Skip to content
MCP server

Feedbacks

Self-hosted visual feedback and session replay that coding agents can read through MCP

Runs locallyStatus and history
Pricing
Open source
Platforms
self-hosted, Chrome extension, Web
Runs
Locally
Version
0.2.3
Listing updated
2 days ago

About Feedbacks

Feedbacks is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Feedbacks is a team tool for reporting website problems with the evidence attached: pinned and annotated screenshots, suggested text replacements, video and session recordings with console, network and performance timelines. The MCP bridge lets Claude Code, Codex or another agent read that material, including scoped evidence from a thread, approved project instructions and each person's assigned work, so it can propose where to start and make the agreed change.

It is built to be self-hosted. One server installation, backed by PostgreSQL and S3-compatible storage, serves one organisation, and the Chrome extension connects to it by URL. The README says it is an early 0.x release and that public registration, billing, SSO and shared-database multi-tenancy are not implemented. A Docker install script is provided for trying it locally.

Other parts include assignments, tags and saved views, optional GitHub Issues sync, guest review links, PDF and image review, surveys, signed webhooks and downloadable bundles with checksums. The license is Apache-2.0, and the vendor says the complete product is free; you supply the infrastructure and any AI tools.

Install

Run in a terminal

claude mcp add feedbacks -- npx -y https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb

Add to claude_desktop_config.json

{
  "mcpServers": {
    "feedbacks": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "feedbacks": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "feedbacks": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "feedbacks": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "feedbacks": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb"
      ]
    }
  }
}

What it does

Annotated screenshots
Pin elements and comment on a captured view.
Text suggestions
Select a phrase and propose its replacement with context attached.
Session replay
Record video or session events with console, network and performance data.
Debug bundles
Export a thread with media, diagnostics and checksums.
Agent context via MCP
Agents read thread evidence, project instructions and assigned work.
Self-hosted server
One Apache-2.0 installation per organisation on PostgreSQL and S3-style storage.

Good for

  • Turn a reviewer's screenshot comment into a coding task for an agent
  • Hand an agent a bug thread with the recording and console log
  • Ask an agent which assigned items to work on next
  • Collect exact copy changes from stakeholders on a staging site
  • Sync feedback threads with GitHub Issues

Pricing

Open source

Free, Apache-2.0; you provide the infrastructure

Prices change. Check feedbacks.softinator.ai before you buy.

Feedbacks FAQ

Is it free?

The vendor says the complete product is free and Apache-2.0 licensed; you provide hosting and AI tools.

Where does my data live?

On your own server, using PostgreSQL and S3-compatible storage.

Which agents work with it?

The site names Codex and Claude Code through MCP.

Is it production-ready for multiple customers?

The README calls it an early 0.x release serving one organisation per deployment, without public registration, billing or SSO.

Is Feedbacks free?

Yes. Feedbacks is open source, so you can use and self-host it for free.

How do I add Feedbacks to Claude Code?

Run this command in your terminal: claude mcp add feedbacks -- npx -y https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb

What are the best alternatives to Feedbacks?

The closest alternatives to Feedbacks are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Feedbacks

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools