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.
-
agent-observability-mcpgithub.com/blueskylineassets/agent-observabilityupdated this year
MCP server for agent observability - structured logging, cost tracking, and compliance audit trails
npm MIT -
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
npm -
Local runtime observability bridge for AI agents debugging React Native/Expo apps on Android — evidence-first: screenshots, UI trees, per-request network, FPS, React renders, CDP console/heap/profile, deterministic diagnosis, before/after compare.
npm Apache-2.0 -
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.
npm MIT ★ 2 -
observable-agentgithub.com/gajanangitte/observable-agentupdated this year
A local AI agent that turns self hosted SigNoz into a sensor: it detects an SLO breach through the SigNoz MCP server, applies a policy gated fix, verifies it, and rolls back if it does not hold. Governed autonomy, a carbon signal, and accessibility as telemetry. Agents of SigNoz hackathon, all three tracks.
MIT -
Local-first observability dashboard for AI agents. MCP-native. Look at every span your agents emit.
pypi MIT ★ 7 -
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 -
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 -
Unified observability gateway for AI agents — one MCP server for Prometheus, Loki, and any backend, with cross-signal anomaly detection and a built-in Web UI.
npm Apache-2.0 ★ 7 -
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.
-
Agent-ready telemetry SDK — enriches OpenTelemetry across Java, Go, Python, Node.js, and browser with structured context for AI-driven observability.
npm Apache-2.0 ★ 11 -
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.
go Apache-2.0 ★ 1 -
Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.
npm MIT ★ 25 -
trace-agentgithub.com/TECHKNOWMAD-LABS/trace-agentupdated this year
Agent observability. pip + MCP server + Claude skill.
MIT -
Self-hosted observability for agentic debugging: traces, logs, replay, AI cost, Agent Action Graphs, MCP, profiles, and usage analytics in one evidence graph.
MIT ★ 2 -
agent-breadcrumbsgithub.com/ejcho623/agent-breadcrumbsupdated this year
Cross-platform agent logging and observability
MIT ★ 4 -
tma1github.com/tma1-ai/tma1active
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.
Apache-2.0 ★ 125 -
actionproofgithub.com/Burakfenerci5/actionproofupdated this year
Tamper-proof audit trail for AI agents — the verifiable layer of agent observability. Signed, offline-verifiable receipts for every agent action. TS + Python, MCP server, zero backend. MIT.
npm MIT -
@vantinel/mcpgithub.com/amitruls1/vantinel-nodeupdated this year
MCP server for Vantinel AI Agent Observability Platform
npm MIT -
@vantinelai/mcpgithub.com/vantinel/vantinel-nodeupdated this year
MCP server for Vantinel AI Agent Observability Platform
npm MIT -
axiom-mcpgithub.com/Mr-Brownn/axiom-mcpupdated this year
MCP server for AI agent observability, guardrails, branching, and execution control
MIT -
stop-mcpgithub.com/echovic/stop-protocolupdated this year
STOP Protocol MCP Server — bring observability to Agent Skills via MCP
npm MIT -
@ura-dev/agentracegithub.com/ura-tools/agentraceupdated this year
Structured observability for AI agents — MCP server + CLI viewer
npm MIT -
Self-hosted coordination and observability hub for AI coding agents
npm AGPL-3.0 ★ 10 -
Agent-native Linux observability and OS policy simulation through MCP.
MIT -
@moltiplex/mcp-servergithub.com/duncanapm/moltiplexupdated this year
MCP server for Moltiplex observability platform — agent-native trace analysis
npm MIT -
kafka-sentinel-mcpgithub.com/sanjay-amu/kafka-sentinel-mcpupdated this year
Read-only Kafka observability for AI agents — MCP server
pypi MIT ★ 3 -
agentdb-mcpgithub.com/zizka-ai/agentdbupdated this year
MCP server for AgentDB — give any AI agent persistent memory and observability
pypi MIT -
Zero-dependency AI agent session observability CLI and read-only MCP inspection server. No shell, no network, no writes.
MIT -
Agent observability MCP server for querying OpenTelemetry traces, failures, tool health, security evidence, and regressions.
pypi MIT -
cairn-mcpupdated this year
MCP server for Cairn — a shared knowledge base of AI agent observations
npm MIT -
agentlens-mcpgithub.com/arkfelix7/agentlensupdated this year
MCP server for AgentLens — zero-code observability for MCP-native AI agents
pypi MIT -
langobs-mcpgithub.com/langobs/langobsupdated this year
MCP server for LangObs — zero-code observability for MCP-native AI agents
pypi MIT -
Ultra-fast, zero-bloat local JSONL observability and tracing for AI coding agents (MCP + CLI).
pypi MIT ★ 2 -
Runtime observability for AI agents — see exactly what your agent did, why it did it, and what it cost.
pypi MIT -
agentwatchgithub.com/nicofains1/agentwatchupdated this year
Multi-agent observability: cascade failure detection, heartbeat monitoring, cross-agent tracing, and forensic replay
npm MIT ★ 1 -
postgresai – Postgres observability built for humans and AI agents
Apache-2.0 ★ 140 -
Agent-native observability: OTLP in, MCP out, one Postgres store. Built for agents, not dashboards.
MIT -
MCP observer that catches AI agents claiming success on tool calls that failed. One command to try.
npm -
Read-only observability MCP server: give an agent eyes on a production host, not hands
MIT -
ctx-capturegithub.com/sathviknayak123/ctx-captureupdated this year
MCP server for context-window observability: capture and query exactly what an LLM agent saw at every step.
pypi MIT -
Cloud-ready multi-agent AI engineering organization reference architecture with FastAPI, LangGraph, MCP, memory, queues, and observability
-
agentscopegithub.com/bhanu-dev82/agentscopeupdated this year
AgentScope: multi-agent pipeline plus a Watchdog that uses SigNoz MCP as a continuous monitoring loop. Agents of SigNoz hackathon (AI & agent observability).
-
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 -
agentgovgithub.com/bdeva1975/agentgovupdated this year
Governance & observability control plane for agentic systems — policy/budget enforcement, audit trail, and MCP integration. Synthetic-data POC.
MIT -
throne-mcp-gatewaygithub.com/mdfifty50-boop/throne-mcp-gatewayupdated this year
20 Production MCP Servers for AI Agent Infrastructure — Safety, Observability, Compliance & Intelligence
★ 1 -
Debug Anything: observe and diagnose any running process, container or pod from your agent with one CLI and MCP server. Evidence, not guesses.
npm MIT -
pixelsquads-mcp-servergithub.com/aitor-alt/pixelupdated this year
MCP Server for Pixel Squads — observe your AI agents as pixel-art characters in a live office
npm MIT -
@winkit/mcpactive
WinKit MCP server - local Windows observability and diagnostics for AI agents, launched over stdio.
npm MIT -
gemini-extensiongithub.com/argosvix/gemini-extensionupdated this year
Argosvix extension for Gemini CLI — AI agent observability with a bundled MCP server (89 tools)
MIT -
Enterprise-AI-Incident-Triage-Automation-Agentgithub.com/KarthikRamesh9149/Enterprise-AI-Incident-Triage-Automation-Agentupdated this year
Enterprise AI Incident Triage and Automation Agent - local-first FastAPI, Next.js, MCP-style tools, OpenAI, RBAC, approvals, evals and observability
-
A perception and attention layer for AI agents: append-only Observations in, permission-filtered world views and evidence-backed Signals out
MIT -
Observability for coding agents. Local-first. Agent-first. Native OTLP, Sentry, and Datadog connectors — MCP so agents can test and debug the running system.
MIT -
Observability MCP server for AI agents - 89 tools to query LLM cost/errors/latency across 7 providers and operate alerts, budgets, evals from Claude/Cursor
npm MIT -
iflow-mcp_brennhill-gasoline-agentic-browsergithub.com/brennhill/gasoline-agentic-browser-devtools-mcpupdated this year
Gasoline Agentic Browser is an AI Debugger, Inspector, and Observability toolkit. It acts as Chrome DevTools for AI Agents using the Model Context Protocol (MCP).
pypi AGPL-3.0-only -
Agent-native observability for NATS and JetStream: web UI, CLI and a read-only MCP server over one bounded query engine.
npm Apache-2.0 -
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 -
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
go MIT ★ 113 -
@cdzzy/engramactive
Standardized long-term memory for AI agents 鈥攆orgetting curve, behavior observer, shared memory spaces, memory versioning, and MCP stdio server
npm MIT -
Agentic-RAGgithub.com/Zhonghui-li/Agentic-RAGupdated this year
Slug Advisor — a deployed tool-calling agent for UCSC course advising: LangGraph ReAct, hybrid retrieval (BM25 + pgvector) + reranker, eval-in-CI, Langfuse observability, MCP server, on GCP Cloud Run.