MCP Server

Connect your AI to user feedback

MCPFeedback exposes an MCP server that lets AI assistants read, create, and manage feedback items — including posting fix notes that notify reporters. Works with Claude, Cursor, Windsurf, ChatGPT, and any MCP-compatible client.

What your AI can do

Once connected, your AI assistant gets these tools automatically:

list_feedback

List feedback items with filters for status, severity, and site. Supports pagination.

siteId, status, severity, limit, cursor

get_feedback

Get full details of a specific feedback item including metadata and screenshots.

feedbackId

update_feedback_status

Update the status of a feedback item (new → accepted → in_progress → resolved).

feedbackId, status

create_feedback

Create a new feedback item programmatically with title, details, and severity.

siteId, title, details, severity, reporterEmail

list_sites

List all sites in your account with their domains and configuration.

includeInactive

post_fix_notes

Post a fix or resolution note on a feedback item. Optionally emails the reporter with the update.

feedbackId, content, notifyReporter

Quick setup

Pick your client. The whole setup takes under 2 minutes.

Before you start

  1. Create an MCPFeedback account (free trial, no credit card)
  2. Go to MCP & API Keys and generate an API key
  3. Copy the config below and paste your key
1Open your terminal
2Run the command below
3Claude Code will confirm the server was added
terminal
claude mcp add mcpfeedback \
  --transport http \
  --url https://mcpfeedback.com/api/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with the key from your dashboard.

Authentication

All requests to the MCP server require a valid API key passed via the Authorization header.

header
Authorization: Bearer mcpf_abc123...

Scoped access

Keys are scoped to your account. Each key can access all sites in your account.

Revocable

Revoke any key instantly from your dashboard. Takes effect immediately.

Usage tracking

See when each key was last used in your API Keys dashboard.

Try these prompts

Once connected, try asking your AI assistant:

Show me all unresolved bug reports
What feedback did we get this week?
Mark feedback #FB-1042 as resolved
Create a bug report for the login page
List all my sites and their status
What are the most critical issues?
Post a fix note on #FB-1042 saying we fixed the layout bug
Let the reporter know we shipped a fix for their issue

Server details

Server URLhttps://mcpfeedback.com/api/mcp
TransportStreamable HTTP (JSON-RPC)
AuthBearer token via Authorization header
Tools6 tools (list, get, update, create feedback + list sites + post fix notes)

Ready to connect?

Create your account and generate an API key to get started.

MCPFeedback — The complete feedback loop