Gives Claude five performance analysis tools for profiling code directly in conversation. The benchmark tool runs JavaScript snippets with statistical timing (p95, p99, ops/sec) and side-by-side comparisons. Memory analyze takes heap snapshots over time and uses linear regression to spot leaks. Big O estimate fits your timing data against common complexity classes and shows an ASCII growth curve. Bundle analyze inspects JavaScript bundles for size, compression, and tree-shaking opportunities. Load test hits HTTP endpoints with configurable concurrency and reports percentile latencies. Useful when you're optimizing hot paths, debugging memory issues, or need quick performance feedback without leaving the chat.
Performance analysis tools for AI agents, exposed via the Model Context Protocol (MCP).
Benchmark JavaScript code execution. Run a snippet N times and measure min/max/avg/median/p95/p99 latency and operations per second. Optionally compare two implementations side by side.
Parameters:
code (string) — JavaScript code to benchmarkiterations (number, default 1000) — Number of iterationscompareCode (string, optional) — Second implementation to comparelabelA / labelB (string) — Labels for comparison outputAnalyze Node.js memory usage: heap used/total, RSS, external memory, and array buffers. Takes snapshots over time and uses linear regression to detect trends and potential memory leaks.
Parameters:
action — "snapshot" | "analyze" | "clear"Estimate Big O complexity from empirical timing data. Fits measurements against O(1), O(log n), O(n), O(n log n), O(n^2), O(n^3), and O(2^n) using R-squared scoring. Includes an ASCII growth curve visualization.
Parameters:
inputSizes (number[]) — Array of input sizesexecutionTimesMs (number[]) — Corresponding execution times in msAnalyze a JavaScript bundle file: raw size, gzip compressed estimate, detected module count, largest modules, and tree-shaking opportunities (side effects, duplicates).
Parameters:
filePath (string) — Absolute path to the bundle fileSimple HTTP load tester. Sends N requests at a given concurrency level and reports response time percentiles, error rate, throughput (req/sec), and status code distribution.
Parameters:
url (string) — Target URLtotalRequests (number, default 100) — Total requests to sendconcurrency (number, default 10) — Concurrent request countmethod (string, default "GET") — HTTP methodheaders (object, optional) — HTTP headersbody (string, optional) — Request bodytimeoutMs (number, default 30000) — Request timeoutnpm install
npm run build
Add to your claude_desktop_config.json:
{
"mcpServers": {
"perf-tools": {
"command": "node",
"args": ["D:/products/mcp-servers/mcp-perf-tools/dist/index.js"]
}
}
}
MIT
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent