Monitoring connectors
19 pre-built Monitoring connectors — 365 MCP tools in all: Better Stack, incident.io, Rootly. Paste your credentials and your agent can call them. No MCP server to write.
Checkmk monitoring: hosts and their configuration, live service states, acknowledged and unhandled problems, host groups and downtimes. REST API on your own site, bearer-style automation user auth.
Better Stack uptime monitoring and incident management: monitors and heartbeats with availability and response times, incidents with acknowledge, escalate and resolve, on-call calendars, escalation policies, status pages and status reports, and the configured integrations.
Read & triage Bugsnag (now SmartBear Insight Hub) errors, projects, organizations, releases, pivots from any AI agent. 9 tools, token auth.
Query Datadog (metrics, logs, monitors, events, incidents, dashboards) from any AI agent. 8 tools, dual-key auth.
Dynatrace observability through the Environment API v2: Davis problems with root cause and impact, monitored entities and tags, metrics and metric queries, log search, events, security problems, SLOs, settings and the audit log. Comment on problems, send deployment and custom events, tag entities.
Let your AI read your Grafana: search dashboards and see their panels and queries, query Prometheus, Loki and SQL data sources, see which alerts are firing and how the rules are defined, read and add annotations, and list contact points, users and teams. Works with Grafana Cloud and self-hosted Grafana.
Let your AI read your Home Assistant: the current state of every sensor, light, door and thermostat, the recorded history, the logbook of what happened when, and your calendars. Read-only: it never controls devices. Works with self-hosted Home Assistant.
incident.io incident response: incidents with updates and timeline, severities, statuses, roles, types and custom fields, actions and follow-ups, alerts and alert sources, on-call schedules and escalations, users, teams and the catalog. Declare and edit incidents, post updates, resolve alerts and page people.
Netskope Security Service Edge, read-only: search alerts and events (application, web, network, incident, endpoint DLP), the admin audit log, user risk scores, Cloud Confidence Index lookups, URL lists, Private Access publishers and apps, and SCIM users and groups.
Query New Relic (NRQL, alerts, incidents, dashboards, deployments, entities) from any AI agent via NerdGraph + REST. 7 tools, API-key auth.
Activity feed of a 1Password Business account from the 1Password Events API: sign-in attempts with outcome, client and location, item usage events (fill, reveal, copy, export, share) and audit events for user, vault, group and permission changes. Read-only; it never returns secret values.
Let your AI work with PagerDuty: see open incidents with their timeline, alerts and notes, find out who is on call, read services, escalation policies, schedules and teams, acknowledge, resolve, reassign or escalate incidents after confirming with you, and pull incident analytics.
Rollbar error monitoring: items with their history and occurrences, top active items and occurrence reports, the Metrics API, deploys, environments and code versions, RQL queries, and the account's projects, users and teams. Resolve, mute, assign and snooze items, comment, and report deploys.
Rootly incident management: incidents with timeline, action items and status page updates, alerts, services, functionalities, teams, severities and incident types, on-call (who is on call, schedules, shifts, escalation policies), status pages and retrospectives. Declare, update, mitigate and resolve incidents, acknowledge and resolve alerts.
Inspect Sentry projects, issues, and error events.
Search Splunk logs and metrics from Claude, ChatGPT or Copilot through Splunk's official MCP Server: run SPL and saved searches, list indexes, hosts and sources, read knowledge objects, and draft SPL with Splunk AI Assistant.
Atlassian Statuspage management API: status pages, components and groups with uptime, incidents and scheduled maintenances with their updates, incident templates, subscribers and system metrics. Open and update incidents, announce maintenances, change component statuses and manage subscribers.
Manage UptimeRobot (uptime monitoring) monitors, alert contacts, maintenance windows, public status pages from any AI agent. 8 tools, API-key auth.
Zabbix monitoring: hosts, host groups, items, triggers, active problems, events and the latest measured values. JSON-RPC API over a single endpoint, bearer API token.
Browse by category
- E-commerce64
- Accounting38
- CRM38
- Public Data37
- Infrastructure29
- Messaging29
- Productivity25
- Analytics24
- ERP23
- Project Management23
- Payments22
- HR20
- Monitoring19
- Databases18
- Finance17
- Logistics16
- Customer Support15
- Email14
- Marketing Automation13
- Social Media13
- Data Enrichment12
- Publishing12
- Sports12
- File Storage12
- Scheduling11
- E-Signature10
- Time Tracking10
- Advertising9
- Government9
- Banking6
- CMS6
- Forms & Surveys6
- IT Service Management6
- Knowledge Base6
- Mapping5
- Field Service4
- Food & Drink4
- Document Management3
- Real Estate3
- Transport3
- Travel3
- Construction2
- Healthcare2
- Gaming1
- Remote Access1
- Wholesale1
All 19 connectors, A–Z
Missing a connector? Add it in a JSON.
Every adapter is a single JSON file under packages/backend/src/adapters/. Copy one, swap endpoint and auth, open a PR — validated by parameterized tests at build time.
// adapters/de/my-adapter.json
{
"slug": "my-erp",
"name": "My ERP",
"category": "erp",
"authType": "BEARER_TOKEN",
"tools": [/* ... */]
}