Live runtime data from a running Flutter app: exceptions, logs, network, frames, diagnosis.
MCPpedia last refreshed this data
io.github.itsonu/flutter-lamp is an MCP server that live runtime data from a running Flutter app: exceptions, logs, network, frames, diagnosis. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 58/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"flutter-lamp": {
"args": [
"-y",
"flutter-lamp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Live runtime data from a running Flutter app: exceptions, logs, network, frames, diagnosis.
This server supports HTTP transport. Be the first to test it - help the community know if it works.
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked flutter-lamp against OSV.dev.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in health
MCP server for the ClinicalTrials.gov v2 API. Search trials, retrieve study details and results, and match patients to eligible trials.
Search ClinicalTrials.gov: find studies, retrieve results, match patients to candidate trials.
MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications
Control FL Studio with Claude: in-DAW mixing, diagnosis, routing, and composition.
MCP Security Weekly
Get CVE alerts and security updates for io.github.itsonu/flutter-lamp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
An MCP server that connects Claude Code, Claude Desktop, Cursor, Codex & Gemini directly to a running Flutter app through the Dart VM Service Protocol — streaming exceptions, logs, network calls, frame timings and memory as structured data, plus an evidence-first root-cause diagnosis engine and a live browser dashboard.
Today you debug Flutter with your AI by copy-pasting stack traces, flutter run
output and DevTools screenshots. The AI is blind between messages.
Flutter Lamp makes the AI runtime-aware. It reads the app's live state over official Flutter/Dart APIs (never scraping DevTools), so instead of "paste the error" the AI can ask the app "what just happened, and why?"
❌ You: *pastes 40 lines of red stack trace*
✅ AI: connect_vm → get_exceptions → diagnose_runtime
→ "RenderFlex overflow in Column at home.dart:42, triggered right after
GET /api/user returned 500. Confidence 85%. Fix: …"
dart:developer)dart:io profiling — covers Dio & package:http, no interceptor neededdiagnose_runtime — correlates evidence into summary · root cause · evidence · confidence · fixes; says "Unknown" below 70% instead of hallucinatinghttp://127.0.0.1:7373 — streams everything over WebSocket, independent of the AI connectionflutter-runtime-diagnosis Claude Code skill| Tool | Purpose | Safety |
|---|---|---|
connect_vm | Connect to a running app's Dart VM Service (ws:// or http://). | mutates |
ensure_tcp_device | Android transports; recommend wireless, optionally promote USB. | mutates |
runtime_health | One-call triage — verdict plus exception/network/frame/log/memory summary. | read-only |
what_changed | Evidence from the window before a failure, with a timeline. | read-only |
get_navigation | Current route and recent transitions, with per-route failures. | read-only |
get_rebuilds | Widget rebuild hotspots resolved to widget, file and line. | read-only |
get_state_activity | Riverpod, Provider and Bloc activity over time, and how often it coincides with build-heavy frames. | read-only |
export_session | The whole session as versioned JSON — brief (diagnoses + cited evidence) or full. | read-only |
explain_diagnosis | Why a diagnosis was reached: resolved evidence, alternatives, gaps. | read-only |
get_capabilities | Active collectors, tool safety classes, what cannot be |