| amd-skills | A plugin bundling AMD-verified Agent Skills that process image and audio via local AI on Ryzen AI, deploy LLMs on AMD Instinct GPUs using vLLM, and evaluate GPU kernel and PyTorch trace performance. | Development | AMD |
| amplitude | This tool acts as an analytics assistant for Amplitude, helping set up tracking, identify product opportunities, examine charts, build dashboards, manage experiments, and analyze user and account data. | Monitoring | — |
| chrome-devtools-mcp | This tool lets coding agents control and inspect a live Chrome browser, capturing performance traces, network requests, console logs with stack traces, and automating actions via Puppeteer. | Development | — |
| codspeed | CodSpeed is a performance testing toolkit offering benchmarking data, flamegraphs, and comparisons; its MCP server supplies Claude detailed profiling context to identify bottlenecks and independently refine performance. | Development | CodSpeed |
| confidence | This tool integrates Confidence's feature flag, experiment, and migration management capabilities into Claude Code, allowing direct access to these functions within that environment. | Development | Spotify Confidence |
| crowdsec | A Claude skill that assists with operating CrowdSec across bare-metal, Docker, Kubernetes, and OPNsense setups—covering bouncers, WAF/AppSec, hub content, and troubleshooting via cscli and LAPI/CAPI, excluding new rule authoring. | Security | CrowdSec |
| crowdstrike-falcon-fusion | A toolkit for building and running CrowdStrike Falcon Fusion automation workflows, covering discovery of live actions, schema-validated YAML creation, workflow import/release, execution tracking, and managing Falcon Next-Gen SIEM lookup files. | Security | CrowdStrike |
| dash0 | Instruments Claude Code sessions with OpenTelemetry, recording tool calls, LLM requests, token consumption, and errors as traces sent to Dash0 or other OTel-compatible backends. | Monitoring | Dash0 |
| datadog | A preview plugin that connects Claude Code to Datadog via a preconfigured MCP server, enabling users to query logs, metrics, traces, and dashboards through natural language conversation. | Monitoring | Datadog |
| datarobot-agent-skills | DataRobot provides a set of AI/ML capabilities covering model training, deployment, and prediction, along with feature engineering, monitoring, explainability, and data preparation, plus App Framework CI/CD support and monitoring for external agents. | Development | DataRobot |
| deepeval | Provides capabilities for integrating DeepEval into AI applications, covering evaluation setup, tracing, dataset management, Confident AI reporting, and cycles of iterative refinement. | Development | Confident AI |
| fullstory | Enables Claude to interface with Fullstory, allowing retrieval of behavioral analytics, session replay data, and customer experience insights. | Monitoring | Fullstory |
| grafana-assistant | Provides guidance and standards for building and operating the Grafana Assistant application and its command-line interface. | Monitoring | Grafana |
| grafana-cloud-mcp | A cloud-hosted MCP server that enables AI-assisted observability for Grafana Cloud, requiring no local setup or installation. | Monitoring | Grafana |
| grafana-mcp | MCP server enabling AI assistants to manage Grafana dashboards, datasources, alerting rules, and incident workflows. | Monitoring | Grafana |
| growthbook | A collection of agent skills covering the entire lifecycle of GrowthBook feature flags and experiments, from setup through management and analysis. | Testing | GrowthBook |
| honeycomb | A collection of skills, agents, and workflows supporting Honeycomb observability tasks, including query patterns, production troubleshooting, SLO management, OpenTelemetry instrumentation, and migrating from Beeline, built to work alongside the Honeycomb MCP server. | Monitoring | Honeycomb |
| langfuse | A skill set for using Langfuse, an open-source platform that helps engineers trace LLM behavior, manage prompts, and evaluate model performance. | Monitoring | Langfuse |
| langfuse-observability | A plugin that captures Claude Code's traces, spans, and session telemetry, exporting them to Langfuse to support LLM monitoring, debugging, and evaluation. | Monitoring | Langfuse |
| logfire | Enables integration of Logfire observability into Python applications through automatic instrumentation for frameworks and libraries such as FastAPI, httpx, asyncpg, and SQLAlchemy. | Monitoring | Pydantic |
| logrocket | Enables Claude Code to interface with LogRocket, allowing natural-language queries for retrieving session replays, performance metrics, error issues, and user behavior data. | Monitoring | LogRocket |
| mlflow | A skillset for using MLflow to instrument, trace, evaluate, and iteratively refine AI agents, supporting a complete workflow from monitoring through validation. | Monitoring | MLflow Team |
| newrelic | A Claude Code integration that connects to New Relic telemetry, enabling terminal-based APM performance investigation, cloud cost analysis, Kubernetes debugging, NRQL query writing, and alert response. | Monitoring | New Relic |
| noibu | Noibu's plugin links Claude to ecommerce session, error, and conversion data, plus marketing, support, and commerce platforms, enabling revenue-loss detection, cross-platform actions, and automated workflows. | Monitoring | Noibu |
| pagerduty | Analyzes code changes by comparing them to historical incident data, generating PagerDuty-based risk scores to flag deployment risks before shipping. | Monitoring | — |
| planetscale | An authenticated hosted MCP server providing access to PlanetScale organizations, databases, branches, schemas, and Insights, enabling data queries, slow query detection, and account information retrieval. | Database | — |
| posthog | This tool integrates Claude Code with PostHog, enabling direct access to analytics data, feature flags, experiment results, error tracking, and insights. | Monitoring | — |
| render | A Render deployment toolkit offering deployment, debugging, and monitoring capabilities, featuring built-in skills, an agent component, slash commands, and a hook for validating render.yaml configuration files. | Deployment | Render |
| rootly | Provides end-to-end incident management covering deployment safety, incident response coordination, on-call scheduling, and post-incident retrospectives. | Monitoring | Rootly |
| sentry | Sentry integration for retrieving error reports and stack traces, searching issues by fingerprint, enabling developers to debug production errors from within their development environment. | Monitoring | — |
| sentry-cli | Enables interaction with Sentry's command-line interface, allowing users to manage and query Sentry data directly from the terminal. | Monitoring | Sentry |
| session-report | Creates an interactive HTML report analyzing Claude Code session data from local transcripts, covering token usage, cache efficiency, subagents, skills, and costliest prompts. | Productivity | Anthropic |
| zscaler | Administers Zscaler's cloud security suite—ZPA, ZIA, ZDX, ZCC, EASM, and Z-Insights—enabling policy configuration, connectivity troubleshooting, security audits, and incident investigation across these components. | Security | Zscaler |