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.
153 apps
Top investigate issues apps
Open full directory →Developer Tools
Rootly
By Rootly
The Rootly MCP server gives MCP clients (Claude, Cursor, Windsurf, Gemini, and others) access to the Rootly incident management platform. Agents can query and manage incidents, alerts, on-call schedules and overrides, teams, services, workflows, retrospectives, and reliability metrics through the Rootly API. It supports OAuth2 login or API token auth, full and slim tool profiles, and optional read-only mode for analytics-focused teams.
Tools: 257 · Prompts: 3
Developer Tools
Datadog
By Datadog
Analyze, investigate, and act on your Datadog telemetry directly from Claude 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.
Tools: 44 · Prompts: 3
Code
Datadog
By Datadog
Analyze, investigate, and act on your Datadog telemetry directly from Claude 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.
Tools: 0 · Prompts: 0
Developer Tools
LaunchDarkly
By Catamorphic Co. dba LaunchDarkly
Manage LaunchDarkly feature flags, AgentControl Configs (AI agent prompts/models), experiments, guarded and automated rollouts, segments, metrics, dashboards, alerts, and observability data (logs, traces, errors, sessions) directly from chat. Create and target flags, run and analyze experiments, configure AI agent prompts and tools, build dashboards and alerts, and investigate production issues without leaving the conversation.
Tools: 169 · Prompts: 2
Developer Tools
CubePath
By CubePath
Connect your CubePath account to check and operate your cloud infrastructure from a conversation. List your servers and their status, look at CPU, memory and bandwidth metrics, start, stop or restart servers, manage DNS zones and records, CDN zones and cache rules, private networks, floating IPs, firewalls, load balancers, NAT gateways, managed Kubernetes clusters, managed databases and object storage buckets. You sign in with your CubePath account and choose which permissions to grant, for example read only access or write access to DNS. The plugin only sees the organization and projects your account belongs to, and every action runs with your role in that organization. Anything destructive or billable asks you first. You can revoke access at any time from Account > Connections in the CubePath dashboard. A CubePath account is required. Billing, payments and account top ups stay in the CubePath dashboard.
Tools: 161 · Prompts: 3
Developer Tools
Vantage
By Vantage
Vantage is the system of record for allocating and optimizing cloud, SaaS, and AI costs. Vantage has multiple tools for optimizing cloud spend and provides organizations with advanced FinOps workflows and cost governance.
Tools: 156
Developer Tools
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: 145 · Prompts: 3
Developer-Tools
InBrief
By InBrief
InBrief is a status page and uptime monitoring service. This connector lets Claude work with the status pages and tools you approve. What you can do: - Check the current status, uptime history and incidents of your pages. - Publish incidents, post updates, resolve them and write postmortems. - Schedule, update, cancel and complete maintenance windows. - Create, update, pause, resume and reorder uptime monitors. - Review subscribers, notification templates, webhooks, badges, widgets and branding. You stay in control. When you connect, you choose which tools and status pages Claude may use, and each connection keeps its own permissions. Your role and your plan still apply to every call. Sensitive changes, such as billing, team membership, API keys, custom domains, credentials and deleting a page or the account, only return a review link: nothing changes until you open it in InBrief, confirm who you are and approve. You can narrow access or disconnect at any time in InBrief settings.
Tools: 138
Developer-Tools
Connic MCP
By connic-org
Connect Claude to a Connic project to inspect and operate your AI agents. View agent details, run history, logs, deployment test results, and usage. Manage deployments, connectors, retrieval data, databases, and approvals with the permissions you grant. Sign in with your Connic account, choose a project and environments, and select read-only access or specific write permissions. You can edit or revoke access under Project Settings → API Keys & MCP Auth. Requires a Connic account with access to a project.
Tools: 131
Developer Tools
Better Stack
By Better Stack, Inc.
Observability for AI agents: query your logs, traces, metrics, and errors with SQL, build dashboards and chart alerts, manage uptime monitors, respond to incidents, see who's on-call, and publish status page reports. You can also create and link error issues in Linear or Jira and search Better Stack's docs without leaving the chat. Connects to your Better Stack account.
Tools: 130 · Prompts: 3
Data-Analytics
mcp.betterstack.com
By Better Stack, Inc.
Connect Claude to your Better Stack Uptime and Telemetry data. Your agent can query logs and metrics, build dashboards, manage uptime monitors, and respond to incidents, all in natural language.
Tools: 116
Developer Tools
Grafana Cloud
By Grafana Labs
Grafana Assistant brings a purpose-built LLM to Grafana so operators, developers, and SREs can troubleshoot issues, manage dashboards, and answer product questions in minutes. Whether you’re analyzing data, polishing dashboards for executives, or guiding teammates to navigation and knowledge resources, Assistant removes manual querying and helps teams move faster. Organizations save hours of toil and reduce operational cost by letting Assistant surface insights while engineers focus on higher-value work.
Tools: 102 · Prompts: 3
Developer-Tools
getstackrun
By STACK
STACK runs between AI agents and the systems they use. Each agent works under a short-lived Passport that states what it may do. STACK checks every call against that Passport, records suspicious behavior, can deny configured actions and writes each decision to a hash-chained audit log. This connector brings STACK's governance into the conversation. With it you can: - register an agent, and list your agents, their permissions and any that are blocked - grant or narrow an agent's access to a connected service. A new grant, or any widening, needs a human to approve it in the STACK Console; narrowing applies immediately - see active Passports and revoke one, every Passport for an agent, or all of them - open a Mission with a spend or action limit, complete or revoke it, and see what an agent did in it - decide flagged Passport checkouts waiting for review - read the audit log, verify its hash chain and export signed records - list security events, adjust detector and PII-redaction settings (loosening needs human approval) and scan text for prompt injection - manage notification rules, inbound webhooks, drop-offs and fleets - read your white-label partner tenants and Connect grants - post and browse public skill requests - check usage A revocation applies to the agent's next call through STACK and cascades to any Passports it delegated. Two tools reach outside STACK: verifying a connection makes one test call to the provider with the stored credential (never shown), and scanning for prompt injection sends flagged content to an LLM classifier on OpenRouter (Claude Haiku 4.5); STACK keeps the verdict and matched snippets, not the content. The connector does not connect or display credentials, issue Passports or run paid skills; those stay in the STACK Console, CLI and full MCP endpoint. Sign-in uses OAuth; a token issued to this connector is refused by the full endpoint. Requires a STACK account. Setup: https://getstack.run/docs/mcp-setup#directory
Tools: 96
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
Developer-Tools
Firezone
By Firezone, Inc.
Unleash the full power of the Firezone REST API using Claude! All REST API operations are available, empowering you to: 1. Create Actors, Groups, Resources, and Policies to manage secure access 2. View audit logs to drill down into who accessed what and when 3. Troubleshoot configuration and access issues quickly
Tools: 89
Developer-Tools
Beaam
By Teqnyk
Beaam keeps watch over the services behind your product and brings forward only what needs attention. Use the connector to inspect current health, review monitoring coverage, investigate incidents and likely causes, manage watchlists and alert rules, and test notification delivery. Calls are scoped to the connected Beaam organization. Read-only and destructive actions are annotated independently so Claude can ask for confirmation when appropriate. Beaam supports Cloudflare, Vercel, Netlify, Supabase, Neon, MongoDB Atlas, Sentry, Stripe, Polar, Resend, DigitalOcean, Hostinger, HTTP endpoints, and MCP servers. It can also connect providers, schedule maintenance, route notifications, and help apply a monitoring plan generated from a project. Every tool uses the same capability layer as the Beaam web app and API, under row-level security scoped to the signed-in organization. Billing, subscription changes, API-key issuance, and organization administration are deliberately not exposed.
Tools: 81
Developer-Tools
CTX
By Cloud Transit Xchange Inc.
CTX connects your cloud, data centers and sites. With the CTX connector, Claude reads your CTX services the same way the CTX console shows them: - Kontrol Edge ports, cloud connections, internet, DC interconnect, backbone, firewall and SD-WAN services, with traffic and errors. - CTX Reflector V2 and v1 reflectors, BGP neighbors, learned, installed and advertised routes, visibility and logs. - Alarms, incidents, outages and planned maintenance. Sign in with your CTX account, including multi-factor authentication and your company's single sign-on. Claude sees only what your account sees: a customer sees its own services, a partner sees its customers. Every tool is read-only: Claude can answer and explain, never change anything. Ask things like "Which of my cloud connections are down?", "Show the BGP neighbors of my reflectors that are not established" or "Was there an incident on my services this week?".
Tools: 81
Grafana MCP Server
By Grafana Labs
An MCP server giving access to Grafana dashboards, datasources, alerting, and more
Tools: 81
Data-Analytics
Moesif
By Moesif
Moesif is the API analytics and monetization platform for teams that treat their APIs as a product. Connect it to Claude and you can understand, manage and monetize your APIs just by asking. Get answers in plain English. "How did traffic and errors look last week?" "Which customers are still calling our v1 endpoints?" "Show me what went wrong on checkout in the last 24 hours." "How much has Acme Corp used this billing period against their plan?" Claude looks at your real data and gives you the answer, not a query to debug. Go from insight to action in the same conversation. Claude can help you: Build cohorts of users and companies, like "customers whose error rate crossed 2% this week" or "accounts close to their plan limit." Set up alerts so your team hears about error spikes, slowdowns or usage drops before your customers do. Create governance rules to enforce quotas, block abusive traffic, or guide customers who outgrow their plan. Organize workspaces and dashboards your whole team can share, with the charts that matter to you. Track adoption with funnels and retention, and see how individual customers use your API. Run usage-based billing: define meters and plans, connect your billing provider, and check what each customer will be invoiced. You stay in control. You sign in with your own Moesif account and choose which organization and app Claude can see, and whether it can only read or can also make changes. Claude asks before it changes or deletes anything. Built around your data. Every Moesif app has its own fields. Claude checks what your data actually contains before it answers, so you get results that fit your workspace instead of generic guesses. Requires a Moesif account.
Tools: 78
Business & Operations
LogMeIn Resolve
By GoTo Technologies USA, LLC
LogMeIn Resolve is a unified endpoint management (UEM) and remote monitoring and management (RMM) platform for internal IT teams and managed service providers (MSPs). This connector brings your Resolve environment into Claude, so you can ask about your fleet in plain language and act on the answer in the same place. What IT teams use it for: - See the whole estate at once — device health, alerts, and inventory across every account and tenant you manage, instead of clicking through them one by one - Cut alert noise — review what's firing, spot the pattern, and acknowledge in bulk - Automate the busywork — run scripts and Remote Execution jobs across the fleet, then check status without opening a separate console - Move tickets forward — read the queue, draft updates, and open tickets with the right service and priority already set - Answer hardware and software inventory questions on the spot — what's deployed, where, and on which version, across every device you manage - Capture what you learn — turn a resolved issue into a Knowledge Base article while the detail is still fresh - Start remote support faster — set up a session and send the invitation without leaving the conversation - Connect Resolve to your other tools — e.g., “Check this device's alert history in Resolve, then post a summary to our incident channel in Slack.” The connector is most valuable where endpoint data meets everything around it: correlating an alert with the ticket it produced, or turning device and ticket history into a report a client can read. It acts on behalf of the signed-in technician and stays within that user's existing Resolve permissions. Read actions never change data; creates, updates, and session actions are yours to approve. Requires a LogMeIn Resolve account. Learn more at logmein.com/products/resolve.
Tools: 77 · Prompts: 3
Developer-Tools
Uptimeify
By Uptimeify
Uptimeify is a white-label monitoring platform for agencies and MSPs, hosted in the EU. Failures are confirmed from multiple locations before an incident opens, and status pages and reports carry your own brand. This connector brings your monitoring into Claude, so you can check sites, investigate outages and manage client setups in plain language. Run live checks: website status and response time, SSL certificates, DNS records and propagation, MX, SPF, DKIM and DMARC, DNS blacklists, WHOIS and domain expiry, HTTP headers, HSTS, redirects, open ports, ping, IP geolocation, ASN and reverse DNS. Work with your account data: list monitors across website, DNS, ICMP, TCP, FTP, SMTP, SSH and IMAP/POP, see current status, check history and uptime, review incidents, inspect alert channels and alert delivery to find out why nobody was notified, and look up status pages, maintenance windows, customers, users and SMS usage. Make changes when you allow it: pause or resume monitors, change check intervals, create website monitors, acknowledge and resolve incidents, post status page updates, schedule maintenance windows, and manage status pages, custom domains, tags, email and SMS alert channels, customers and scheduled reports. You stay in control. On the consent screen you choose each area separately, and every write area starts unchecked. Claude only sees the tools you granted, and only the data your Uptimeify role can access, so a customer-restricted user sees only that customer. Deletions require explicit confirmation. You can revoke access at any time under Settings, Connected apps. Example prompts: "Which of my monitors are down right now?" "Why did nobody get an alert for the outage at deinkunde.com last night?" "Check SSL, SPF and DMARC for deinkunde.com." "Schedule a maintenance window for deinkunde.com on Saturday from 22:00 to 02:00." Requires an Uptimeify account. Your monitoring data is hosted and processed in the EU, in line with the GDPR.
Tools: 76
Developer Tools
Nobl9
By Nobl9
Nobl9 is the reliability platform, built on service level objectives (SLOs) and error budgets. It tells you whether the services your customers depend on are working, how much room you have before they notice a problem, and what to fix first. With this app, you can ask ChatGPT those questions in plain words and get answers from your own live Nobl9 data, in the same conversation where you do the rest of your work. Ask things like: Which of my services are closest to burning their error budget this month? What reliability target should the payments API have, given how it has behaved? Which alerts fired this week and which ones mattered? Set up a target for this service, and show me before you change anything. What you get: a straight answer on service health in one question; the story behind an alert, with the data that fired it; reliability targets built from how your services behave for users, with the error budget tracked against real monitoring data; alerts that page when a budget is burning fast and stay quiet when it drifts slowly; a status update you can paste into a channel, written from the numbers. Nobl9 works from the monitoring tools your team already runs, including Prometheus, Datadog, Dynatrace, New Relic, Amazon CloudWatch, Google Cloud Monitoring, Splunk and others, so there is nothing new to instrument and the answers match your dashboards. What it can do: read your services, SLOs, error budgets, alerts and connected data sources; run a query against a connected data source; and draft, validate or apply an SLO or alert policy when you ask. How it stays safe: you sign in with your own Nobl9 account, and ChatGPT sees only what you can see. Asking questions never changes anything. When you ask it to set up or change a target or an alert, it drafts the change, validates it against your organization, and shows you the full definition. Requires a Nobl9 account. Documentation: docs.nobl9.com/tools-and-utilities/mcp-server
Tools: 74 · Prompts: 3
Data & Analytics
Datadog Experiments
By Datadog Inc
This plugin is the best way to agentically interact with Datadog Product Analytics, Feature Flagging, and Experimentation
Tools: 73 · Prompts: 3
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
Need a custom investigate issues integration built?