Redmine MCP Server for Cline
Servidor MCP de Redmine para Cline
Este es un servidor MCP (Protocolo de contexto de modelo) personalizado que se integra con Redmine, lo que le permite interactuar con sus proyectos y problemas de Redmine a través de la extensión Cline VS Code.
Prerrequisitos
Node.js: necesita tener Node.js (versión 18 o más reciente) instalado en su sistema.
Instancia de Redmine: necesita una instancia de Redmine en ejecución con la API REST habilitada.
Clave API de Redmine: Necesita una clave API para su cuenta de usuario de Redmine. Puede encontrarla en la configuración de su cuenta de Redmine (normalmente en "Mi cuenta" -> "Clave de acceso API").
Cline: necesita la extensión Cline VS Code instalada y configurada.
Related MCP server: Redmine MCP Server
Instalación
Clonar el repositorio:
git clone https://github.com/ilask/Redmine-MCP.git cd Redmine-MCPInstalar dependencias:
npm install
Configuración
Establecer variables de entorno: cree un archivo
.enven la raíz del directorio del proyecto y agregue lo siguiente, reemplazando los marcadores de posición con su nombre de host de Redmine y su clave API reales:REDMINE_HOST=your-redmine-host.com REDMINE_API_KEY=your-redmine-api-keyImportante: ¡No envíe su archivo
.enval control de versiones! Contiene información confidencial. El archivo.gitignoreincluido en este repositorio debería impedir que se envíe.
Añadiendo a Cline
Abrir la configuración de Cline: en VS Code, abra la extensión Cline y vaya a la pestaña Servidor MCP.
Editar la configuración de MCP: haga clic en "Editar la configuración de MCP" para abrir el archivo
cline_mcp_settings.json.Agregar el servidor: agregue la siguiente entrada al objeto
mcpServers, reemplazando la rutaargscon la ruta absoluta al archivoserver.jsen su sistema:{ "mcpServers": { "redmine-server": { "command": "node", "args": ["C:\\Users\\yourusername\\path\\to\\Redmine-MCP\\server.js"], "disabled": false, "autoApprove": [] } } }Importante: asegúrese de utilizar barras invertidas dobles (
\\) en la ruta en Windows.Guardar: Guarde el archivo
cline_mcp_settings.json. Cline debería detectar los cambios automáticamente e iniciar el servidor.
Recursos y herramientas disponibles
Recursos
redmine://projects/{project_id}: Este recurso representa un proyecto de Redmine. Reemplace{project_id}con el ID real de un proyecto en su instancia de Redmine. Puede usar la herramientaaccess_mcp_resourceen Cline para leer los detalles de un proyecto. Por ejemplo:<access_mcp_resource> <server_name>redmine-server</server_name> <uri>redmine://projects/123</uri> </access_mcp_resource>
(Reemplace 123 con un ID de proyecto válido). Esto devolverá los detalles del proyecto en formato JSON.
Herramientas
create_issue: Esta herramienta permite crear un nuevo problema en Redmine. Acepta los siguientes parámetros:project_id(cadena, obligatoria): el ID del proyecto donde debe crearse el problema.subject(cadena, obligatorio): el asunto del problema.description(cadena, obligatoria): la descripción del problema.
Puedes usar la herramienta
use_mcp_toolen Cline para llamar a esta herramienta. Por ejemplo:<use_mcp_tool> <server_name>redmine-server</server_name> <tool_name>create_issue</tool_name> <arguments> { "project_id": "456", "subject": "My New Issue", "description": "This is a test issue created via Cline." } </arguments> </use_mcp_tool>(Reemplace
456con un ID de proyecto válido). Esto creará un nuevo problema en el proyecto especificado y devolverá los detalles del problema en formato JSON.
Solución de problemas
Error de conexión cerrada: Si ve un error como "Error MCP -1: Conexión cerrada", asegúrese de que las variables de entorno
REDMINE_HOSTyREDMINE_API_KEYestén configuradas correctamente. Además, asegúrese de que su instancia de Redmine sea accesible desde su equipo.Revisar los registros del servidor: Si encuentra problemas, revise la salida del servidor en la terminal de VS Code para ver si hay mensajes de error. El servidor registra los errores en la consola.
Available Tools
1 toolcreate_issueC
Create a new Redmine issue
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project ID | |
| subject | Yes | Issue subject | |
| description | Yes | Issue description |
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 states this is a creation operation but doesn't mention permissions required, whether it's idempotent, error handling, or what happens on success (e.g., returns an issue ID). For a mutation tool with zero annotation coverage, this leaves critical behavioral aspects unspecified.
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 with no wasted words. It's appropriately sized for a simple creation tool and front-loads the essential information, making it easy to parse quickly.
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 this is a mutation tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns, error conditions, or behavioral nuances. The agent lacks critical information needed to use this tool effectively in real scenarios.
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 input schema already documents all three parameters (project_id, subject, description) with basic descriptions. The tool description adds no additional parameter context beyond what's in the schema, resulting in the baseline score 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 clearly states the action ('Create a new') and resource ('Redmine issue'), making the purpose immediately understandable. However, it doesn't differentiate from siblings (though none exist) or specify what constitutes a 'Redmine issue' beyond the basic concept, which prevents a perfect score.
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 alternatives, prerequisites, or contextual constraints. The description merely restates the tool's function without offering any usage context, which is a significant gap for effective agent decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to compare it to. The tool's purpose is clearly defined and distinct by default.
The single tool follows a clear verb_noun pattern (create_issue), which is consistent with itself. There are no other tools to create inconsistency, so the naming is perfectly predictable.
A single tool is too few for a server named 'Redmine MCP Server for Cline', which implies broader functionality for interacting with Redmine (e.g., an issue tracking system). This minimal set severely limits the server's utility and scope.
The tool surface is severely incomplete for Redmine interaction, as it only allows creating issues without any ability to read, update, delete, or search issues, or handle other Redmine entities like projects or users. This creates significant gaps for agent workflows.
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
Share one project context across ChatGPT, Claude, Telegram and any MCP client.
Model Context Protocol server for todo.vu task management and time tracking.
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
An MCP server that provides access to Testiny projects, test cases and test runs
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceA Model Context Protocol server for interacting with Redmine using its REST API, enabling the management of tickets, projects, and user data through integration with LLMs.78MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables Claude Code to directly interact with Redmine project management systems, supporting issue management, project operations, and search features.229MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI coding agents to interact with Redmine projects, issues, time tracking, and members through natural language via the Model Context Protocol.
- AlicenseAqualityDmaintenanceEnables Cursor IDE to directly interact with OpenProject through the Model Context Protocol, supporting CRUD operations on projects and work packages.915MIT
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/papunoko/Redmine-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server