarise it.
Install
Run in a terminal
claude mcp add mcp --env FEEDUNA_API_TOKEN='<FEEDUNA_API_TOKEN>' -- npx -y https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpbAdd to claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpb"
],
"env": {
"FEEDUNA_API_TOKEN": "<FEEDUNA_API_TOKEN>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpb"
],
"env": {
"FEEDUNA_API_TOKEN": "<FEEDUNA_API_TOKEN>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpb"
],
"env": {
"FEEDUNA_API_TOKEN": "<FEEDUNA_API_TOKEN>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpb"
],
"env": {
"FEEDUNA_API_TOKEN": "<FEEDUNA_API_TOKEN>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpb"
],
"env": {
"FEEDUNA_API_TOKEN": "<FEEDUNA_API_TOKEN>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
FEEDUNA_API_TOKENScoped, expiring access key created in Feeduna App setup. Grant only the permissions needed.Required
Tools this server provides (5)
Taken from the project documentation; the running server may differ.
- feeduna_get_setup
- Read app details and installation guidance
- feeduna_list_feedback
- Read one bounded page of feedback
- feeduna_get_feedback
- Read one receipt by UUID
- feeduna_export_feedback
- Read one bounded export page
- feeduna_submit_feedback
- Create a feedback receipt
What it does
- Scoped access keys
- Keys are limited to setup, read or submit permissions and expire within 90 days.
- Feedback reading tools
- Tools list pages of reports, fetch a single receipt by UUID and export paginated feedback.
- Optional feedback submission
- A reports:write permission enables creating new feedback receipts from the MCP host.
- Local stdio transport
- Runs as a local Node.js process, not a hosted remote endpoint or OAuth connection.
- Untrusted content handling
- Reporter text and context are marked as data and do not authorise downstream actions.
Good for
- Summarise recent customer feedback for an app inside an AI assistant
- Group reported problems and cite receipt IDs before planning fixes
- Export feedback pages for analysis in a local MCP host
- Submit a feedback report from an assistant when write access is granted
Pricing
Free trial
Feeduna offers a 14-day trial; paid subscription is EUR25 per month per the README.
Prices change. Check app.feeduna.com before you buy.
Feeduna FAQ
Which runtime does the connector need?
The README says it requires Node.js 22 or later and runs as a local stdio connector.
Can the connector create Linear issues?
No. The docs say it cannot send issues to Linear; that delivery is an explicit action in the Feeduna inbox.
How is the connector licensed?
The README says the connector source is MIT licensed, which does not cover the Feeduna backend, service or brand.
What permissions are needed to read feedback?
Reading feedback requires the reports:read scope; submitting requires reports:write, which is optional.
Is Feeduna free?
Feeduna is a paid product with a free trial.
How do I add Feeduna to Claude Code?
Run this command in your terminal: claude mcp add mcp --env FEEDUNA_API_TOKEN='<FEEDUNA_API_TOKEN>' -- npx -y https://github.com/performeon/feeduna-mcp/releases/download/v0.1.1/feeduna-mcp-0.1.1.mcpb
What are the best alternatives to Feeduna?
The closest alternatives to Feeduna are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Where this comes from
- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.
Alternatives to Feeduna

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 467K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.8K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
- Remote
- Open source
- 34.6K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools