Category Hub
Investigate Issues apps and integrations
Investigate Issues apps connect ChatGPT and Claude to logs, metrics, traces, incident details, error reports, screen recordings, and telemetry so teams can query evidence and troubleshoot production or customer problems. Compare tools by connected observability and support sources, query and visualization options, incident workflows, and supported actions.
34 apps
Top investigate issues apps
Open full directory →Code
Datadog
By Datadog
Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help!
Tools: 0 · Prompts: 0
Grafana MCP Server
By Grafana MCP Server
A comprehensive Model Context Protocol (MCP) server for Grafana that provides: - Dashboards: Search, get, update, patch, and create dashboards with context window optimization - Datasources: List and query Prometheus, Loki, and ClickHouse datasources - Prometheus: Execute PromQL queries, histogram percentile analysis, and retrieve metric metadata - Loki: Query logs and metrics using LogQL, detect log patterns - ClickHouse: Execute SQL queries, discover tables and schemas - Alerting: List, create, update, and delete alert rules and contact points - Incidents: Manage incidents in Grafana Incident - Sift: Investigate errors and performance issues - OnCall: Manage on-call schedules, shifts, and alert groups - Pyroscope: Continuous profiling with profile types, labels, and flame graphs - Navigation: Generate accurate deeplinks to Grafana resources - Annotations: Query, create, update, and patch annotations - Admin: Manage teams, users, roles, and permissions - Rendering: Generate PNG snapshots of dashboard panels Requires Grafana version 9.0 or later for full functionality.
Tools: 71
Data-Analytics
Wingify
By Wingify Software Pvt. Ltd
Wingify helps teams analyze experimentation performance, review behavior insights, and manage testing campaigns directly from Claude.
Tools: 29 · Prompts: 1
Code
Google Compute Engine
By Google
Enables you to agentically manage your cloud compute infrastructure spanning deployment and operations.
Tools: 29
Data
Coralogix
By Coralogix
Bring Coralogix into your AI workflow. Enable Claude to work with your logs, metrics, and traces so you can explore and debug issues through natural language - run queries, inspect incidents and alert details, and ground answers in the data your team already relies on. Spend less time jumping between tools and more time understanding what your telemetry is telling you.
Tools: 16
Developer-Tools
Subtext
By Fullstory
Subtext is session replay built for agents instead of humans. Connect it and your Claude agents can open real production sessions and investigate them directly—no scrubbing a timeline, no video to watch. Learn more at https://subtext.fullstory.com/docs/introduction Hand your agent a Subtext link from wherever it already looks—a Sentry issue, a Linear ticket, a support thread, a PR—and it jumps to the right moment, inspects screenshots and accessibility trees, diffs DOM state, and reads console and network activity to find the root cause. Then it files the fix or hands you the finding. You review the answer, not the replay. What your agent gets: Session tools it calls directly: open a session, jump to a moment, inspect and compare state—purpose-built so agents traverse dense session data efficiently, with fewer tokens than pointing a general agent at raw replay. Best-in-class capture from Fullstory: Fullcapture behavior, pixel-perfect screenshots on demand, DOM diffs, and windowed console and network context. Privacy built for production: precision tools for agents to mask or exclude sensitive fields, plus agent-friendly DLP scanning tools over MCP. Cost-effective: Capture every session without sampling and never miss a critical user experience or bug report. Agents review the ones that matter most. Works with Claude Code or any MCP-compatible agent. Code-first install, self-serve signup, generous free tier, usage-based pricing. Bring your own agent harness—Subtext is the session context it was missing. Session replay used to be something humans watched. Now it's evidence your agents act on.
Tools: 15 · Prompts: 3
Data
Honeycomb
By honeycomb.io
Query and explore observability data from OpenTelemetry or dozens of other sources in your honeycomb.io account.
Tools: 13
Endor Labs
By Endor Labs
Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help!
Prompts: 4
Developer Tools
Datadog (Preview)
By Datadog
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production applications, identify, visualize, and remediate issues in your critical services. Run agentic loops to ensure you continue to maintain good observability and service management posture.
Prompts: 3
Developer Tools
Render
By Render
Provides skills for deploying apps with Blueprints, debugging failed deploys, monitoring service health and metrics, building Render Workflows, and migrating from Heroku.
Prompts: 3
Developer Tools
Statsig
By Statsig, LLC
Bring your Statsig workspace into Codex. Product builders can now explore, manage, and create Statsig experiments, feature gates, dynamic configs, and more directly in Codex conversations. Ask things like: “Move this experiment to 50% rollout.” “Turn on this feature gate for all users.” “Show me which dynamic configs changed this week.” "Explain how the DAU metric is defined.” You can both read and write to Statsig: inspect experiment settings, read metric definitions, update allocations, toggle feature flags, edit targeting rules, and modify dynamic config values directly from Codex. The app connects through Statsig’s MCP server and honors your existing Statsig permissions, so you only see and change what you’re authorized to access—across projects, environments, and teams.
Prompts: 1
Developer Tools
Armature
By Armature
Armature helps developers inspect configured MCP servers, review recorded agent sessions and use cases, investigate recurring issues, and report missing app capabilities through ChatGPT.
Prompts: 1
Developer Tools
Sentry
By OpenAI
Use Sentry skills to inspect recent issues, review events, and summarize production errors with a read-only workflow.
Prompts: 1
Developer Tools
Birdie
By Birdie
Birdie helps you capture customer issues and turn them into clear context for troubleshooting. Instead of relying on written descriptions, customers can record their screen to show the issue. Birdie captures the full context, including what happened, what they clicked, and technical evidence such as console logs, network requests, session data, device metadata, and reproduction steps. This gives your agent the context it needs to understand the issue, troubleshoot it accurately, and move faster to a resolution. With Birdie, your agent does not have to guess what the customer meant. It can see what the customer saw and use the right evidence to investigate the issue. Built for support and technical teams, Birdie reduces back and forth and helps both humans and AI troubleshoot customer issues faster.
View details →
Developer Tools
Threpoly
By Threpoly
Threpoly helps teams review the health, availability and security posture of monitored managed file transfer applications from within ChatGPT. Use Threpoly to check current service status, identify active outages, review historical SLA performance, investigate failed connectivity checks, monitor upload and download workflow tests, and see whether expected files or AS2 messages are overdue. Threpoly also provides security scores and prioritized recommendations for monitored services, helping teams identify configuration changes and areas that may need attention. The app is read-only. It retrieves monitoring information from the authenticated customer’s Threpoly account and does not expose passwords, private keys or other secrets.
View details →
Business & Operations
Catalog CLI Pro
By Helm
Catalog CLI Pro helps users inspect uploaded Amazon Category Listing Reports from ChatGPT. Users can list available catalogs, run catalog quality audits, summarize priority issues, drill into specific checks such as missing attributes or intent-based bullet coverage, and understand duplicate-row filtering in scan results.
View details →
Developer-Tools
OctoPerf MCP
By OctoPerf
OctoPerf MCP connects Claude to the OctoPerf load-testing platform so you can run a full performance-testing workflow in natural language. Import virtual users from HAR captures, Postman collections, Playwright scripts, JMX files or plain URLs, then validate and auto-correlate them so replay stops failing on dynamic parameters (CSRF tokens, session IDs). Configure and launch load scenarios (ramp-up, stairs, ramp-up/down), schedule them, and read back results: summary metrics, response-time charts, error breakdowns, threshold alarms and insights — and export bench reports as PDF. Hosted remote server: Streamable HTTP with OAuth 2.1 (Dynamic Client Registration + PKCE) — no API key to copy or store. Each user connects with their own OctoPerf account through the browser and can revoke access anytime. Works against OctoPerf SaaS or self-hosted, covering project, virtual-user, scenario and bench-result management (~100 tools).
Tools: 96
Grafana MCP Server
By Grafana MCP Server
A comprehensive Model Context Protocol (MCP) server for Grafana that provides: - Dashboards: Search, get, update, patch, and create dashboards with context window optimization - Datasources: List and query Prometheus, Loki, and ClickHouse datasources - Prometheus: Execute PromQL queries, histogram percentile analysis, and retrieve metric metadata - Loki: Query logs and metrics using LogQL, detect log patterns - ClickHouse: Execute SQL queries, discover tables and schemas - Alerting: List, create, update, and delete alert rules and contact points - Incidents: Manage incidents in Grafana Incident - Sift: Investigate errors and performance issues - OnCall: Manage on-call schedules, shifts, and alert groups - Pyroscope: Continuous profiling with profile types, labels, and flame graphs - Navigation: Generate accurate deeplinks to Grafana resources - Annotations: Query, create, update, and patch annotations - Admin: Manage teams, users, roles, and permissions - Rendering: Generate PNG snapshots of dashboard panels Requires Grafana version 9.0 or later for full functionality.
Tools: 71
Data-Analytics
Costory
By Costory
Costory is a FinOps MCP. It lets Claude work as your FinOps Agent, exploring and explaining your cloud and AI spend across AWS, GCP, Azure, Datadog, Anthropic, Snowflake, and OpenAI. Key features: - Query costs by any dimension (service, team, environment, region) and compare periods with natural-language questions - Build and update cost dashboards and reports - Create budget alerts and cost-anomaly notifications - Define cost allocations (virtual dimensions) - Track cost-driving changes using annotated events - Surface custom business and unit-economics metrics The connector reads from your Costory workspace and requires a Costory account.
Tools: 37
Code
incident.io
By incident.io
Manage your full incident.io workspace from one place. Declare and triage incidents, ack pages, check who's on call, and track follow-ups - without switching tools. Analyze incident trends, escalation response rates, and alert noise across your organization. Browse your catalog, query telemetry from connected observability tools, and run structured operational reviews. Everything your team needs to stay on top of things, without the tab juggling.
Tools: 35
Developer-Tools
Steadybit
By Steadybit
Steadybit is a reliability and chaos engineering platform. This connector lets Claude work with your own Steadybit tenant: explore what you run, design and execute chaos experiments against it, and interpret the results. Discover your systems Browse environments, teams, and services. Search targets — hosts, containers, Kubernetes workloads, cloud resources — with Steadybit's query language, inspect their attributes, and see which chaos actions your teams are allowed to use. Design and run experiments Search and read existing experiment designs, draft new ones from a plain-language description, create them from your own templates, and start or cancel runs. Steadybit's AI can suggest experiments tailored to a service and its weak points. Understand what happened Review past executions step by step, read execution logs, query the metrics recorded during a run, and pull reliability advice and service risk reports. Ask why an experiment failed and get an analysis grounded in the actual run data, not guesswork. Everything Claude sees is scoped to your own permissions: the connector acts as you, limited to your teams, their environments, and the actions they may run. Read-only tools are annotated as such, and starting an experiment is marked destructive, so Claude asks before injecting a fault.
Tools: 30
Data-Analytics
Fullstory
By Fullstory
Ask your product data anything, and get answers you can verify. Fullstory MCP connects Claude to your product's behavioral data. Ask how many users adopted a feature, where checkout is leaking, or whether yesterday's release broke something, and Claude builds the segment, computes the metric, and explains the result with a link back to Fullstory. Analytics connectors can give you numbers. Fullstory shows you what happened. Every metric unpacks into real session replay, so "conversion dropped 12%" becomes "the coupon field errors for logged-out users." And because Fullstory autocaptures clicks, page views, errors, and frustration signals, many questions need no instrumentation at all. Ask about rage clicks on pricing or errors in checkout without shipping a single event. What Claude can do: Build and save segments and metrics. Describe the users or behavior you care about in your own words; Claude creates the segment or metric in Fullstory where your whole team can reuse it. Compute on demand. Counts, rates, trends, and breakdowns by device, browser, geography, or user property, over any time window. Speak your product's language. Claude discovers your pages, named elements, and defined events, so questions map to your real product vocabulary instead of guessed selectors. Analyze conversion. Read your saved funnels and measure where users drop and why. Back every number with sessions. Retrieve the sessions and events behind any metric, including frustration signals like rage clicks and dead clicks. Read sessions at scale. Ask Claude to review dozens of sessions behind a drop-off or an alert and report the patterns, including failures that never reached your error tracker. Teams use it to let PMs, support, and engineers self-serve answers that used to queue behind an analyst, and to settle "why did this number move?" with evidence instead of theories.
Tools: 25
Productivity
CloudEagle MCP
By CloudEagle.ai
CloudEagle.ai is an AI-powered SaaS Management, AI Governance, and SaaS Security platform that gives enterprises one command center to discover, secure, govern, and optimize their entire SaaS and AI stack, including AI usage control and both human and non-human identities. Trusted by RingCentral, Automation Anywhere, Shiji, and Rec Room, CloudEagle helps organizations save 10–30% on software spend while managing hundreds of SaaS and AI apps, without disrupting existing tools. CloudEagle governs applications, identities, and non-human identities (service accounts, bots, API keys, AI agents) continuously, rationalizing redundant tools and tracking security posture against frameworks like NIST 800. Onboarding takes 30 minutes; savings and governance start day one. To date: $50B+ in spend processed, $3B+ saved. With 500+ integrations, CloudEagle eliminates shadow SaaS and AI, enforces AI usage policies, and secures non-human identities. Slack-enabled, no-code workflows automate onboarding/offboarding, access reviews, license harvesting, and just-in-time access, while an autonomous agent triggers renewals and routes approvals through Slack, Jira, or ServiceNow. By correlating IT, HR, Finance, and Security data, CloudEagle surfaces hidden risk, unauthorized AI use, excessive privileges, orphaned identities, and overspend, backed by usage benchmarking that strengthens every vendor negotiation.
Tools: 24
Other
JupiterOne
By JupiterOne
JupiterOne is a agentic risk management platform that maps your cloud resources, identities, devices, vulnerabilities, and the relationships between them into a queryable graph. This connector lets you work with that graph in natural language: run J1QL queries against your asset inventory, explore entity types, triage active alerts, create and evaluate detection rules, review integration ingestion status, and build dashboards. Every action runs with your existing JupiterOne user permissions.
Tools: 24
Need a custom investigate issues integration built?