Sentry MCP integration for AI agents.
Allow AI agents to inspect Sentry organizations, projects, issues, events, releases, integrations, and release health through structured actions.
- ACTION CONTRACTS
- 19
- AUTHENTICATION
- OAuth 2.0
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Sentry integration exposes
The Sentry Agent App provides investigation primitives rather than an automatic claim that an error has been fixed. Agents can list organization projects and unresolved issues, retrieve a specific event, and inspect release context before proposing engineering work.
Error payloads may contain user data, request details, stack traces, and secrets accidentally captured by an application. The agent should retrieve only the event fields needed for diagnosis, redact sensitive values, and link back to Sentry rather than copying complete payloads into other systems.
VERIFIED ACTION SAMPLE
Real Sentry capabilities.
Showing 12 of 19 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_alertREADGet one alert workflow in a Sentry organization by workflow id.
INPUTS: organizationIdOrSlug / alertId
update_issueWRITEUpdate mutable attributes on one Sentry issue, such as status, assignment, or bookmarks.
INPUTS: organizationIdOrSlug / issueId / status / hasSeen / isPublic
get_issueREADGet one issue in a Sentry organization by numeric id or short id.
INPUTS: organizationIdOrSlug / issueId
get_issue_eventREADGet one event for a Sentry issue by event id, or use latest, oldest, or recommended selectors.
INPUTS: organizationIdOrSlug / issueId / eventId / environments
get_organization_integrationREADGet one installed Sentry organization integration by its integration id.
INPUTS: organizationIdOrSlug / integrationId
get_organization_integration_configREADList available integration provider configs for a Sentry organization, optionally filtered by provider key.
INPUTS: organizationIdOrSlug / providerKey
get_organization_releaseREADGet one release in a Sentry organization, with optional health and summary statistics included.
INPUTS: organizationIdOrSlug / version / health / summaryStatsPeriod / healthStatsPeriod
get_projectREADGet one Sentry project by organization and project slug or id.
INPUTS: organizationIdOrSlug / projectIdOrSlug
get_release_health_statsREADRetrieve release health session statistics for one Sentry release by querying the sessions endpoint with that release version.
INPUTS: organizationIdOrSlug / version / fields / groupBy / query
get_replayREADGet one replay instance in a Sentry organization by replay id.
INPUTS: organizationIdOrSlug / replayId / start / end / statsPeriod
get_sentry_appREADGet one Sentry App by id or slug, including integration metadata and OAuth client settings.
INPUTS: sentryAppIdOrSlug
list_alertsREADList alert workflows for a Sentry organization, with optional id, project, and search filters.
INPUTS: organizationIdOrSlug / ids / query / sortBy / projectIds
INPUT CONTRACTS
Know what the action needs before it runs.
get_alert
organizationIdOrSlugREQUIRED- The organization id or slug that owns the alert workflow.
alertIdREQUIRED- The alert workflow id to retrieve.
update_issue
organizationIdOrSlugREQUIRED- The organization id or slug that owns the issue.
issueIdREQUIRED- The Sentry issue id to update.
statusOPTIONAL- The new issue status such as resolved, resolvedInNextRelease, unresolved, or ignored.
hasSeenOPTIONAL- Whether the current user has seen the issue after this update.
isPublicOPTIONAL- Whether the issue should be visible via a public permalink.
get_issue
organizationIdOrSlugREQUIRED- The organization id or slug that owns the issue.
issueIdREQUIRED- The Sentry issue id or short id to retrieve.
get_issue_event
organizationIdOrSlugREQUIRED- The organization id or slug that owns the issue.
issueIdREQUIRED- The Sentry issue id whose event should be retrieved.
eventIdREQUIRED- The event id or selector such as latest, oldest, or recommended.
environmentsOPTIONAL- The environment names used to filter which issue event Sentry selects.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Production triage
List unresolved issues for a named project, inspect representative events, and rank findings with links to evidence.
Regression investigation
Compare an issue timeline with release health and repository commits before opening engineering work.
Customer-impact review
Extract only the identifiers needed to connect an incident with CRM or support context.
SAFETY BOUNDARY
Operate Sentry with explicit limits
- Treat stack traces and event payloads as potentially sensitive.
- Limit reads to the named organization and project.
- Do not resolve or ignore an issue solely from model classification.
- Verify release and issue identifiers before updating state.
CONNECTION MODEL
OAuth 2.0
Sentry uses OAuth 2.0. Connection requirements and availability are determined by the provider and the Working Machines deployment.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 18
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Sentry.