vigilante
Provides an instrumentation adaptor for Node.js applications to capture runtime events such as HTTP requests, function calls, and errors.
Planned instrumentation adaptor for PHP applications to capture runtime events.
Planned instrumentation adaptor for Python applications to capture runtime events.
Planned instrumentation adaptor for Rust applications to capture runtime events.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
vigilante
Runtime instrumentation that makes any app visible to LLMs — via MCP.
Built by @retamayo
Vigilante hooks into a running application with zero changes to your code. It records every HTTP request, function call, return value, object mutation, and error — then exposes it all to any MCP-capable LLM so it can autonomously debug your app.
Language-agnostic design. The MCP server speaks a universal event format. Per-language adaptors handle instrumentation. Node.js adaptor included, with plans to develop Rust, PHP, and Python adaptors.
Quick start
# 1. Clone and install
git clone https://github.com/retamayo/vigilante.git
cd vigilante
npm install
# 2. Run your app with instrumentation
node --require ./vigilante/adapters/node.js your-app.js
# 3. Add to your .mcp.json (Claude Code / Claude Desktop){
"mcpServers": {
"vigilante": {
"command": "node",
"args": ["path/to/vigilante/vigilante/server.js"]
}
}
}Then tell the LLM: "the cart total is wrong" — it will query Vigilante and trace the runtime to find the bug.
Related MCP server: codinfy-agent-monitor
How it works
Your App --> Adaptor (hooks functions) --> Events File (JSON) --> MCP Server --> LLMThe Node.js adaptor installs two hooks before your app runs:
Hook | What it captures |
| Wraps exported functions of user-land modules ( |
| Intercepts HTTP requests/responses, creates spans per request |
Events go into a ring buffer (keeps the last 2000 events) flushed to a temp file. The MCP server reads it on demand. Queries return up to 500 events at a time.
Sensitive data is automatically redacted — passwords, tokens, secrets, and authorization headers are replaced with [redacted] before being written to the event buffer.
MCP interface
Connect any MCP client to node vigilante/server.js (stdio transport).
Resources
URI | Description |
| Summary of all request spans — method, path, status, event count |
| Full event buffer |
| Current / last-known call stack |
Tools
vigilante_help — Returns a reference guide for all resources, query params, and recommended workflow. Call this first.
vigilante_query — Query runtime events with composable filters:
Param | Type | Description |
| string | Natural language filter, or "all" to skip keywords |
| string | Filter to one request span (e.g. "http-3") |
| number | Events after this ID (incremental polling) |
| string | ISO timestamp range |
| string | Follow a key path through runtime (e.g. "user.balance") |
| string | Trace data flow chain for a key path |
| [string, string] | Compare two spans structurally |
| string |
|
| number | Max events per query (default 50, max 500) |
Example queries
"what errors occurred?" -> keyword filter
{ spanId: "http-3" } -> all events from one request
{ track: "user.balance" } -> follow balance through mutations
{ dataflow: "user.balance" } -> trace: read -> pass -> mutate -> return
{ diff: ["http-1", "http-3"] } -> compare working vs broken request
{ since: 42 } -> incremental polling from last seen
{ spanId: "http-5", format: "tree" } -> nested call tree for one requestEvent format
{
"id": 42,
"timestamp": "2026-04-06T06:05:45.601Z",
"type": "call",
"spanId": "http-3",
"depth": 0,
"source": { "module": "./lib", "fn": "checkout" },
"data": { "args": [{"balance": 500, "cart": [...]}, "alice", "HALF"] }
}Event types: call, return, error, mutation, io_start, io_end
File structure
vigilante/
context.js -- ring buffer, span tracking, disk persistence
server.js -- MCP server (language-agnostic)
register.js -- backwards-compat entry point
adapters/
node.js -- Node.js instrumentation adaptor
package.json
README.md
LICENSEAdding a new language
Write an adaptor that:
Hooks function calls in the target language
Writes events to the same temp file in the universal format above
The MCP server works unchanged — it just reads the file
Security
Vigilante is a development-only debugging tool. It should not be used in production.
Authorization headers are redacted automatically
Passwords, tokens, secrets, and API keys in request bodies and function arguments are redacted
The events file is written to the OS temp directory
No data is sent over the network — the MCP server reads a local file via stdio
Philosophy
Vigilante records faithfully and analyzes nothing. The buffer is the source of truth. The LLM draws its own conclusions.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Production runtime data for Android and KMP apps (startup, ANRs, slow screens) for coding agents
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
Voice-powered bug reporting with 13 MCP tools. Record bugs by talking; let AI find and fix them.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA 100% local development monitoring tool that captures browser console logs, network requests, and backend server output for analysis by AI assistants via MCP. It enables LLMs to debug applications by providing structured, real-time access to full-stack log data and persistent local storage.7MIT
- FlicenseNot gradedqualityCmaintenanceProvides real-time monitoring of AI agents, context, usage limits, workflows, files, Git, tests, builds, errors, secrets, and model-economy advice for tools like Claude Code, Codex, and Cursor, with 30 MCP tools for comprehensive observability.1-
- FlicenseNot gradedqualityDmaintenanceRecords all MCP tool interactions in a centralized ledger, enabling developers to trace, replay, inspect, and audit AI agent workflows.-
- AlicenseNot gradedqualityDmaintenanceProvides unified AI agent observability including tracing, cost tracking, performance monitoring, anomaly detection, and audit trails via MCP.56 npmMIT