Este servidor MCP integra el seguimiento de errores de Honeybadger con Cursor IDE, lo que le permite obtener y analizar errores directamente desde su entorno de desarrollo.
Node.js 18+ instalado
Cuenta Honeybadger con acceso a la API
IDE de cursor con soporte MCP
Related MCP server: Jira Context MCP Server
git clone git@github.com:vishalzambre/honeybadger-mcp.git
cd honeybadger-mcp
npm installnpm run buildInstalación global:
npm install -g honeybadger-mcpLuego configúrelo en Cursor:
{
"mcpServers": {
"honeybadger": {
"command": "honeybadger-mcp",
"env": {
"HONEYBADGER_API_KEY": "your_api_key_here",
"HONEYBADGER_PROJECT_ID": "your_project_id"
}
}
}
}Instalación basada en proyectos (alternativa):
Si prefiere administrar el servidor MCP como una dependencia del proyecto:
npm install honeybadger-mcpEn este caso, el comando en su Cursor mcp_servers.json apuntaría a la instalación local dentro de node_modules de su proyecto:
{
"mcpServers": {
"honeybadger": {
"command": "node",
"args": ["./node_modules/honeybadger-mcp/dist/index.js"],
"env": {
"HONEYBADGER_API_KEY": "your_api_key_here",
"HONEYBADGER_PROJECT_ID": "your_project_id"
}
}
}
}Crea un archivo .env en la raíz de tu proyecto:
# Required: Your Honeybadger API key
HONEYBADGER_API_KEY=your_api_key_here
# Optional: Default project ID (can be overridden per request)
HONEYBADGER_PROJECT_ID=your_project_id
# Optional: Custom Honeybadger URL (defaults to https://app.honeybadger.io)
HONEYBADGER_BASE_URL=https://app.honeybadger.ioClave API :
Crear un nuevo token de autenticación personal
Copia el token para tu archivo .env
ID del proyecto :
Vaya a su proyecto en Honeybadger
El ID del proyecto está en la URL: https://app.honeybadger.io/projects/{PROJECT_ID}
O encuéntrelo en la configuración del proyecto
Añade el servidor MCP a la configuración de Cursor. Edita tu ~/.cursor/mcp_servers.json (o equivalente):
{
"mcpServers": {
"honeybadger": {
"command": "node",
"args": ["/path/to/honeybadger-mcp/dist/index.js"],
"env": {
"HONEYBADGER_API_KEY": "your_api_key_here",
"HONEYBADGER_PROJECT_ID": "your_project_id"
}
}
}
}Esta sección se actualizará o eliminará, ya que ya se ha explicado anteriormente. Si prefiere el método anterior de clonar e instalar globalmente desde una ruta local, aún puede hacerlo, pero se recomienda usar el paquete npm publicado para facilitar las actualizaciones y la administración.
Si se instala desde un clon local:
# Navigate to your cloned honeybadger-mcp directory
npm install -g . # Installs from the current directory
# Then configure in Cursor as before
# ... (Cursor configuration for local global install)Una vez configurado, puedes utilizar estas herramientas en Cursor:
List recent unresolved errors from Honeybadger in production environmentGet details for Honeybadger fault ID 12345Analyze Honeybadger issue 12345 and provide fix suggestionsGet the latest 5 occurrences for Honeybadger fault 12345list_honeybadger_faultsEnumera fallas recientes con filtrado opcional por entorno y estado resuelto.
Parámetros:
project_id (opcional): ID del proyecto
limit (opcional): Número de fallos (predeterminado: 20, máximo: 100)
environment (opcional): Filtrar por entorno
resolved (opcional): Filtrar por estado resuelto
get_honeybadger_faultObtiene información detallada sobre una falla específica.
Parámetros:
fault_id (obligatorio): El ID de falla
project_id (opcional): ID del proyecto
get_honeybadger_noticesObtiene avisos (ocurrencias de errores) para una falla específica.
Parámetros:
fault_id (obligatorio): El ID de la falla
project_id (opcional): ID del proyecto
limit (opcional): Número de avisos (predeterminado: 10, máximo: 100)
analyze_honeybadger_issueProporciona un análisis completo con sugerencias de soluciones.
Parámetros:
fault_id (obligatorio): El ID de la falla
project_id (opcional): ID del proyecto
include_context (opcional): incluye el contexto de la solicitud (valor predeterminado: verdadero)
Lista de errores recientes : "Muéstrame los últimos errores sin resolver de producción"
Analizar el error específico : "Analizar la falla 12345 de Honeybadger y sugerir soluciones".
Obtener contexto de error : "Obtener las últimas incidencias del error 12345 con contexto completo"
Revisar y corregir : utilice el análisis para comprender y solucionar el problema en su código.
Error de autenticación : Verifique que su clave API sea correcta y tenga los permisos adecuados
Proyecto no encontrado : Verifique que el ID de su proyecto sea correcto
Problemas de conexión : verificar el acceso de red a la API de Honeybadger
Ejecute el servidor directamente para ver los mensajes de error:
node dist/index.jsConsulte los registros del cursor para detectar problemas relacionados con MCP:
macOS: ~/Library/Logs/Cursor/
Windows: %APPDATA%\Cursor\logs\
Linux: ~/.config/Cursor/logs/
Almacene las claves API de forma segura y nunca las envíe al control de versiones
Utilice claves API específicas del entorno cuando sea posible
Considere usar tokens API de solo lectura para esta integración
Rote regularmente sus claves API
Para ampliar este servidor MCP:
Agregar nuevas herramientas en el método setupToolHandlers()
Implementar métodos de controlador correspondientes
Actualizar la lista de herramientas y la documentación
Pruebe exhaustivamente su configuración de Honeybadger
Para problemas con:
Este servidor MCP : Verifique el código y la configuración
API de Honeybadger : consulte la documentación de la API de Honeybadger
Integración de Cursor MCP : consulte la documentación de Cursor
Comprehensive analysis of a Honeybadger issue with fix suggestions
| Name | Required | Description | Default |
|---|---|---|---|
| fault_id | Yes | The ID of the fault to analyze | |
| project_id | No | Optional project ID (uses env var if not provided) | |
| include_context | No | Include request context and parameters in analysis |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'analysis' and 'fix suggestions' imply a read-only operation, it doesn't specify whether this requires authentication, has rate limits, or what the output format looks like. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that clearly states the tool's purpose without any wasted words. It's appropriately sized and front-loaded with the core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (analysis with suggestions), no annotations, and no output schema, the description is minimally adequate. It states what the tool does but lacks details on output format, error handling, or integration with siblings. It meets basic requirements but has clear gaps for effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema (e.g., it doesn't explain what 'comprehensive analysis' entails or how parameters affect it). Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs 'comprehensive analysis' of a Honeybadger issue and provides 'fix suggestions', which is a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'get_honeybadger_fault' or 'get_honeybadger_notices', which might provide similar data without analysis or suggestions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There's no mention of when to choose this analysis tool over the sibling 'get' tools, nor any prerequisites or exclusions. The agent must infer usage from the description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a specific fault/error from Honeybadger by ID
| Name | Required | Description | Default |
|---|---|---|---|
| fault_id | Yes | The ID of the fault to fetch | |
| project_id | No | Optional project ID (uses env var if not provided) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Fetch') but does not describe what 'fetch' entails—e.g., whether it's a read-only operation, requires authentication, has rate limits, or what the return format looks like. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('Fetch a specific fault/error from Honeybadger by ID'). There is no wasted language or redundancy, making it highly concise and well-structured for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not cover behavioral aspects like safety, authentication, or response format, which are crucial for a tool that fetches data. While the purpose is clear, the overall context for effective use by an AI agent is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters ('fault_id' and 'project_id') fully described in the schema. The description adds no additional meaning beyond what the schema provides, such as explaining parameter interactions or usage nuances. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Fetch') and resource ('a specific fault/error from Honeybadger by ID'), distinguishing it from sibling tools like 'list_honeybadger_faults' (which presumably lists multiple faults) and 'get_honeybadger_notices' (which fetches notices rather than faults). It precisely communicates the tool's function without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by specifying 'by ID,' suggesting it's for retrieving a single, known fault. However, it does not explicitly state when to use this tool versus alternatives like 'list_honeybadger_faults' or 'analyze_honeybadger_issue,' nor does it mention prerequisites or exclusions. The guidance is implied but lacks explicit comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch notices (occurrences) for a specific fault
| Name | Required | Description | Default |
|---|---|---|---|
| fault_id | Yes | The ID of the fault to fetch notices for | |
| project_id | No | Optional project ID (uses env var if not provided) | |
| limit | No | Number of notices to fetch (default: 10, max: 100) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Fetch') but does not cover critical aspects like whether this is a read-only operation, potential rate limits, authentication needs, error handling, or what the return format looks like (e.g., pagination, structure). This leaves significant gaps for a tool with no annotation support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence that efficiently conveys the core purpose without any redundant or unnecessary information. It is front-loaded and appropriately sized for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and no output schema, the description is incomplete. It does not address behavioral traits (e.g., safety, performance) or explain what the tool returns, which is critical for a tool with three parameters and no structured output documentation. The high schema coverage is insufficient to compensate for these gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting all three parameters (fault_id, project_id, limit) with their purposes, optionality, and defaults. The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline for high schema coverage without compensating value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Fetch') and resource ('notices (occurrences) for a specific fault'), distinguishing it from sibling tools like 'get_honeybadger_fault' (which fetches fault details) and 'list_honeybadger_faults' (which lists faults). It precisely defines the scope of the operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention sibling tools like 'analyze_honeybadger_issue' or explain scenarios where fetching notices is appropriate versus other operations, leaving the agent without contextual usage cues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent faults from Honeybadger
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | No | Optional project ID (uses env var if not provided) | |
| limit | No | Number of faults to fetch (default: 20, max: 100) | |
| environment | No | Filter by environment (e.g., production, staging) | |
| resolved | No | Filter by resolved status |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'List recent faults' but doesn't explain what 'recent' means (e.g., time range), how results are ordered, pagination behavior, or error handling. This leaves significant gaps for a tool with 4 parameters and no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with zero waste. It's front-loaded with the core action and resource, making it highly efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, no annotations, no output schema), the description is inadequate. It doesn't explain return values, error conditions, or behavioral traits like rate limits or authentication needs. For a list operation with filtering options, more context is needed to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 4 parameters. The description adds no additional parameter information beyond implying a list operation. This meets the baseline of 3, as the schema handles the heavy lifting, but the description doesn't enhance understanding of parameter interactions or defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('List') and resource ('recent faults from Honeybadger'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_honeybadger_fault' or 'get_honeybadger_notices', which likely retrieve specific items rather than lists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'analyze_honeybadger_issue' or 'get_honeybadger_fault', nor does it specify use cases or prerequisites beyond the basic action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_honeybadger_issueget_honeybadger_faultget_honeybadger_noticeslist_honeybadger_faultsScored across 4 tools
Each tool has a clearly distinct purpose with no overlap: analyze_honeybadger_issue provides analysis and fix suggestions, get_honeybadger_fault retrieves a specific fault by ID, get_honeybadger_notices fetches occurrences for a fault, and list_honeybadger_faults lists recent faults. The descriptions make it easy to distinguish between analyzing, fetching specific items, fetching related data, and listing collections.
All tool names follow a consistent verb_noun pattern with snake_case: analyze_honeybadger_issue, get_honeybadger_fault, get_honeybadger_notices, and list_honeybadger_faults. The naming is predictable and readable, using clear verbs like 'analyze', 'get', and 'list' paired with specific nouns.
With 4 tools, the count is reasonable for a Honeybadger server, covering core operations like listing, fetching, and analyzing faults. It's slightly on the minimal side but well-scoped for basic error monitoring tasks, though additional tools for actions like creating or updating issues might be expected in a more comprehensive set.
The tool set covers key read operations for Honeybadger: listing faults, fetching specific faults and their notices, and analyzing issues. However, it lacks write operations (e.g., creating, updating, or resolving faults) and broader management features, which are minor gaps that agents might need to work around for full lifecycle coverage.
Error tracking for Laravel and PHP apps. Let your agent fetch errors, stack traces and context.
The bug mediator for AI-built apps: plain-English diagnosis + a ready fix, in your editor.
Product Hunt for AI tools. Search, submit, upvote from Claude Code or Cursor.
Investigate errors, track deployments, analyze performance, and manage application monitoring
