Provides 27 tools for error monitoring, performance tracking, and application health analysis in Sentry. Features include exception and message capture, breadcrumb tracking, transaction monitoring, session management, project/issue management, release creation, alert rule configuration, and error searching capabilities.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Sentry para Cursor list recent unresolved issues in the coflow project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Um servidor MCP completo para integração com Sentry no Cursor, oferecendo 27 ferramentas para monitoramento de erros, performance e saúde de aplicações.
27 Ferramentas Completas: 12 SDK + 15 API
Release Health: Monitoramento completo de sessões
Performance Monitoring: Transações e spans
Alertas Customizados: Regras de alerta automatizadas
Busca Avançada: Por arquivo, short ID, queries complexas
Setup Automático: Configuração de projetos com um comando
Monitor em Tempo Real: Script de monitoramento incluído
Related MCP server: Sentry MCP Server
cd /Users/agents/Desktop/context-engineering-intro/sentry-mcp-cursor
npm install
npm run build# Edite config.env com suas credenciais (já configurado)
nano config.env./add-to-cursor.sh./start-cursor.sh - Script otimizado para Cursor
./start-standalone.sh - Inicia com validações e status detalhado
./start.sh - Script padrão
./start-mcp.sh - Script com configurações hardcoded
./test-standalone.sh - Executa suite completa de testes
./monitor.sh - NOVO! Monitor em tempo real com estatísticas
./add-to-cursor.sh - NOVO! Adiciona ao Cursor automaticamente
./add-to-claude-code.sh - Adiciona ao Claude Code
./remove-from-claude-code.sh - Remove do Claude Code
mcp__sentry__sentry_capture_exception - Captura exceções
mcp__sentry__sentry_capture_message - Captura mensagens
mcp__sentry__sentry_add_breadcrumb - Adiciona breadcrumbs
mcp__sentry__sentry_set_user - Define usuário
mcp__sentry__sentry_set_tag - Define tags
mcp__sentry__sentry_set_context - Define contexto
mcp__sentry__sentry_start_transaction - Inicia transação
mcp__sentry__sentry_finish_transaction - Finaliza transação
mcp__sentry__sentry_start_session - Inicia sessão
mcp__sentry__sentry_end_session - Finaliza sessão
mcp__sentry__sentry_set_release - Define release
mcp__sentry__sentry_capture_session - Captura sessão
mcp__sentry__sentry_list_projects - Lista projetos
mcp__sentry__sentry_list_issues - Lista issues
mcp__sentry__sentry_create_release - Cria release
mcp__sentry__sentry_list_releases - Lista releases
mcp__sentry__sentry_get_organization_stats - Estatísticas
mcp__sentry__sentry_create_alert_rule - Cria alertas
mcp__sentry__sentry_resolve_short_id - Resolve IDs curtos
mcp__sentry__sentry_get_event - Obtém evento
mcp__sentry__sentry_list_error_events_in_project - Lista erros
mcp__sentry__sentry_create_project - Cria projeto
mcp__sentry__sentry_list_issue_events - Lista eventos de issue
mcp__sentry__sentry_get_issue - Obtém issue
mcp__sentry__sentry_list_organization_replays - Lista replays
mcp__sentry__sentry_setup_project - Setup de projeto
mcp__sentry__sentry_search_errors_in_file - Busca erros em arquivo
No Cursor, as ferramentas ficam disponíveis com o prefixo mcp__sentry__:
// Capturar exceção
await mcp__sentry__sentry_capture_exception({
error: "Database connection failed",
level: "error",
tags: {
component: "database"
}
});
// Listar projetos
await mcp__sentry__sentry_list_projects();
// Criar release
await mcp__sentry__sentry_create_release({
version: "app@1.0.0",
projects: ["coflow"]
});Execute o monitor para acompanhar estatísticas:
./monitor.shO monitor exibe:
Status do servidor MCP
Configuração no Cursor
Estatísticas das últimas 24h
Issues não resolvidas
Última release
Total de ferramentas disponíveis
Atualização automática a cada 30s
Execute a suite completa de testes:
./test-standalone.sh# Verificar configuração
cat ../.cursor/mcp.json
# Reinstalar
./add-to-cursor.sh
# Reiniciar Cursor# Verificar se o servidor está rodando
ps aux | grep "node dist/index.js"
# Reiniciar servidor no CursorSENTRY_DSN=https://782bbb46ddaa4e64a9a705e64f513985@o927801.ingest.us.sentry.io/5877334
SENTRY_AUTH_TOKEN=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
SENTRY_ORG=coflow
SENTRY_API_URL=https://sentry.io/api/0/
SENTRY_RELEASE=mcp-sentry-cursor@1.0.0
SENTRY_ENVIRONMENT=production✅ Script monitor.sh para monitoramento em tempo real
✅ Script add-to-cursor.sh para instalação automatizada
✅ Melhor suporte para config.env no start-cursor.sh
✅ Documentação atualizada com prefixos do Cursor
MIT
Desenvolvido com ❤️ para Cursor
Add a breadcrumb for debugging context
Inputs: message (required), category, level, data.
Capture and send an exception to Sentry
Inputs: error (required), level, tags, context, +1 more.
Capture and send a message to Sentry
Inputs: message (required), level, tags, context.
Manually capture a session for server-mode/request-mode
Inputs: sessionId (required), distinctId, status, duration, +1 more.
Create an alert rule for a project
Inputs: projectSlug (required), name (required), conditions, actions, +1 more.
Create a new project in Sentry. Track deployments, releases and health metrics.
Inputs: name (required), slug (required), team (required), platform.
Create a new release
Inputs: version (required), projects, url, dateReleased.
End the current session with a specific status
Inputs: status.
Finish the current transaction
Inputs: status.
Retrieve a specific Sentry event from an issue. Requires issue ID/URL and event ID.
Inputs: projectSlug (required), eventId (required).
Retrieve and analyze a Sentry issue. Accepts issue URL or ID.
Inputs: issueId (required).
Get organization statistics
Inputs: stat (required), since, until, resolution.
List error events from a specific Sentry project. View recent errors, frequency patterns and occurrence timestamps.
Inputs: projectSlug (required), limit, query.
List events for a specific Sentry issue. Analyze event details, metadata and patterns.
Inputs: issueId (required), limit.
List issues for a project
Inputs: projectSlug (required), query.
List replays from a Sentry organization. Monitor user sessions, interactions, errors and experience issues.
Inputs: project, limit, query.
List all projects in the organization
Inputs: no named parameters.
List releases for a project
Inputs: projectSlug (required).
Retrieve details about an issue using its short ID. Maps short IDs to issue details, project context and status.
Inputs: shortId (required).
Search for Sentry errors occurring in a specific file. Find all issues related to a particular file path or filename.
Inputs: projectSlug (required), filename (required).
Set custom context data
Inputs: name (required), context (required).
Set the release version for release health tracking
Inputs: release (required), dist.
Set a tag that will be sent with all events
Inputs: key (required), value (required).
Set up Sentry for a project returning a DSN and instructions for setup.
Inputs: projectSlug (required), platform.
Set user context for Sentry
Inputs: id, email, username, ip_address, +1 more.
Start a new session for release health monitoring
Inputs: distinctId, sessionId, release, environment.
Start a performance monitoring transaction
Inputs: name (required), op (required), description.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 27 tools
Most tools have distinct purposes targeting specific Sentry resources or actions, with clear separation between event capture, issue management, project operations, and monitoring. However, some overlap exists between 'sentry_setup_project' and 'sentry_create_project', and between 'sentry_capture_session' and 'sentry_start_session/end_session', which could cause minor confusion.
All tools follow a consistent 'sentry_verb_noun' pattern with snake_case throughout, making them predictable and easy to parse. The naming convention is uniform across all 27 tools, with no deviations in style or structure.
With 27 tools, the count is borderline high for a Sentry integration, feeling somewhat heavy compared to typical well-scoped servers (3-15 tools). While Sentry is a complex platform, this many tools may overwhelm agents and suggest potential fragmentation or redundancy in the surface.
The tool set provides comprehensive coverage of Sentry's core functionalities, including error/exception capture, issue management, project/release operations, performance monitoring, session tracking, and alerting. There are no obvious gaps, and the surface supports full CRUD/lifecycle workflows for the domain.
MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
