Best Trace AI Skills & MCP Servers

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

TRACE32 debugger MCP server — low-cost MCP frontend for session, dialog, field, history, and resource inspection with stable cold start.

TRACE32 CMM language server via MCP — parse, diagnostics, completions, hover, symbols, and CLI validation for PRACTICE scripts. Native binary, no Node.js runtime needed.

Seitrace Insights MCP

Runtime feedback MCP server for AI coding agents. ViewGraph sees the UI - TracePulse feels the backend.

Argosvix MCP server — AI agent から traces / cost / alert を直接 query するための Model Context Protocol server (stdio transport).

Code intelligence toolkit for AI agents — extract functions, trace call chains, find callers, detect dead code without reading entire files. Works as MCP server, CLI, or agent skill. Supports JS/TS, Python, Go, Rust, Java.

CLI and MCP server for noticed — search your developer network, trace connections, find the shortest path to anyone through GitHub and LinkedIn.

Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the failure as an executable test.

Observability for MCP servers and LLM applications — traces, metrics, dashboards. One-line instrumentation for OpenAI, Anthropic, Gemini, and MCP. Self-hosted with Grafana + Prometheus + Jaeger.

Deterministic governance engine for AI agents — enforce worlds (permanent rules) and plans (mission constraints) with full audit trace

Model Context Protocol (MCP) server for Dynatrace

MCP server that exposes the Langfuse REST API as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.

MCP server for iOS leak hunting and performance investigation. 42 tools across .memgraph, .trace, and .mxdiagnostic files. v1.18 adds analyzeMetricKitPayload (42nd tool, post-mortem production-diagnostics from MetricKit JSON payloads — crash clusters, han

AI copilot for TouchDesigner with live MCP control (DeepSeek v4 optimized) — 110 tools (incl. v2.5: td_get_activity_log, td_ocr_image, td_check_for_updates, td_get_traces, tool approval gates; v2.5.5: td_ingest_url web ingestion), focus + locations, hint

MCP server for atrib. Walks informed_by chains backward from a record_hash to surface the reasoning chain that produced it.

CLI and MCP server for thenextrace.app — plan races and training from your terminal and from AI agents.

MCP server that exposes MCPLab evaluation tools — query runs, results, and traces via the Model Context Protocol

Stdio proxy for MCP servers that logs all JSON-RPC traffic to a replayable trace file.

Runtime verification for AI coding agents. MCP server that lets Claude Code verify code changes work end-to-end via Playwright + OpenTelemetry + SigNoz.

AI Value Trace and BVF, the agentic-native conversation framework. Run a Trace on a named account.

Cross-references — find who imports or uses a symbol, locate declarations, and trace inheritance chains.

MCP server for AI agents to investigate OpenTelemetry traces, metrics, and logs

MCP server for Xcode Instruments trace analysis