sentry-automation
npx machina-cli add skill davepoon/buildwithclaude/sentry-automation --openclawSentry Automation via Rube MCP
Automate Sentry error tracking and monitoring operations through Composio's Sentry toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/sentry
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Sentry connection via
RUBE_MANAGE_CONNECTIONSwith toolkitsentry - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitsentry - If connection is not ACTIVE, follow the returned auth link to complete Sentry OAuth
- Confirm connection status shows ACTIVE before running any workflows
Core Workflows
1. Investigate Issues
When to use: User wants to find, inspect, or triage error issues
Tool sequence:
SENTRY_LIST_AN_ORGANIZATIONS_ISSUES- List issues across the organization [Required]SENTRY_GET_ORGANIZATION_ISSUE_DETAILS- Get detailed info on a specific issue [Optional]SENTRY_LIST_AN_ISSUES_EVENTS- View individual error events for an issue [Optional]SENTRY_RETRIEVE_AN_ISSUE_EVENT- Get full event details with stack trace [Optional]SENTRY_RETRIEVE_ISSUE_TAG_DETAILS- Inspect tag distribution for an issue [Optional]
Key parameters:
organization_id_or_slug: Organization identifierissue_id: Numeric issue IDquery: Search query (e.g.,is:unresolved,assigned:me,browser:Chrome)sort: Sort order (date,new,freq,priority)statsPeriod: Time window for stats (24h,14d, etc.)
Pitfalls:
organization_id_or_slugis the org slug (e.g., 'my-org'), not the display name- Issue IDs are numeric; do not confuse with event IDs which are UUIDs
- Query syntax uses Sentry's search format:
is:unresolved,assigned:me,!has:release - Events within an issue can have different stack traces; inspect individual events for details
2. Manage Project Issues
When to use: User wants to view issues scoped to a specific project
Tool sequence:
SENTRY_RETRIEVE_ORGANIZATION_PROJECTS- List projects to find project slug [Prerequisite]SENTRY_RETRIEVE_PROJECT_ISSUES_LIST- List issues for a specific project [Required]SENTRY_RETRIEVE_ISSUE_EVENTS_BY_ID- Get events for a specific issue [Optional]
Key parameters:
organization_id_or_slug: Organization identifierproject_id_or_slug: Project identifierquery: Search filter stringstatsPeriod: Stats time window
Pitfalls:
- Project slugs are different from project display names
- Always resolve project names to slugs via RETRIEVE_ORGANIZATION_PROJECTS first
- Project-scoped issue lists may have different pagination than org-scoped lists
3. Configure Alert Rules
When to use: User wants to create or manage alert rules for a project
Tool sequence:
SENTRY_RETRIEVE_ORGANIZATION_PROJECTS- Find project for the alert [Prerequisite]SENTRY_RETRIEVE_PROJECT_RULES_BY_ORG_AND_PROJECT_ID- List existing rules [Optional]SENTRY_CREATE_PROJECT_RULE_FOR_ALERTS- Create a new alert rule [Required]SENTRY_CREATE_ORGANIZATION_ALERT_RULE- Create org-level metric alert [Alternative]SENTRY_UPDATE_ORGANIZATION_ALERT_RULES- Update existing alert rules [Optional]SENTRY_RETRIEVE_ALERT_RULE_DETAILS- Inspect specific alert rule [Optional]SENTRY_GET_PROJECT_RULE_DETAILS- Get project-level rule details [Optional]
Key parameters:
name: Alert rule nameconditions: Array of trigger conditionsactions: Array of actions to perform when triggeredfilters: Array of event filtersfrequency: How often to trigger (in minutes)actionMatch: 'all', 'any', or 'none' for condition matching
Pitfalls:
- Project-level rules (CREATE_PROJECT_RULE) and org-level metric alerts (CREATE_ORGANIZATION_ALERT_RULE) are different
- Conditions, actions, and filters use specific JSON schemas; check Sentry docs for valid types
frequencyis in minutes; setting too low causes alert fatigueactionMatchdefaults may vary; explicitly set to avoid unexpected behavior
4. Manage Releases
When to use: User wants to create, track, or manage release versions
Tool sequence:
SENTRY_LIST_ORGANIZATION_RELEASES- List existing releases [Optional]SENTRY_CREATE_RELEASE_FOR_ORGANIZATION- Create a new release [Required]SENTRY_UPDATE_RELEASE_DETAILS_FOR_ORGANIZATION- Update release metadata [Optional]SENTRY_CREATE_RELEASE_DEPLOY_FOR_ORG- Record a deployment for a release [Optional]SENTRY_UPLOAD_RELEASE_FILE_TO_ORGANIZATION- Upload source maps or files [Optional]
Key parameters:
version: Release version string (e.g., '1.0.0', commit SHA)projects: Array of project slugs this release belongs todateReleased: Release timestamp (ISO 8601)environment: Deployment environment name (e.g., 'production', 'staging')
Pitfalls:
- Release versions must be unique within an organization
- Releases can span multiple projects; use the
projectsarray - Deploying a release is separate from creating it; use CREATE_RELEASE_DEPLOY
- Source map uploads require the release to exist first
5. Monitor Organization and Teams
When to use: User wants to view org structure, teams, or member lists
Tool sequence:
SENTRY_GET_ORGANIZATION_DETAILSorSENTRY_GET_ORGANIZATION_BY_ID_OR_SLUG- Get org info [Required]SENTRY_LIST_TEAMS_IN_ORGANIZATION- List all teams [Optional]SENTRY_LIST_ORGANIZATION_MEMBERS- List org members [Optional]SENTRY_GET_PROJECT_LIST- List all accessible projects [Optional]
Key parameters:
organization_id_or_slug: Organization identifiercursor: Pagination cursor for large result sets
Pitfalls:
- Organization slugs are URL-safe identifiers, not display names
- Member lists may be paginated; follow cursor pagination
- Team and member visibility depends on the authenticated user's permissions
6. Manage Monitors (Cron Monitoring)
When to use: User wants to update cron job monitoring configuration
Tool sequence:
SENTRY_UPDATE_A_MONITOR- Update monitor configuration [Required]
Key parameters:
organization_id_or_slug: Organization identifiermonitor_id_or_slug: Monitor identifiername: Monitor display nameschedule: Cron schedule expression or intervalcheckin_margin: Grace period in minutes for late check-insmax_runtime: Maximum expected runtime in minutes
Pitfalls:
- Monitor slugs are auto-generated from the name; use slug for API calls
- Schedule changes take effect immediately
- Missing check-ins trigger alerts after the margin period
Common Patterns
ID Resolution
Organization name -> Slug:
1. Call SENTRY_GET_ORGANIZATION_DETAILS
2. Extract slug field from response
Project name -> Slug:
1. Call SENTRY_RETRIEVE_ORGANIZATION_PROJECTS
2. Find project by name, extract slug
Pagination
- Sentry uses cursor-based pagination with
Linkheaders - Check response for cursor values
- Pass cursor in next request until no more pages
Search Query Syntax
is:unresolved- Unresolved issuesis:resolved- Resolved issuesassigned:me- Assigned to current userassigned:team-slug- Assigned to a team!has:release- Issues without a releasefirst-release:1.0.0- Issues first seen in releasetimes-seen:>100- Seen more than 100 timesbrowser:Chrome- Filter by browser tag
Known Pitfalls
ID Formats:
- Organization: use slug (e.g., 'my-org'), not display name
- Project: use slug (e.g., 'my-project'), not display name
- Issue IDs: numeric integers
- Event IDs: UUIDs (32-char hex strings)
Permissions:
- API token scopes must match the operations being performed
- Organization-level operations require org-level permissions
- Project-level operations require project access
Rate Limits:
- Sentry enforces per-organization rate limits
- Implement backoff on 429 responses
- Bulk operations should be staggered
Quick Reference
| Task | Tool Slug | Key Params |
|---|---|---|
| List org issues | SENTRY_LIST_AN_ORGANIZATIONS_ISSUES | organization_id_or_slug, query |
| Get issue details | SENTRY_GET_ORGANIZATION_ISSUE_DETAILS | organization_id_or_slug, issue_id |
| List issue events | SENTRY_LIST_AN_ISSUES_EVENTS | issue_id |
| Get event details | SENTRY_RETRIEVE_AN_ISSUE_EVENT | organization_id_or_slug, event_id |
| List project issues | SENTRY_RETRIEVE_PROJECT_ISSUES_LIST | organization_id_or_slug, project_id_or_slug |
| List projects | SENTRY_RETRIEVE_ORGANIZATION_PROJECTS | organization_id_or_slug |
| Get org details | SENTRY_GET_ORGANIZATION_DETAILS | organization_id_or_slug |
| List teams | SENTRY_LIST_TEAMS_IN_ORGANIZATION | organization_id_or_slug |
| List members | SENTRY_LIST_ORGANIZATION_MEMBERS | organization_id_or_slug |
| Create alert rule | SENTRY_CREATE_PROJECT_RULE_FOR_ALERTS | organization_id_or_slug, project_id_or_slug |
| Create metric alert | SENTRY_CREATE_ORGANIZATION_ALERT_RULE | organization_id_or_slug |
| Create release | SENTRY_CREATE_RELEASE_FOR_ORGANIZATION | organization_id_or_slug, version |
| Deploy release | SENTRY_CREATE_RELEASE_DEPLOY_FOR_ORG | organization_id_or_slug, version |
| List releases | SENTRY_LIST_ORGANIZATION_RELEASES | organization_id_or_slug |
| Update monitor | SENTRY_UPDATE_A_MONITOR | organization_id_or_slug, monitor_id_or_slug |
Powered by Composio
Source
git clone https://github.com/davepoon/buildwithclaude/blob/main/plugins/all-skills/skills/sentry-automation/SKILL.mdView on GitHub Overview
Automate error tracking and monitoring in Sentry using Composio's Rube MCP toolkit. This skill covers managing issues/events, configuring alert rules, tracking releases, and monitoring projects and teams, with guidance to always fetch current tool schemas first.
How This Skill Works
Connect Rube MCP to Sentry, verify the connection is ACTIVE, and fetch current schemas with RUBE_SEARCH_TOOLS. Then drive workflows using the SENTRY_* commands (e.g., list issues, retrieve issue details, manage alerts) to automate routine Sentry tasks across organizations and projects.
When to Use It
- Investigate and triage issues across an organization (Investigate Issues workflow).
- View or manage issues scoped to a specific project (Manage Project Issues workflow).
- Create, update, or inspect alert rules for a project (Configure Alert Rules workflow).
- Monitor releases and project health by querying issues and events (Release/Health monitoring).
- Onboard a new Sentry connection and validate the MCP integration setup (Setup/Verification).
Quick Start
- Step 1: Add the MCP server (https://rube.app/mcp) and run RUBE_SEARCH_TOOLS to fetch current tool schemas.
- Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkit 'sentry' and complete OAuth if prompted; ensure the status becomes ACTIVE.
- Step 3: Run a starter workflow like Investigate Issues (SENTRY_LIST_AN_ORGANIZATIONS_ISSUES) to confirm setup.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to get the current tool schemas before running any workflows.
- Explicitly connect to Sentry with RUBE_MANAGE_CONNECTIONS and the 'sentry' toolkit, then authenticate if prompted.
- Verify the connection status is ACTIVE before executing any workflows.
- Resolve project slugs by first listing organization projects (RETRIEVE_ORGANIZATION_PROJECTS) to avoid slug/name mixups.
- Use Sentry-specific query syntax (e.g., is:unresolved, assigned:me) and keep IDs distinct (numeric for issues, UUIDs for events).
Example Use Cases
- Triaging an unresolved error across the organization using SENTRY_LIST_AN_ORGANIZATIONS_ISSUES.
- Listing issues for a specific project and drilling into event details with SENTRY_LIST_AN_ISSUES_EVENTS and SENTRY_RETRIEVE_AN_ISSUE_EVENT.
- Creating a new alert rule for a project with SENTRY_CREATE_PROJECT_RULE_FOR_ALERTS and validating with SENTRY_RETRIEVE_ALERT_RULE_DETAILS.
- Inspecting a project's stack trace by retrieving a specific issue event via SENTRY_RETRIEVE_AN_ISSUE_EVENT.
- Onboarding a new Sentry project by establishing an ACTIVE RUBE MCP connection and confirming via a simple issue query.
Frequently Asked Questions
Related Skills
terraform
chaterm/terminal-skills
Terraform 基础设施即代码
ansible
chaterm/terminal-skills
Ansible 自动化运维
monitoring
chaterm/terminal-skills
监控与告警
git-advanced
chaterm/terminal-skills
Git 高级操作
CI/CD Pipeline Security Expert
martinholovsky/claude-skills-generator
Expert in CI/CD pipeline design with focus on secret management, code signing, artifact security, and supply chain protection for desktop application builds
datadog-automation
davepoon/buildwithclaude
Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.