Jira Insights MCP
Jira Insights MCP
Un servidor de Protocolo de contexto de modelo (MCP) para administrar esquemas de activos de Jira Insights (JSM).
Última actualización: 09/04/2025
Descripción general
Este servidor MCP proporciona herramientas para interactuar con los esquemas de activos de Jira Insights (JSM) mediante el Protocolo de Contexto de Modelo. Permite gestionar esquemas de objetos, tipos de objetos y objetos en Jira Insights.
Related MCP server: MCP Atlassian
Características
Administrar esquemas de objetos (crear, leer, actualizar, eliminar)
Administrar tipos de objetos (crear, leer, actualizar, eliminar)
Administrar objetos (crear, leer, actualizar, eliminar)
Consultar objetos utilizando AQL (lenguaje de consulta Atlassian)
Prerrequisitos
Node.js 20 o posterior
Docker (para implementación en contenedores)
Instancia de Jira Insights con acceso a la API
Token de API de Jira con los permisos adecuados
Instalación
Desarrollo local
Clonar el repositorio:
git clone https://github.com/aaronsb/jira-insights-mcp.git cd jira-insights-mcpInstalar dependencias:
npm installConstruir el proyecto:
npm run build
Estibador
Construya la imagen de Docker:
./scripts/build-local.shUso
Configuración de MCP
Para utilizar este servidor MCP con Claude u otros asistentes de IA que admitan el Protocolo de contexto de modelo, agréguelo a su configuración de MCP mediante uno de los siguientes métodos:
Configuración de compilación local
Si ha creado el proyecto localmente, utilice esta configuración:
{
"mcpServers": {
"jira-insights": {
"command": "node",
"args": ["/path/to/jira-insights-mcp/build/index.js"],
"env": {
"JIRA_API_TOKEN": "your-api-token",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_HOST": "https://your-domain.atlassian.net",
"LOG_MODE": "strict"
}
}
}
}Configuración basada en Docker
Si prefiere utilizar la imagen de Docker (recomendada para la mayoría de los usuarios), utilice esta configuración:
{
"mcpServers": {
"jira-insights": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "JIRA_API_TOKEN",
"-e", "JIRA_EMAIL",
"-e", "JIRA_HOST",
"ghcr.io/aaronsb/jira-insights-mcp:latest"
],
"env": {
"JIRA_API_TOKEN": "your-api-token",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_HOST": "https://your-domain.atlassian.net"
}
}
}
}Esta configuración basada en Docker extrae la última imagen de GitHub Container Registry y la ejecuta con las variables de entorno necesarias.
Corriendo localmente por el desarrollo
Para desarrollo y pruebas locales:
# Build the Docker image
./scripts/build-local.sh
# Run the Docker container
JIRA_API_TOKEN=your_token JIRA_EMAIL=your_email JIRA_HOST=your_host ./scripts/run-local.shHerramientas disponibles
administrar_esquema_jira_insight
Administre esquemas de objetos de Jira Insights con operaciones CRUD.
{
"operation": "list",
"maxResults": 10
}administrar_tipo_de_objeto_de_jira_insight
Administre los tipos de objetos de Jira Insights con operaciones CRUD.
{
"operation": "list",
"schemaId": "1",
"maxResults": 20
}objeto de gestión de Jira Insight
Administre objetos de Jira Insights con operaciones CRUD y consultas AQL.
{
"operation": "query",
"aql": "objectType = \"Application\"",
"maxResults": 10
}Recursos disponibles
El servidor MCP proporciona varios recursos para acceder a los datos de Jira Insights:
jira-insights://instance/summary: estadísticas de alto nivel sobre la instancia de Jira Insightsjira-insights://aql-syntax: guía completa sobre la sintaxis del lenguaje de consulta de activos (AQL) con ejemplosjira-insights://schemas/all: lista completa de todos los esquemas con sus tipos de objetosjira-insights://schemas/{schemaId}/full: definición completa de un esquema específico, incluidos los tipos de objetosjira-insights://schemas/{schemaId}/overview: descripción general de un esquema específico que incluye metadatos y estadísticasjira-insights://object-types/{objectTypeId}/overview: descripción general de un tipo de objeto específico, incluidos atributos y estadísticas
Mejoras planificadas
Estamos trabajando en varias mejoras para mejorar la funcionalidad y la usabilidad de Jira Insights MCP:
Mejoras de alta prioridad
Manejo mejorado de errores
Mensajes de error más detallados con problemas de validación específicos
Soluciones sugeridas para errores comunes
Ejemplos específicos de la operación para ayudar a los usuarios a corregir problemas
Mejoras en las consultas AQL
Utilidades de validación y formato para consultas AQL
Consultas de ejemplo específicas del esquema
Mejores mensajes de error para problemas de consulta
Mejora del descubrimiento de atributos
Recuperación de atributos mejorada para tipos de objetos
Almacenamiento en caché para un mejor rendimiento
Mejor manejo del parámetro "expandir"
Mejoras de prioridad media
Generación de plantillas de objetos
Plantillas para crear objetos basados en tipos de objetos
Generación de marcadores de posición específicos de cada tipo
Reglas de validación en plantillas
Biblioteca de consultas de ejemplo
Consultas de ejemplo específicas del esquema
Sugerencias de consultas sensibles al contexto
Plantillas de consulta para operaciones comunes
Documentación mejorada
Documentación de sintaxis AQL mejorada
Documentación específica de la operación
Escenarios de error comunes y soluciones
Para obtener más detalles sobre las mejoras planificadas, consulte:
TODO.md- Lista completa de tareas por hacer con todas las tareas organizadas por prioridadIMPLEMENTATION_PLAN.md- Planes de implementación detallados para las mejoras de alta prioridadHANDLER_IMPROVEMENTS.md- Cambios específicos necesarios para cada archivo de controladorIMPROVEMENT_SUMMARY.md- Resumen conciso de las mejoras planificadasdocs/API_MIGRATION_TODO.md- Estado de la migración de la API y mejoras planificadas
Desarrollo
Guiones
npm run build: compila el código TypeScriptnpm run lint: Ejecutar ESLintnpm run lint:fix: Ejecuta ESLint con corrección automáticanpm run test: Ejecutar pruebasnpm run watch: vigila los cambios y reconstruyenpm run generate-diagrams: Genera diagramas de dependencia de TypeScript
Scripts de Docker
./scripts/build-local.sh: Construye la imagen de Docker./scripts/run-local.sh: Ejecuta el contenedor Docker
Solución de problemas
Problemas comunes
Errores de validación de consultas AQL
Asegúrese de que los valores con espacios estén entre comillas:
Name = "John Doe"Utilice mayúsculas para los operadores lógicos:
AND,OR(noand,or)Compruebe que los tipos de objetos y atributos existan en su esquema
Problemas con los atributos de tipo de objeto
Al utilizar el parámetro "expandir" con "atributos", asegúrese de que el tipo de objeto exista
Comprueba que tienes permisos para ver los atributos
Problemas de conexión de la API
Verifique que su token de API de Jira tenga los permisos necesarios
Compruebe que la URL del host de Jira sea correcta
Asegúrese de que su red permita conexiones a la API de Jira
Licencia
Instituto Tecnológico de Massachusetts (MIT)
Available Tools
3 toolsmanage_jira_insight_objectC
Manage Jira Insights objects with CRUD operations and AQL queries
| Name | Required | Description | Default |
|---|---|---|---|
| aql | No | AQL query string. Required for query operation. IMPORTANT: For comprehensive AQL documentation, refer to the "jira-insights://aql-syntax" resource using the access_mcp_resource tool. This resource contains detailed syntax guides, examples, and best practices. Guide to Constructing Better Jira Insight AQL Queries: Understanding AQL Fundamentals: - Object Type Case Sensitivity: Use exact case matching for object type names (e.g., ObjectType = "Supported laptops" not objectType = "Supported laptops"). - String Values in Quotes: Always enclose string values in double quotes, especially values containing spaces (e.g., Name = "MacBook Pro" not Name = MacBook Pro). - Attribute References: Reference attributes directly by their name, not by a derived field name (e.g., use Name not name). - LIKE Operator Usage: Use the LIKE operator for partial string matching, but be aware it may be case-sensitive. Effective Query Construction: - Start Simple: Begin with the most basic query to validate object existence before adding complex filters: ObjectType = "Supported laptops" - Examine Response Objects: Study the first responses to understand available attribute names and formats before using them in filters. - Keyword Strategy: When searching for specific items, try multiple potential keywords (e.g., "ThinkPad", "Lenovo", "Carbon") rather than just exclusion logic. - Incremental Complexity: Add filter conditions incrementally, testing after each addition rather than constructing complex queries in one step. Managing Complex Queries: - AND/OR Operators: Structure complex conditions carefully with proper parentheses: ObjectType = "Supported laptops" AND (Name LIKE "ThinkPad" OR Name LIKE "Lenovo") - NOT Operators: Use NOT sparingly and with proper syntax: ObjectType = "Supported laptops" AND NOT Name LIKE "MacBook" - Reference Object Queries: For filtering on related objects, use their object key as a reference: ObjectType = "Supported laptops" AND Manufacturer = "PPL-231" - Pagination Awareness: For large result sets, utilize the startAt and maxResults parameters to get complete data. | |
| attributes | No | Attributes of the object as key-value pairs. Optional for create/update. | |
| expand | No | Optional fields to include in the response | |
| includeAttributes | No | Should the objects attributes be included in the response. If this parameter is false only the information on the object will be returned and the object attributes will not be present. | |
| includeAttributesDeep | No | How many levels of attributes should be included. E.g. consider an object A that has a reference to object B that has a reference to object C. If object A is included in the response and includeAttributesDeep=1 object A's reference to object B will be included in the attributes of object A but object B's reference to object C will not be included. However if the includeAttributesDeep=2 then object B's reference to object C will be included in object B's attributes. | |
| includeExtendedInfo | No | Include information about open Jira issues. Should each object have information if open tickets are connected to the object? | |
| includeTypeAttributes | No | Should the response include the object type attribute definition for each attribute that is returned with the objects. | |
| maxResults | No | Maximum number of objects to return. Used for list and query operations. Can also use snake_case "max_results". | |
| name | No | Name of the object. Required for create operation, optional for update. | |
| objectId | No | The ID of the object. Required for get, update, and delete operations. Can also use snake_case "object_id". | |
| objectTypeId | No | The ID of the object type. Required for create operation. Can also use snake_case "object_type_id". | |
| operation | Yes | Operation to perform on the object | |
| resolveAttributeNames | No | Replace attribute IDs (attr_xxx) with actual attribute names in the response. This provides more meaningful attribute names for better readability. | |
| schemaId | No | The ID of the schema to use for enhanced validation. When provided, the query will be validated against the schema structure, providing better error messages and suggestions. | |
| simplifiedResponse | No | Return a simplified response with only essential key-value pairs, excluding detailed metadata, references, and type definitions. Useful for reducing response size and improving readability. | |
| startAt | No | Index of the first object to return (0-based). Used for list and query operations. Can also use snake_case "start_at". |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'CRUD operations and AQL queries' but lacks details on permissions, side effects, rate limits, or response formats. For a tool with 16 parameters and complex operations like delete/update, this is insufficient—it doesn't explain what 'manage' entails beyond high-level operations.
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 overly concise to the point of under-specification—it's a single sentence that fails to convey necessary details for such a complex tool. It lacks front-loaded critical information and doesn't structure guidance effectively, making it inefficient despite its brevity.
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 (16 parameters, no annotations, no output schema), the description is incomplete. It doesn't address behavioral aspects, usage context, or output expectations, leaving significant gaps. For a multi-operation tool managing objects, more comprehensive guidance is needed to support 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?
The description adds minimal parameter semantics beyond the input schema, which has 100% coverage. It implies parameters relate to CRUD and AQL operations but doesn't elaborate on specific usage or interactions. Since schema coverage is high, the baseline is 3, but the description doesn't compensate with additional insights like parameter dependencies or examples.
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's purpose: 'Manage Jira Insights objects with CRUD operations and AQL queries.' It specifies the resource (Jira Insights objects) and the operations (CRUD + AQL queries). However, it doesn't explicitly differentiate from sibling tools like 'manage_jira_insight_object_type' or 'manage_jira_insight_schema,' which likely manage different resources.
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 its siblings or alternatives. It mentions CRUD operations and AQL queries but doesn't specify scenarios, prerequisites, or exclusions. For example, it doesn't clarify if this is for basic object management while siblings handle types/schemas, leaving usage context implied at best.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
manage_jira_insight_object_typeC
Manage Jira Insights object types with CRUD operations
| Name | Required | Description | Default |
|---|---|---|---|
| description | No | Description of the object type. Optional for create/update. | |
| expand | No | Optional fields to include in the response | |
| icon | No | Icon for the object type. Optional for create/update. | |
| maxResults | No | Maximum number of object types to return. Used for list operation. Can also use snake_case "max_results". | |
| name | No | Name of the object type. Required for create operation, optional for update. | |
| objectTypeId | No | The ID of the object type. Required for get, update, and delete operations. Can also use snake_case "object_type_id". | |
| operation | Yes | Operation to perform on the object type | |
| schemaId | No | The ID of the schema. Required for create operation. Can also use snake_case "schema_id". | |
| startAt | No | Index of the first object type to return (0-based). Used for list operation. Can also use snake_case "start_at". |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states 'CRUD operations' without detailing permissions, side effects, rate limits, or response behavior. It lacks critical information for a mutation-capable tool.
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 without unnecessary words. It's 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?
For a tool with 9 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain return values, error handling, or behavioral nuances needed for safe and effective 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 parameters are well-documented in the schema. The description adds no additional parameter semantics beyond the generic 'CRUD operations', which aligns with the baseline for high schema coverage.
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 states the tool performs CRUD operations on Jira Insights object types, which is a clear purpose. However, it doesn't differentiate from sibling tools like 'manage_jira_insight_object' or 'manage_jira_insight_schema', leaving ambiguity about scope boundaries.
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?
No guidance is provided on when to use this tool versus its siblings or alternatives. The description mentions CRUD operations but doesn't specify contexts, prerequisites, or exclusions for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
manage_jira_insight_schemaC
Manage Jira Insights object schemas with CRUD operations
| Name | Required | Description | Default |
|---|---|---|---|
| description | No | Description of the schema. Optional for create/update. | |
| expand | No | Optional fields to include in the response | |
| maxResults | No | Maximum number of schemas to return. Used for list operation. Can also use snake_case "max_results". | |
| name | No | Name of the schema. Required for create operation, optional for update. | |
| operation | Yes | Operation to perform on the schema | |
| schemaId | No | The ID of the schema. Required for get, update, and delete operations. Can also use snake_case "schema_id". | |
| startAt | No | Index of the first schema to return (0-based). Used for list operation. Can also use snake_case "start_at". |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure but only states 'manage with CRUD operations.' It doesn't describe authentication requirements, rate limits, error conditions, what 'delete' actually destroys, or response formats. For a multi-operation tool with mutation capabilities, 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 directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded with the core purpose, though it could benefit from more detail given 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?
For a complex tool with 7 parameters supporting 5 different operations (including destructive ones like delete) and no output schema or annotations, the description is inadequate. It doesn't explain return values, error handling, or operational constraints, leaving the agent with insufficient context to use the tool 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 already documents all 7 parameters thoroughly. The description adds no parameter-specific information beyond the generic 'CRUD operations' mention, which doesn't provide additional semantic context about individual parameters or their relationships.
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 states the tool manages Jira Insights object schemas with CRUD operations, which provides a general purpose but lacks specificity about what 'manage' entails. It doesn't distinguish this schema management tool from its sibling object and object type management tools, leaving the scope vague.
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?
No guidance is provided about when to use this tool versus its siblings (manage_jira_insight_object and manage_jira_insight_object_type). The description mentions CRUD operations but doesn't specify contexts, prerequisites, or exclusions for choosing this schema management tool over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
3 tool updates
v1.0.0- First observed
manage_jira_insight_object - First observed
manage_jira_insight_object_type - First observed
manage_jira_insight_schema
TDQS
Each tool has a clearly distinct purpose targeting different Jira Insights components: objects, object types, and schemas. The descriptions specify unique domains (objects, object types, schemas) with no overlap in functionality, making it easy for an agent to select the correct tool.
All tool names follow a consistent verb_noun pattern with 'manage_jira_insight_' prefix followed by the specific component (object, object_type, schema). This predictable naming convention enhances readability and usability across the tool set.
With only 3 tools, the count feels thin for a server named 'Jira Insights MCP', which might imply broader functionality. However, it covers core management areas adequately, though it could benefit from additional tools for querying or reporting to be more comprehensive.
The tools provide CRUD operations for key Jira Insights components (objects, types, schemas), covering essential management tasks. A minor gap exists in lacking dedicated query or analysis tools beyond AQL mentioned in one description, but core workflows are well-supported.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for Product Management
An MCP server that provides access to Testiny projects, test cases and test runs
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceModel Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.5,853MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that enables AI agents to interact with Atlassian products (Confluence and Jira) for content management, issue tracking, and project management through a standardized interface.2,4056MIT
- -licenseNot gradedqualityCmaintenanceA local MCP server for administering Atlassian Cloud Assets and Jira, providing hundreds of tools for schemas, projects, workflows, and more.-
- AlicenseNot gradedqualityBmaintenanceModel Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Supports both Cloud and Server/Data Center deployments.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aaronsb/jira-insights-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server