MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
—
npm MIT -
trace-agentgithub.com/TECHKNOWMAD-LABS/trace-agentupdated this year
Agent observability. pip + MCP server + Claude skill.
MIT -
Ultra-fast, zero-bloat local JSONL observability and tracing for AI coding agents (MCP + CLI).
pypi MIT ★ 2 -
agent-trace-intelligencegithub.com/harinarayn/agent-trace-intelligenceupdated this year
MCP server that diagnoses why your agent behaved the way it did, and how to fix it
pypi MIT -
gosce-authenticated-mcp-traced-agentupdated this year
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
pypi MIT -
gosce-structured-output-mcp-traced-agentupdated this year
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
pypi MIT -
Local evidence and replay for coding agents: replay what happened, see what the trace could not prove, and attach safe evidence to review. Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, MCP.
pypi MIT ★ 107 -
vibe-tracegithub.com/vinay-umrethe/vibe-traceupdated this year
Agent sessions archive and MCP server for vibe-coding agent traces.
pypi AGPL-3.0-or-later -
MCP server that lets agents query their own OpenTelemetry traces — runs, span trees, slow spans, human-approval logs, token/cost usage.
pypi MIT -
@probebrowser/trace-mcpupdated this year
Trace MCP - Bridge between AI Agents and Trace
npm SEE LICENSE IN LICENSE -
tracegithub.com/BUKOWSKIREAL/traceupdated this year
Trace — a local, background version tracker for multi-CLI-agent coding workflows (Claude Code, Codex, Cursor, ...). Content-addressed snapshots in SQLite, per-agent attribution, diff/restore/revert via an Electron console and an MCP server.
MIT ★ 5 -
langfuse-traces-mcpgithub.com/karandeepsinghsodhi/skill-to-fetch-tracesupdated this year
MCP server that fetches Langfuse traces and provides them as context to VS Code coding agents.
pypi MIT -
SourceTrace: AI compliance provenance API. Traces regulations and standards to primary sources. Auditable JSON—no hallucinations. For AI agents and compliance teams.
MIT -
mcp-servergithub.com/bitDive/mcp-serverupdated this year
BitDive Model Context Protocol (MCP) server. The Autonomous Quality Loop for AI agents. Provides real runtime context, before/after trace comparison, and integration testing workflows.
★ 75 -
Passive Chromium CDP tracing for AI coding agents: DOM baselines, incremental changes, network events, and queryable browser history.
MIT ★ 1 -
@moltiplex/mcp-servergithub.com/duncanapm/moltiplexupdated this year
MCP server for Moltiplex observability platform — agent-native trace analysis
npm MIT -
elasticdash-mcpgithub.com/terryatrocketventures/elasticdash-mcpupdated this year
ElasticDash MCP server — search, inspect, and rerun AI agent traces from ElasticDash
npm MIT -
021-mcpupdated this year
MCP server for interacting with LLM traces - search, analyze, and debug your AI agent executions
pypi MIT -
可独立部署的 Agent 中台:对话入口、方案与工作流编排,知识库、工具/MCP、评测与全链路 Trace(Spring Boot 3 + Vue 3 + AgentScope)
MIT ★ 3 -
签证材料预审 Agent:本地 PDF/OCR、版本化 Rule Pack、受控 Workflow、材料一致性核验与 Trace Replay
Apache-2.0 -
coachgithub.com/ofekkir/coachupdated this year
Turn an agent's execution traces into a queryable model of what it did — served back to the agent over MCP.
Apache-2.0 ★ 7 -
vibetracergithub.com/omeedcs/vibetracerupdated this year
Real-time tracing, replaying, and rewinding of AI coding assistant edits. MCP server for AI self-correction. Cross-agent support (Claude Code, Cursor, Codex). Export to Agent Trace JSON and git-ai git notes.
cargo MIT -
MCP server for AI agents to investigate OpenTelemetry traces, metrics, and logs
npm Apache-2.0 -
Capture local AI agent traces and inspect failures, approvals, token usage, and run regressions through MCP.
pypi MIT ★ 1 -
@simul8r/mcpgithub.com/simul8r-ai/simul8r-mcpupdated this year
Simul8r MCP Server - Browser automation with cloud execution tracing for AI agents
npm MIT -
An MCP server for planning, execution and validation: Structured reasoning (think_*) + execution tracking (ship_*) + roadmap + signals for AI coding agents. Rust · stdio + Streamable HTTP · git-native, Agent-Trace-compatible traces.
cargo MIT ★ 2 -
autoai-agentwatchgithub.com/autoailabadmin/agentwatchupdated this year
AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior
npm Apache-2.0 -
@gettrace/mcpupdated this year
Trace MCP - Give your AI agents eyes for debugging
npm SEE LICENSE IN LICENSE -
Record a program run, then let coding agents query the trace over MCP. Python, Rust, TypeScript.
MIT -
Self-recalling long-term memory & reasoning traces for AI agents, via MCP + local SQLite.
npm MIT -
mcp-observabilitygithub.com/zavora-ai/mcp-observabilityupdated this year
Observability MCP Server — logs, traces, metrics, alerts, dashboards, incidents, SLOs, and runbooks for AI agents
cargo Apache-2.0 -
trailai-mcpgithub.com/tmam-dev/trailupdated this year
Trail MCP server — coding agents authenticate with a Trail API key and stream their runs into Trail as traces.
npm Apache-2.0 -
Trace your AI coding agent on your laptop: OpenObserve in one command, example or real Claude Code traces, ready-made dashboards, an MCP server, and an AGENTS.md so your AI assistant can set it up for you.
MIT -
qorrelate-mcp-servergithub.com/sethmichaelking/arqiveupdated this year
MCP server for Qorrelate observability platform - 123 tools for AI agents to manage logs, traces, metrics, session replays, and alerts
npm MIT -
3D engine that AI agents drive: real-time WebGL2 (Flare), offline path tracing (Bake) and an MCP server.
npm MIT -
MCP server for Arize Phoenix — LLM tracing, evaluation, and dataset management via AI agents
MIT -
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
go MIT ★ 113 -
Self-hosted LLM & agent tracing with infinite retention: a Next.js dashboard on Vercel backed by your own Firebase project, with scoped API keys, a REST API, a TypeScript SDK, and an MCP server so AI agents can work with traces.
MIT -
@borg-collective/initgithub.com/borg-farther/borg-initupdated this year
Zero-config installer for the Borg Collective failure-trace federation. Registers an agent, writes credentials, wires the MCP server into your AI assistant.
npm MIT -
agentpiergithub.com/gatewaybuddy/agentpierupdated this year
Airlock — infra-identifier + PII redaction for AI agent traces. Catches account IDs, ARNs, IPs, hostnames, bucket names, secrets AND PII in one pass. Library + MCP server. Apache-2.0.
NOASSERTION -
@firetrace/mcpactive
Model Context Protocol server for FireTrace: lets AI agents list, read, record, and delete traces through a scoped API key.
npm MIT -
Local-first database for AI agents. Runs, retries, forks, traces and memory in one SQLite file. Python + TypeScript SDKs, CLI, and MCP server. Zero dependencies.
Apache-2.0 -
Tracy profiler MCP adapter for AI agents to capture instrumented applications, export trace CSV data, and analyze zone timing through the DCC-MCP ecosystem.
pypi MIT -
MCP server for LogoLab: trace an image to a clean SVG and export a full app-icon set, locally, from your coding agent.
npm MIT -
mcp-datadoggithub.com/viamus/mcp-datadogupdated this year
A Datadog MCP implemented in C# that exposes logs, metrics, traces, and monitors as structured context for AI agents, enabling automated observability analysis, test validation, incident investigation, and operational insights.
MIT ★ 5 -
Benchmark and MCP tools for LLM agents doing root-cause analysis on OpenTelemetry metrics, traces and logs. 20 recorded microservice incidents, every run scored against a 28-line rule and replayable. Only the strongest models clearly win.
Apache-2.0 -
Zero-config runtime X-ray for your dev server: live service map, request traces, N+1 detection, and an MCP server so coding agents can see real runtime behaviour
MIT -
Local-first semantic memory for Pi coding agent — powered by LogosDB MCP (stdio). Auto-indexes projects, persists turn records and thinking traces across sessions, injects relevant context on every prompt. Zero cloud.
npm MIT ★ 1 -
MoleSignal on the command line: logs, metrics, traces, incidents and approvals, deployments, source maps and symbols from CI, and MCP over stdio for AI agent tools
npm Apache-2.0 -
lgtm-mcpgithub.com/adarshba/lgtm-mcpupdated this year
MCP server for the Grafana observability stack — investigate latency, errors, and traces via intent-based tools. Connects AI agents (Claude, Cursor, OpenCode) to Prometheus, Loki, and Tempo over stdio.
cargo NOASSERTION -
systracesuitegithub.com/r1chard-lyu/systracesuiteupdated this year
Systracesuite is a MCP server designed to expose Linux tracing and debugging capabilities such as bpftrace, perf, ftrace, and syscall tracing to LLMs and autonomous agents.
Apache-2.0 ★ 2 -
otel-mcpgithub.com/moondef/otel-mcpupdated this year
OpenTelemetry traces for AI coding agents via MCP
npm MIT ★ 2 -
Typed MCP agent runtime with Docker Firecracker sandboxes tracing replay and trajectory evals
MIT -
Summarize a supplied agent tool-call trace: per-tool stats, the error list, and totals.
npm MIT -
Testorimno update data
AI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
npm -
Unified realtime agent trace database & search MCP
pypi Apache-2.0 -
Open eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
pypi -
perfdigest-mcpgithub.com/onlyxitachi/perfdigest-mcpupdated this year
Local MCP server that digests development-loop reports — profilers (NVIDIA ncu, AMD rocprof, Linux perf, Apple Metal, chrome-trace), build tools (ptxas, clang -ftime-trace, cmake, ninja, cargo), benchmarks (criterion), CI run logs, and git change state — into token-efficient JSON for LLM coding agents.
pypi Apache-2.0 -
observe-instrument-mcpgithub.com/alanzha2/observe-instrument-mcpupdated this year
MCP server that instruments Python AI agents with the ioa-observe-sdk (OpenTelemetry tracing)
pypi -
Signed agent-only friction board: findings backed by verified trace packs, in a closed vocabulary.
oci