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.
-
Step-by-step observability for MCP agent workflows
npm 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 ★ 106 -
otel-mcpgithub.com/moondef/otel-mcpupdated this year
OpenTelemetry collector that exposes traces to AI coding agents via MCP
npm 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 -
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.
MIT ★ 2 -
agent-safety-mcpgithub.com/luciferforge/agent-safety-mcpupdated this year
MCP server for AI agent safety — cost guards, injection scanning, decision tracing, agent identity (KYA), and signed receipts
pypi MIT -
Capture local AI agent traces and inspect failures, approvals, token usage, and run regressions through MCP.
MIT ★ 1 -
Record a program run, then let coding agents query the trace over MCP. Python, Rust, TypeScript.
MIT -
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
npm MIT -
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 -
MCP server for persisting agent long-term memory and step-by-step reasoning traces in SQLite
npm MIT -
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
MIT ★ 112 -
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 -
@moebiusx/otel-mcp-servergithub.com/moebiusx/otel-mcp-serverupdated this year
OpenTelemetry MCP Server — expose traces, metrics, logs, Elasticsearch, Alertmanager, and ZK proofs to AI agents via the Model Context Protocol
npm Apache-2.0 -
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 -
@mukundakatta/agentsnap-mcpgithub.com/mukundakatta/agentsnap-mcpupdated this year
MCP server: snapshot tests for tool-call traces. Capture, normalize, and diff agent tool-use traces to catch silent regressions. Wraps @mukundakatta/agentsnap for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
npm MIT -
otel-mcpgithub.com/moondef/otel-mcpupdated this year
OpenTelemetry traces for AI coding agents via MCP
MIT ★ 2 -
Agent observability MCP server for querying OpenTelemetry traces, failures, tool health, security evidence, and regressions.
pypi MIT -
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
pypi MIT -
agentwatchgithub.com/nicofains1/agentwatchupdated this year
Multi-agent observability: cascade failure detection, heartbeat monitoring, cross-agent tracing, and forensic replay
MIT ★ 1 -
forge-thinkgithub.com/halflifezyf2680/forge-thinkupdated this year
Structured multi-step orchestration for MCP agents: adversarial lenses, reusable SOP workflows, and persistent traces.
MIT ★ 3 -
Security auditor for AI agents and MCP servers — config analysis, prompt injection testing, tool probing, data flow tracing
npm MIT -
threadworkgithub.com/Tianqi-Bu/threadworkupdated this year
CLI-native multi-agent collaboration for Claude Code: hot-pluggable role yamls, persistent memory MCP, step-level trace replay.
MIT ★ 1 -
hartracegithub.com/rafsanbasunia/hartraceupdated this year
An MCP server for HTTP traffic analysis with value provenance tracing — token-efficient HAR inspection for AI agents.
pypi MIT -
claude-agent-org-toolsgithub.com/suguruooki/claude-agent-org-toolsupdated this year
Organization-theory based tools for Claude Code Agent Teams — 8 tools: Andon, Topology, RACI, OrgMemory, Workflow, QualityGate, Trace, Knowledge
npm MIT -
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
-
Code graph for AI agents: impact analysis and call tracing over MCP (Python, TypeScript). Local, deterministic, SQLite.
MIT ★ 2 -
adversarial-regulatory-arbitrage-mcpgithub.com/apifyforge/adversarial-regulatory-arbitrage-mcpupdated this year
Regulatory arbitrage detection and beneficial ownership tracing for AI agents via the Model Context Protocol.
MIT -
mcp-auditgithub.com/nyx-builds/mcp-auditupdated this year
Agent observability MCP server — trace, audit, and monitor AI agent tool calls. OpenTelemetry, Prometheus, and Grafana export.
-
Governed MCP + Skills agent platform over a legacy engineering-ops system: entitlements, audit, human-in-the-loop writes, eval-gated releases, OpenTelemetry tracing.
MIT -
OpenTelemetry MCP Server — expose traces, metrics, logs, and ZK proofs to AI agents via the Model Context Protocol
Apache-2.0 -
MCP server interface for AI agent and MCP security auditing — config analysis, trust audits, prompt injection testing, tool probing, and data flow tracing
npm MIT -
Agent Behaviour Drift Sentinel: detects silent behavioural drift in agent execution traces against a signed baseline. Reference implementation of the public SHPBL behaviour specification.
MIT ★ 1 -
Connect AI agents to a live Synopsys Verdi session through MCP: waveforms, signal values, driver tracing, and RTL source.
MIT ★ 24 -
An evidence-chain whiteboard and MCP server that keeps AI research agents honest: every claim traces back to the run and the code that produced it.
npm AGPL-3.0-or-later -
Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.
pypi Apache-2.0 ★ 95 -
MCP server for AI agents to explore SystemVerilog, Verilog and VHDL (beta) designs: trace connectivity, walk hierarchy, jump to source - without pasting RTL into context. Built on najaeda.
Apache-2.0 ★ 22 -
What any website is, with evidence: AI builder traces, tech stack, popularity and trust signals. MCP server, agent skill and plugins.
MIT ★ 2 -
A precise local codebase map for AI coding agents: find, trace, and predict with file-line evidence.
pypi MIT -
Evidence-grounded IT support agent: Gemini function calling over an MCP-style tool server (KB search, ticket search, ticket drafts), with a 60-question eval harness, LLM judge, and OpenTelemetry tracing.
★ 1 -
Trace anything running - dynamic reverse engineering for AI agents. MCP server + CLI with evidence records: hooks, syscalls, memory, network. The dynamic half of REA.
MIT ★ 1 -
OSINT Agent Skills — 24 MCP tools for autonomous OSINT investigation. DNS, WHOIS, CT logs, Shodan, breach data, geolocation, crypto tracing. Works with Claude Code, Cursor, any MCP client.
npm MIT -
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
MIT ★ 241 -
Debuggatha: repo-aware code reviewer for AI coding agents. MCP server, CLI and VS Code extension with rule-traced findings.
MIT ★ 1 -
agent-observabilitygithub.com/KryptosAI/agent-observabilityupdated this year
Trace AI agent execution: every tool call, every error, every dollar. Open source agent observability for Claude, Cursor, opencode, and any MCP-compatible agent. Local-first, free forever.
MIT ★ 2 -
kodeklaritygithub.com/vjvkrm/kodeklarityupdated this year
Shared knowledge & memory of your code, for AI agents. Code graph + persistent memory layer — impact analysis, risk scoring, cross-boundary tracing, agent-to-agent knowledge sharing.
npm AGPL-3.0-only -
Framework-agnostic Java observability sidecar agent: chat with a live JVM via MCP/web UI (metrics, slow calls, errors, logs, thread dumps, method traces). Self-hosted, attachable (Arthas-style). Apache-2.0.
Apache-2.0 ★ 3 -
Drive a live Flutter app from an AI agent or CI: Semantics snapshots, gated taps and typing, screenshots, perf traces. No flutter_test harness, no test file between actions.
MIT ★ 3 -
Open-source desktop browser shared by AI agents and people: automation first, AI second, humans last. Pluggable pointer/CAPTCHA/clipboard models, MCP, full action trace.
MIT -
State machine dispatch server for AI agent workflows. Typed YAML specs, MCP server (stratum-mcp), and Python library (stratum-py) — postconditions, retries, gates, and auditable execution traces for Claude Code and Codex.
NOASSERTION ★ 2 -
AMKP (Agentic Multimodal Knowledge Plane): API/SDK/MCP-first Evidence + Policy + Tenancy plane for multi-product RAG — hard isolation, Parse Ladder / TableEvidence, guarded agentic retrieve, traces & eval.
-
MCP server for Layerdock: read website feedback (selector, screenshot, console and network trace) in Claude Code, Cursor and other coding agents, then fix and resolve it.
MIT -
codegraphxgithub.com/techcraze00/codegraphxupdated this year
Token-efficient codebase graph engine for AI coding agents. Tree-sitter parsing, SQLite semantic graph, impact tracing, and an MCP server with zero-config auto-indexing.
npm MIT -
Visible AI-driven robotics demos powered by VLM policies, MCP skills, and AI coding agents. Reviewable HTML reports — frames, maps, tool traces, scores — instead of buried terminal logs.
MIT ★ 7 -
Enterprise MCP server & CLI toolkit for AI agents: Spec-Driven SDLC, codebase reverse-engineering (/trace), cross-surface SSOT docs, deterministic codegen, and automated Playwright E2E testing.
npm MIT -
LLM observability and evals in a single binary: traces, prompts, datasets, scores and review queues for LLM and agent apps. Self-hosted, SQLite inside, OpenTelemetry-native, MCP and CLI for coding agents.
Apache-2.0 ★ 1 -
Self-hosted error tracking built for coding agents. Your apps crash, your agent reads the stack trace and fixes it. Sentry alternative for ~$5/month. Community: skool.com/kenkai
MIT ★ 5 -
MCP server for Home Assistant — lets AI agents author and validate HA configuration and automations (entities, templates, traces, energy, ZHA, HACS) with a strict no-device-control boundary
npm MIT ★ 4 -
Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時,每個結論都能追到產生它的程式碼。Claude Code · Codex · Cursor · Gemini CLI
AGPL-3.0 ★ 501 -
Agent memory you can audit. Every lesson cites its source; trace a bad memory and remove it with a receipt. Local-first MCP server for Claude Code, Cursor and Cline.
npm Apache-2.0