NeuralTrust ha sido reconocido por Gartner → Leer más

Conecta Sentry MCP a tus agentes de IA, de forma segura.

Un único endpoint seguro para cada llamada a Sentry que hacen tus agentes de IA: acotada por usuario, inspeccionada y registrada.

Elige las herramientas que pueden usar tus agentes de IA

76 herramientas del esquema de Sentry MCP.

Mostrando 76 herramientas

  • search_issuesreadSearches for grouped issues in Sentry using natural language. Returns a list of issues, not counts or aggregations.
  • get_issue_detailsreadGets detailed information about a specific Sentry issue by ID, URL or event ID, including metadata, tags and stack traces.
  • get_issue_tag_valuesreadGets the distribution of values for a tag on an issue.
  • search_issue_eventsreadSearches the events within a single issue using Sentry query syntax.
  • update_issuewriteUpdates an issue's status or assignment in Sentry.
  • add_issue_notewriteAdds a human-visible comment to a Sentry issue's activity feed.
  • get_issue_activityreadGets the activity feed and comments for a Sentry issue.
  • get_issue_user_reportsreadGets legacy User Reports or crash-report feedback attached to a Sentry issue.
  • link_issuewriteLinks an existing external ticket or GitHub pull request to a Sentry issue by URL.
  • unlink_issuewriteRemoves an external ticket or GitHub pull request reference from a Sentry issue by URL.
  • search_eventsreadSearches events and replays, and performs counts and aggregations. The only tool for statistics.
  • get_event_stacktracereadGets the full stack trace for an event.
  • get_issue_breadcrumbsreadGets the breadcrumbs recorded before an error occurred.
  • get_trace_detailsreadGets the details of a distributed trace.
  • get_event_attachmentreadDownloads attachments from a Sentry event.
  • get_sentry_resourcereadReads a single Sentry resource by ID or URL: issues, events, traces, replays and profiles.
  • find_dropped_eventsreadFinds events that were dropped before being stored in Sentry, showing what was and was not ingested.
  • get_agent_conversation_detailsreadFetches the chronological transcript and debugging details for one agent conversation, formerly called an AI conversation.
  • get_ai_conversation_detailsreadDeprecated alias for get_agent_conversation_details.
  • get_latest_base_snapshotreadGets the latest UI screenshots/images for an app from the preprod snapshot system.
  • get_profilereadAnalyzes CPU profiling data to identify performance bottlenecks and detect regressions.
  • get_profile_detailsreadInspects a specific Sentry profile in detail.
  • get_replay_detailsreadGets high-level information about a specific Sentry replay by URL or replay ID.
  • get_snapshotreadGets a preprod snapshot comparison summary, including metadata, counts, and changed image sections.
  • get_snapshot_imagereadGets metadata and image content for one image in a preprod snapshot.
  • get_span_detailsreadGets detailed information about a specific span within a Sentry trace.
  • search_agent_conversationsreadSearches Sentry Agent Conversations, formerly called AI Conversations, returning one summary row per conversation.
  • search_ai_conversationsreadDeprecated alias for search_agent_conversations.
  • search_errorsreadSearches Sentry error events: exceptions and crashes with stack traces.
  • search_logsreadSearches Sentry logs: application log entries, including error- and warning-severity log messages.
  • search_metricsreadSearches Sentry metrics: counters, gauges, and distributions, as rows or aggregates.
  • search_profilesreadSearches Sentry profiles: transaction and continuous profile results, profile IDs, and profiled transactions.
  • search_replaysreadSearches Sentry session replays: rage clicks, dead clicks, visited pages, errors seen, and replay users.
  • search_tracesreadSearches Sentry spans and traces: requests, API/HTTP calls, endpoints, DB queries, AI/LLM calls, and other operations.
  • analyze_issue_with_seerreadUses Seer to analyze a production error and return a root cause analysis with specific code fixes.
  • whoamireadIdentifies the authenticated user in Sentry.
  • find_organizationsreadFinds the organizations the user has access to in Sentry.
  • find_teamsreadFinds the teams in an organization.
  • find_projectsreadFinds the projects in Sentry.
  • find_releasesreadFinds releases in Sentry.
  • find_dsnsreadLists all Sentry DSNs for a specific project.
  • create_teamwriteCreates a new team in Sentry.
  • create_projectwriteCreates a new project in Sentry, including its DSN.
  • add_team_to_projecthigh riskGrants a team access to an existing Sentry project.
  • create_dsnwriteCreates an additional DSN for an existing project.
  • find_dashboardsreadFinds Sentry dashboards in an organization.
  • get_dashboard_detailsreadGets detailed information about a specific Sentry dashboard.
  • get_release_detailsreadGets details for a Sentry release.
  • remove_team_from_projecthigh riskRevokes a team's access to an existing Sentry project.
  • update_dsnwriteUpdates the settings of an existing DSN (client key) in a project, such as name, active status and rate limit.
  • update_projectwriteUpdates project metadata in Sentry, such as name, slug, and platform.
  • get_docreadFetches the full markdown content of a Sentry documentation page.
  • search_docsreadSearches Sentry documentation for SDK setup, instrumentation, and configuration guidance.
  • create_alert_rulewriteCreates a Sentry Alert (workflow) with notification actions and explicit sources.
  • create_metric_monitorwriteCreates a Sentry Metric Monitor with Static, Percent or Dynamic detection in a project.
  • create_uptime_monitorwriteCreates a Sentry HTTP uptime monitor.
  • delete_alert_rulehigh riskPermanently deletes a Sentry Alert (workflow), preserving its connected monitors.
  • delete_metric_monitorhigh riskPermanently deletes a Sentry Metric Monitor, preserving its connected Alerts and their other monitors.
  • delete_monitor_environmenthigh riskDeletes one environment from a Sentry cron monitor.
  • delete_uptime_monitorhigh riskDeletes a Sentry HTTP uptime monitor.
  • find_alert_rulesreadFinds Sentry alert rules.
  • find_metric_monitorsreadFinds Sentry Metric Monitors that evaluate errors, performance, logs, metrics or crash rates.
  • find_monitorsreadFinds Sentry cron monitors.
  • find_uptime_monitorsreadFinds Sentry uptime monitors.
  • get_alert_optionsreadDiscovers available actions, conditions, or sources for a Sentry Alert (notification workflow).
  • get_alert_rulereadGets details for a Sentry alert rule.
  • get_metric_monitor_detailsreadInspects a Sentry Metric Monitor's query, dataset, detection mode, thresholds, resolution conditions and connected Alerts.
  • get_monitor_detailsreadGets details for a Sentry cron monitor.
  • get_uptime_monitor_detailsreadGets details for a Sentry uptime monitor, including recent checks.
  • update_alert_rulewriteUpdates a Sentry Alert (workflow), including notification actions and connections.
  • update_metric_monitorwriteUpdates a Sentry Metric Monitor's query, detection conditions, metadata, status or connected Alerts.
  • update_uptime_monitorwriteUpdates a Sentry HTTP uptime monitor.
  • execute_sentry_toolhigh riskExecutes an available Sentry MCP tool discovered through search_sentry_tools.
  • get_sentry_mcp_inforeadGets information about the running Sentry MCP server.
  • onboarding_status_updatewriteUpdates the progress shown in Sentry's agentic onboarding UI.
  • search_sentry_toolsreadSearches the available Sentry MCP tool catalog by name and description.

Qué expone Sentry MCP

Sentry MCP agrupa sus 76 herramientas en 7 categorías, cada una con una política inicial sugerida.

Las 76 herramientas en JSON, listas para pegar.

CategoríaIncluyeAccesoPolítica sugerida
IssuesBúsqueda de issues en lenguaje natural o sintaxis Sentry, detalle, valores de etiquetas y actualizacionesLectura / EscrituraAudita los cambios de estado y las asignaciones
Eventos y trazasBúsqueda de eventos, agregaciones, stack traces, breadcrumbs, trazas y adjuntosLecturaTrata el contenido de los eventos como entrada no confiable
SeerAnálisis de causa raíz con IA y sugerencias de corrección de códigoLecturaContrasta los hallazgos con el código antes de actuar
OrganizaciónUsuario actual, organizaciones, equipos, proyectos, releases y DSNsLectura / EscrituraExige aprobación para crear proyectos y equipos
DocumentaciónBúsqueda y lectura de la documentación de SentryLecturaPermite búsquedas en la documentación
Alertas y monitoresReglas de alerta (workflows), monitores de métricas, monitores cron y monitores de disponibilidadLectura / EscrituraPermite lecturas; exige aprobación para crear, actualizar y eliminar alertas y monitores
Utilidades MCPBúsqueda en el catálogo de herramientas, ejecución dinámica de herramientas, información del servidor y progreso de onboardingLectura / EscrituraRevisa las llamadas a execute_sentry_tool, que puede ejecutar cualquier herramienta disponible

Conecta Sentry MCP a tu agente de IA

Cuatro pasos, menos de diez minutos.

  1. 01

    Inicia sesión en NeuralTrust

    Abre la plataforma de NeuralTrust, inicia sesión y ve a Getting started, después a Connect your tools.

    Inicia sesión en NeuralTrust
  2. 02

    Elige tu agente

    Cuando te pregunte qué agente usas, elige Claude Code, Codex, Cursor, Windsurf, Copilot o tu propio código.

    Elige tu agente
  3. 03

    Conecta Sentry

    Busca Sentry en la lista de herramientas y conéctalo.

    Conecta Sentry
  4. 04

    Conecta tu agente

    Sigue los pasos en pantalla para añadir la configuración a tu agente y envía el prompt de prueba.

    Conecta tu agente

Permisos hasta la herramienta individual

No permites ni bloqueas Sentry MCP entero. Permites exactamente las herramientas que puede llamar cada agente, una a una.

Sentry MCP76 HERRAMIENTAS DISPONIBLES
Agente de revisión de código4 herramientas, solo lectura
Bot de triaje de incidencias9 herramientas
Asistente del equipo de plataformalas 76 herramientas
  • Herramienta por herramientaConectar el servidor no es la unidad de acceso. Cada herramienta se concede por separado.
  • Denegado por defectoUna herramienta que no has activado nunca se expone al agente.
  • Aprobación en las escriturasLas herramientas que modifican o borran pueden exigir la confirmación de una persona.

¿Es seguro Sentry MCP?

Un endpoint en lugar de credenciales en claro. Cada llamada se comprueba contra la política y queda registrada.

Agentes de IASe conectan desde la configuración de tu cliente MCP.NeuralTrustSe aplican los controles según tu configuración.Sentry MCP76 herramientas documentadas.
Asistentes de códigoConexión y credencialespor usuarioEventos y trazas24 herramientas
Copilotos internosPolíticas de acceso a herramientasdenegado por defectoAlertas y monitores19 herramientas
Automatizaciones de flujosInspección de peticiones y respuestasen líneaOrganización16 herramientas
Clientes MCP compatiblesMonitorización de actividadalertas y registrosResto de herramientas17 herramientas
Preguntas frecuentes

Preguntas habituales sobre usar Sentry MCP a través de TrustGate.

Conecta Sentry MCP al instante

Elige las herramientas, apunta tu agente a TrustGate y Sentry MCP queda activo: acotado, inspeccionado y registrado.