fdbck
Hosted MCP server to triage, approve and retry user feedback from your coding agent
- Pricing
- Freemium
- Platforms
- API, vscode, CLI
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
About fdbck
fdbck is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
The README-style docs describe fdbck's MCP endpoint as a way to reach your feedback inbox from inside Claude Code, Cursor or VS Code. Instead of switching to the dashboard, you can list new reports, read an item's message and run history, and approve a triaged item so a local worker writes the fix and opens a draft pull request.
Authentication reuses the worker token you already have, sent as a bearer header over Streamable HTTP. Approving a fix only enqueues the job and returns immediately, so the agent polls get_run_status to follow progress. The actual fix runs on your own machine with your own AI subscription, and fdbck stores no model keys.
The server suits solo developers and small teams who collect feedback from users and want an agent to handle the routine triage and first-pass fixes. Notes you add to an item are read by later agent runs, but adding a note never starts a run by itself.
Install
Run in a terminal
claude mcp add --transport http fdbck https://fdbck.app/api/mcpAdd to Settings → Connectors → Add custom connector
https://fdbck.app/api/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"fdbck": {
"url": "https://fdbck.app/api/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"fdbck": {
"type": "http",
"url": "https://fdbck.app/api/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"fdbck": {
"serverUrl": "https://fdbck.app/api/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"fdbck": {
"type": "http",
"url": "https://fdbck.app/api/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
Tools this server provides (9)
Taken from the project documentation; the running server may differ.
- list_feedback
- Compact inbox rows, newest first, with project, view and pagination filters.
- get_feedback
- Full detail for one feedback item, including run history and PR links.
- get_run_status
- Current run phase and live progress for an item.
- approve_fix
- Approves a triaged item so the worker writes a fix and opens a draft PR.
- dismiss_feedback
- Marks an item as won't-fix or not actionable.
- retry_item
- Requeues the failed phase for an item whose last run failed.
- list_notes
- Reads the owner notes on an item.
- add_note
- Appends guidance to an item without starting a run.
- run_phase
- Queues a triage or planning run for an item.
What it does
- Inbox listing
- Lists feedback rows newest first, filterable by project and view, with pagination.
- Item inspection
- Returns the full message, triage result, owner notes and run history for one item.
- Fix approval
- Approves a triaged item so the local worker writes a fix and opens a draft PR.
- Run polling
- Reports the current run phase and live progress for an item after approval or retry.
- Owner notes
- Lets agents read and append durable guidance that later triage and planning runs take into account.
- Retry and dismiss
- Requeues a failed phase or marks an item as won't-fix.
Good for
- Reviewing overnight user feedback from inside a coding session
- Approving obvious bug reports so a local agent drafts the fix PRs
- Following a fix run's progress without opening the dashboard
- Adding guidance to an item so the next triage run considers it
Pricing
Freemium, from $15 a month
Free for one project; Pro is $19 flat or $15/mo billed yearly.
Prices change. Check fdbck.app before you buy.
fdbck FAQ
How do I authenticate?
Use your existing worker token (wt_...) from Account → Local worker as a bearer Authorization header on the MCP endpoint.
Does approving a fix run immediately?
approve_fix enqueues the job and returns at once; the fix runs on your machine through the local worker, and you poll get_run_status for progress.
What does the Free plan include?
The Free plan covers one project with unlimited feedback, AI triage, agent fixes and draft PRs, with fdbck branding on the public board.
Are AI fixes metered?
The pricing page says AI triage, fixes and draft PRs are never metered on any tier, since they run on the user's own agent subscription.
Is fdbck free?
fdbck has a free plan, with paid plans for more usage or features. Paid plans start at $15 a month.
How do I add fdbck to Claude Code?
Run this command in your terminal: claude mcp add --transport http fdbck https://fdbck.app/api/mcp
What are the best alternatives to fdbck?
The closest alternatives to fdbck are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.
Alternatives to fdbck

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