"Automating Testing and Debugging for LLMs in Production" matching MCP servers:

Enables triggering, streaming, and reviewing autonomous production-incident investigations directly from your editor, with human-gated approval for any mutating actions.

MCP server for the Production Master incident-investigation service, enabling any MCP client to drive investigations via tool calls with pass-through authentication.

Enables MCP clients to discover and execute operational tools such as database mutations and system diagnostics over stdio, with deterministic structured outputs and Langfuse observability.

A TypeScript MCP server starter kit supporting stdio and HTTP/SSE transports. Includes tools for system metrics, HTTP fetching with URL restrictions, and temporary key-value memory with namespace and TTL support.

Connects AI agents to live observability stacks including Sentry, GitHub, Vercel, Better Stack, and Cloudflare, enabling end-to-end incident investigation, deployment correlation, root cause analysis, and regression triage.

A small notes server exposing scoped, cacheable tools over streamable HTTP, with OAuth token introspection and resource-server metadata so callers are identified per user. It enforces per-subject rate limits as tool-level errors and emits OpenTelemetry spans following MCP semantic conventions, and can also run locally over stdio without auth.

Enables LLMs to interact with Kibana through composable toolboxes for building dashboards, managing data, and handling alerts, among other operations.

Enables AI agents to interact seamlessly with Splunk environments through 20+ tools for search, analytics, data discovery, administration, and health monitoring. Features AI-powered troubleshooting workflows and supports multiple Splunk instances with production-ready security.

Enables interaction with Google Cloud services including billing cost analysis, log querying, and metrics monitoring through natural language commands. Provides comprehensive tools for managing GCP resources, analyzing costs, detecting anomalies, and retrieving operational insights.

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

Self-hosted Nightingale (n9e) includes a native Streamable HTTP MCP server at /mcp for querying alerts, rules, metrics, logs, hosts and dashboards with the caller's existing permissions. Users deploy the Nightingale server themselves; the implementation and deployment documentation are in the main repository, and the official website is https://n9e.io.

Enables precise measurement of live HTTP and WebSocket services while maintaining an append-only, evidence-based ledger of claims that agents can query with explicit timestamps, staleness indicators, and instructions for re-verification.

Enables AI-driven SOC investigations by providing automated Splunk querying, threat intelligence enrichment, and response actions through natural language. Includes tools for IP pivoting, lateral movement detection, and label harvesting.

A Model Context Protocol server that provides seamless integration with Coroot observability platform, enabling monitoring of applications, analysis of performance metrics, examination of logs and traces, and management of infrastructure through Coroot's comprehensive API.

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

An MCP server implementation that integrates AI assistants with Langfuse workspaces, allowing models to query LLM metrics by time range.

Provides a standardized way for MCP clients to interact with Apache Airflow's REST API, supporting operations like DAG management and monitoring Airflow system health.

MCP server that integrates with VictoriaMetrics vmanomaly API to enable AI-assisted anomaly detection, model management, and configuration generation.

Enables AI clients like Claude to triage, investigate, and operate Icinga installations through natural language, integrating with Icinga's REST APIs and providing deep awareness of monitoring plugins and historical performance data.

A safety layer and monitoring copilot for AI agents using Splunk MCP, recording tool calls, enforcing policies, and blocking risky actions.

A production-oriented reliability, benchmarking, and evaluation system that layers multi-version protocol negotiation, adaptive streaming, connection pooling, and resilience onto an MCP agent runtime.

Provides tools to search Splunk logs, inject test data, and send triage emails, enabling AI-driven incident investigation.

Enables AI agents to investigate incidents by listing services and dependencies, searching redacted logs, summarizing metrics, checking recent deploys, and producing ranked timelines with scoped tokens, validation, rate limiting, and audit logging.

Provides governed MCP tools for querying optionally restricted Microsoft Sentinel/Log Analytics tables and optional Defender XDR hunting data, retrieving incidents and entities, and—for agent identities only—adding attributed incident comments, with Entra ID authentication, KQL validation, rate limits, and redacted audit logging.

Provides Model Context Protocol access to the Dynatrace platform API, letting AI agents run live queries against observability, security, and platform data and manage a Dynatrace environment. It is hosted remotely by Dynatrace, so MCP hosts can add it by name from the official registry without installing anything.

A remote, Dynatrace-hosted MCP server that gives AI agents live API access to your Dynatrace environment. It enables querying and analyzing observability, security, and platform data — such as DQL queries, logs, traces, problems, and dashboards — so agents can act on production context instead of static knowledge.

Model Context Protocol (MCP) server for debugging, analyzing, and diagnosing Kubernetes clusters directly from AI agents.

Production-grade MCP Gateway in Go featuring dynamic OpenAPI tool registration, RBAC governance, in-flight PII/DLP redaction, and structured JSON audit logging.

Laravel Telescope-style debugging for Hono apps whose dashboard endpoint is also an MCP server: read recent exceptions with the request that produced them, recent requests filtered by status or duration, one request in full, and the slowest queries. Five read-only tools, zero runtime dependencies.

MCP server for analyzing Perfetto traces with LLMs — query .pftrace files in PerfettoSQL via Claude Code or any MCP client

An MCP server that gives coding agents programmatic access to Sumo Logic logs via the Search Job API, enabling issue triage in preview deployments and production without leaving the editor.

AI-powered incident management MCP server that enables investigation, root cause analysis, and response actions for production incidents using mocked data for demo purposes.

An instrumented MCP server for debugging lost tool calls in Claude Desktop, using ping, echo, sized_echo, and slow_echo tools to record and analyze the full protocol flow.

MCP server that gives AI agents access to your application's OpenTelemetry traces for querying, analysis, and debugging.

Enables LLMs to analyze and manage DBOS workflows, including introspection, workflow management, and authentication, to help debug applications in development or production.

An MCP server for debugging Temporal workflows, enabling LLM-assisted inspection of workflow executions, detailed workflow info, and event history.

An MCP server for streaming and searching macOS Console.app and iOS device logs, enabling real-time log access and debugging through natural language.

An MCP server that emits OpenTelemetry traces, metrics, and logs to OTLP endpoints in various formats. It includes tool-mimicry profiles to generate realistic traffic resembling common tools like nginx, postgres, and AWS Lambda for testing and demonstration purposes.

A Model Context Protocol server that enables retrieving and analyzing Sentry issues, including stacktraces and debugging information.

MCP server exposing AI agent observability tools: list, inspect, and deterministically replay recorded agent execution traces for debugging failures.