pypi feedback-synthesis-mcpstreamable-httpMITupdated 20d ago
Customer feedback intelligence for AI agents and developers. Synthesize GitHub Issues, Hacker News threads, and App Store reviews into ranked pain clusters with evidence links. Pay-per-call via x402 micropayments — no signup required.
What can you do with Feedback Synthesis MCP?
Feedback Synthesis MCP
Customer feedback intelligence for AI agents and developers. Synthesize GitHub Issues, Hacker News threads, and App Store reviews into ranked pain clusters with evidence links. Pay-per-call via x402 micropayments — no signup required.
Stop reading through hundreds of feedback items manually. Feedback Synthesis MCP collects from multiple sources, runs a multi-pass LLM pipeline, and returns ranked pain clusters with impact scores, evidence links, and suggested actions — machine-readable for agents, human-readable for founders.
Quick Start
Install:
pip install feedback-synthesis-mcp
Set your wallet key (any EVM wallet with USDC on Base mainnet):
export EVM_PRIVATE_KEY=your_private_key_here
Add to Claude Desktop — edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "feedback-synthesis-mcp",
"env": {
"EVM_PRIVATE_KEY": "your_private_key_here"
}
}
}
}
Add to Cursor — edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "feedback-synthesis-mcp",
"env": {
"EVM_PRIVATE_KEY": "your_private_key_here"
}
}
}
}
Restart your client. You now have four customer intelligence tools available.
Tools
| Tool | What it does | Price |
|---|---|---|
synthesize_feedback |
Multi-source synthesis → ranked pain clusters with evidence | $0.05/call |
get_pain_points |
Quick single-source pain point extraction | $0.02/call |
search_feedback |
Full-text search across cached feedback items | $0.01/call |
get_sentiment_trends |
Time-series sentiment across sources | $0.03/call |
Supported sources: GitHub Issues, Hacker News, Apple App Store Reviews
Examples
Synthesize feedback from multiple sources
synthesize_feedback(
sources=[
{"type": "github_issues", "target": "owner/my-repo", "labels": ["bug", "feature-request"]},
{"type": "hackernews", "target": "Show HN: MyProduct"}
],
since="2026-01-01T00:00:00Z"
)
Returns:
{
"job_id": "syn_abc123",
"status": "completed",
"summary": "Analyzed 347 feedback items from 2 sources. Found 6 pain clusters.",
"pain_clusters": [
{
"rank": 1,
"title": "Authentication flow breaks on mobile Safari",
"severity": "critical",
"frequency": 23,
"impact_score": 0.92,
"description": "Users report inability to complete OAuth login on iOS Safari. Affects onboarding conversion.",
"evidence": [
{
"source": "github",
"url": "https://github.com/owner/my-repo/issues/142",
"snippet": "Login fails silently on Safari 17.2+"
}
],
"suggested_actions": [
"Fix Safari WebAuthn polyfill (see issue #142)",
"Add fallback auth flow for mobile browsers"
]
}
]
}
Quick pain points from GitHub Issues
get_pain_points(
source={"type": "github_issues", "target": "owner/my-repo", "labels": ["bug"]},
top_n=5
)
Search for specific topics
search_feedback(query="pricing too expensive", sources=["github_issues", "hackernews"])
Track sentiment over time
get_sentiment_trends(
sources=[{"type": "appstore", "target": "com.example.myapp"}],
since="2025-10-01T00:00:00Z",
granularity="weekly"
)
Payment
This MCP uses x402 micropayments on Base mainnet (USDC). You need:
- An EVM wallet with USDC on Base mainnet
- The wallet's private key set as
EVM_PRIVATE_KEY
Each call costs $0.01–$0.05 USDC. Payments are made automatically — no subscriptions, no API keys.
No payment configured? The server returns a helpful error with setup instructions.
Architecture
This package is a thin MCP client. All processing happens on the hosted backend:
Your Agent / Claude Desktop
│
▼
feedback-synthesis-mcp (this package)
- MCP tool definitions
- x402 payment signing
- Zero business logic
│ HTTPS + x402
▼
Hosted Backend (Railway)
- Multi-source data collection
- 3-stage LLM pipeline (Haiku × N + Sonnet × 1)
- SQLite caching + FTS search
- x402 payment verification
Server code is private (moat). Thin client is open source.
Direct MCP over HTTP (Streamable HTTP Transport)
Skip the PyPI package for programmatic/agent access using the hosted MCP endpoint directly:
MCP Server URL: https://feedback-synthesis-mcp-production.up.railway.app/mcp/
For MCP clients that support Streamable HTTP transport (Claude Desktop via HTTP, custom agents):
{
"mcpServers": {
"feedback-synthesis-mcp": {
"type": "streamable-http",
"url": "https://feedback-synthesis-mcp-production.up.railway.app/mcp/"
}
}
}
x402 payment is handled automatically by the client SDK. Set EVM_PRIVATE_KEY in your environment.
License
MIT
Install
Add Feedback Synthesis MCP to your client. Pick the one you use.
{
"servers": {
"feedback-synthesis-mcp": {
"type": "http",
"url": "https://feedback-synthesis-mcp-production.up.railway.app/mcp"
}
}
}Add to `.vscode/mcp.json` in your workspace.
claude mcp add feedback-synthesis-mcp -- uvx feedback-synthesis-mcpcodex mcp add feedback-synthesis-mcp -- uvx feedback-synthesis-mcpamp mcp add feedback-synthesis-mcp -- uvx feedback-synthesis-mcp{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "uvx",
"args": [
"feedback-synthesis-mcp"
]
}
}
}Add to `claude_desktop_config.json`, then restart Claude Desktop.
{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "uvx",
"args": [
"feedback-synthesis-mcp"
]
}
}
}Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.
{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "uvx",
"args": [
"feedback-synthesis-mcp"
]
}
}
}Add to `~/.codeium/windsurf/mcp_config.json`.
{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "uvx",
"args": [
"feedback-synthesis-mcp"
]
}
}
}Add to `cline_mcp_settings.json` via the MCP Servers panel.
{
"mcpServers": {
"feedback-synthesis-mcp": {
"command": "uvx",
"args": [
"feedback-synthesis-mcp"
]
}
}
}Add to `~/.gemini/settings.json`.
{
"mcpServers": {
"feedback-synthesis-mcp": {
"type": "local",
"command": "uvx",
"args": [
"feedback-synthesis-mcp"
],
"tools": [
"*"
]
}
}
}Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.
{
"context_servers": {
"feedback-synthesis-mcp": {
"command": {
"path": "uvx",
"args": [
"feedback-synthesis-mcp"
]
}
}
}
}Add to your Zed `settings.json`.
uvx feedback-synthesis-mcpRun `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.
4 tools
Feedback Synthesis MCP exposes 4 tools to a connected agent.
- synthesize_feedback
- Multi-source synthesis → ranked pain clusters with evidence
- get_pain_points
- Quick single-source pain point extraction
- search_feedback
- Full-text search across cached feedback items
- get_sentiment_trends
- Time-series sentiment across sources
Score
84 / 100
Excellent
- Documentation25/25
- Maintenance25/25
- Trust13/20
- Capability6/15
- Install experience15/15
- Documents what it does and how to connect
- Has a resolvable package or endpoint
- Exposes at least one tool, prompt or resource
- README has substantive content
- Includes a code example
- Documents its configuration
- Mentions credentials or security posture
- Last commit 12 days ago
- Has a release history
- Repository is not archived
- Licensed MIT
- Namespace verified in the official MCP registry
- Claimed by its owner
- Published under an organisation
- 4 tool(s) documented
- Provides prompt templates
- Provides resources
- 18 documented install method(s)
- Published to a package registry
- Offers a hosted endpoint — no local install
Version history
| Versions | Published |
|---|---|
| 0.1.2Latest | Aug 19, 2026 |
| 0.1.1 | Apr 11, 2026 |
| 0.1.0 | Apr 3, 2026 |