Skip to main content
Glama
leandr92

mcp-openproject-standalone

by leandr92
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

Standalone MCP Server for OpenProject

🇷🇺 Русский | 🇬🇧 English

🇷🇺 Русский

Standalone MCP-сервер для интеграции OpenProject с Cursor IDE. Работает полностью локально, без необходимости развертывани дополнительного сервера для обработки.

Описание

Этот MCP-сервер позволяет Cursor IDE напрямую взаимодействовать с вашим экземпляром OpenProject через Model Context Protocol. Сервер работает полностью локально и не требует развертывания на облачных платформах.

Related MCP server: OpenProject MCP Server

Установка

Установка через npm (рекомендуется, после публикации)

После публикации пакета в npm, установите его глобально:

npm install -g mcp-openproject-standalone

Или локально в проект:

npm install mcp-openproject-standalone

Зависимости установятся автоматически вместе с пакетом.

Установка из исходников

Если вы клонировали репозиторий или хотите использовать локальную версию:

Автоматическая установка зависимостей

Зависимости устанавливаются автоматически при первом запуске MCP-сервера. Просто настройте конфигурацию MCP (см. ниже), и при первом подключении зависимости будут установлены автоматически.

Ручная установка зависимостей (опционально)

Если хотите установить зависимости вручную заранее:

npm install

Примечание: Если вы планируете использовать вариант с npm link (см. ниже), то нужно сделать скрипт исполняемым:

chmod +x index.js

Если вы используете вариант с node index.js в конфигурации MCP, то этот шаг не обязателен.

Обновление пакета

После первичной установки пакет можно обновить до последней версии.

Обновление при использовании npx

Если вы используете npx в конфигурации MCP, пакет автоматически обновляется до последней версии при каждом запуске. Дополнительных действий не требуется.

Обновление при глобальной установке

Если вы установили пакет глобально через npm install -g, обновите его командой:

npm update -g mcp-openproject-standalone

Или переустановите последнюю версию:

npm install -g mcp-openproject-standalone@latest

Обновление при локальной установке

Если пакет установлен локально в проект:

npm update mcp-openproject-standalone

Или переустановите последнюю версию:

npm install mcp-openproject-standalone@latest

Проверка текущей версии

Чтобы узнать текущую установленную версию:

npm list -g mcp-openproject-standalone

Или для локальной установки:

npm list mcp-openproject-standalone

Чтобы узнать последнюю доступную версию в npm:

npm view mcp-openproject-standalone version

После обновления

После обновления пакета перезапустите Cursor IDE, чтобы изменения вступили в силу.

Настройка в Cursor

Добавьте следующую конфигурацию в файл MCP Cursor (~/.cursor/mcp.json или ~/.config/cursor/mcp.json):

Автоматическая установка через npx (рекомендуется)

Используйте npx для автоматической установки и запуска пакета. Если пакет не установлен, npx автоматически скачает и запустит его:

{
  "mcpServers": {
    "openproject": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-openproject-standalone"
      ],
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Преимущества:

  • ✅ Автоматическая установка пакета при первом запуске

  • ✅ Не требует предварительной установки

  • ✅ Автоматическое обновление до последней версии

  • ✅ Кэширование пакета для последующих запусков

Примечание: Флаг -y автоматически подтверждает установку пакета без запроса.

Если установили через npm (глобально или локально)

Если вы уже установили пакет глобально:

npm install -g mcp-openproject-standalone

Тогда в конфигурации можно использовать:

{
  "mcpServers": {
    "openproject": {
      "command": "mcp-openproject-standalone",
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Примечание: При глобальной установке (npm install -g) команда mcp-openproject-standalone будет доступна из любого места. При локальной установке используйте полный путь к node_modules/.bin/mcp-openproject-standalone или используйте npx mcp-openproject-standalone.

Если используете локальную версию из исходников

Вариант 1: Через npm link

npm link

Тогда в конфигурации можно использовать:

{
  "mcpServers": {
    "openproject": {
      "command": "mcp-openproject-standalone",
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Вариант 2: Прямой путь к файлу

{
  "mcpServers": {
    "openproject": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-openproject-standalone/index.js"
      ],
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Доступные функции

  1. list_projects - Получить список всех проектов

  2. get_project - Получить детали проекта по ID

  3. list_work_packages - Получить список задач в проекте

  4. get_work_package - Получить детали задачи по ID

  5. create_work_package - Создать новую задачу

  6. update_work_package - Обновить существующую задачу

  7. list_statuses - Получить список всех доступных статусов в OpenProject

  8. get_available_statuses - Получить доступные статусы для конкретной задачи (workflow). Возвращает текущий статус и все статусы, которые можно установить для этой задачи

Переменные окружения

Переменные окружения можно задать двумя способами:

1. В конфигурации MCP (рекомендуется)

Добавьте секцию env в конфигурацию MCP в файле ~/.cursor/mcp.json или ~/.config/cursor/mcp.json:

{
  "mcpServers": {
    "openproject": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-openproject-standalone/index.js"],
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Этот способ удобен, так как все настройки хранятся в одном месте.

2. Через системные переменные окружения

Также можно задать переменные окружения в системе перед запуском:

export OPENPROJECT_BASE_URL="https://your-openproject-instance.com"
export OPENPROJECT_API_KEY="your-api-token-here"

Поддерживаемые переменные:

  • OPENPROJECT_BASE_URL или OPENPROJECT_URL - URL вашего OpenProject

  • OPENPROJECT_API_KEY или OPENPROJECT_API_TOKEN - API токен из OpenProject

Использование

После настройки вы сможете использовать в Cursor:

  • "Покажи мне все проекты из OpenProject"

  • "Покажи все задачи в проекте с ID 123"

  • "Создай задачу в проекте 1 с названием 'Новая задача'"

  • "Обнови задачу #123"

  • "Покажи все доступные статусы"

  • "Какие статусы можно установить для задачи #123?"

Преимущества

  • ✅ Полностью standalone - работает локально

  • ✅ Не требует развертывания на Netlify

  • ✅ Поддержка чтения и записи (CRUD операции)

  • ✅ Простая установка и настройка

  • ✅ Полный контроль над кодом

🇬🇧 English

Standalone MCP server for integrating OpenProject with Cursor IDE. Works completely locally, without the need to deploy on Netlify or other cloud platforms.

Description

This MCP server allows Cursor IDE to directly interact with your OpenProject instance through the Model Context Protocol. The server runs completely locally and does not require deployment on cloud platforms.

Installation

Install via npm (Recommended, after publication)

After the package is published to npm, install it globally:

npm install -g mcp-openproject-standalone

Or locally in a project:

npm install mcp-openproject-standalone

Dependencies will be installed automatically with the package.

Install from source

If you cloned the repository or want to use a local version:

Automatic dependency installation

Dependencies are installed automatically on the first run of the MCP server. Simply configure the MCP settings (see below), and dependencies will be installed automatically on first connection.

Manual dependency installation (Optional)

If you want to install dependencies manually in advance:

npm install

Note: If you plan to use the npm link option (see below), you need to make the script executable:

chmod +x index.js

If you use the node index.js option in the MCP configuration, this step is not required.

Updating the Package

After the initial installation, you can update the package to the latest version.

Updating when using npx

If you use npx in the MCP configuration, the package is automatically updated to the latest version on each run. No additional action is required.

Updating with global installation

If you installed the package globally via npm install -g, update it with:

npm update -g mcp-openproject-standalone

Or reinstall the latest version:

npm install -g mcp-openproject-standalone@latest

Updating with local installation

If the package is installed locally in a project:

npm update mcp-openproject-standalone

Or reinstall the latest version:

npm install mcp-openproject-standalone@latest

Checking current version

To see the currently installed version:

npm list -g mcp-openproject-standalone

Or for local installation:

npm list mcp-openproject-standalone

To see the latest available version on npm:

npm view mcp-openproject-standalone version

After updating

After updating the package, restart Cursor IDE for the changes to take effect.

Configuration in Cursor

Add the following configuration to the MCP Cursor file (~/.cursor/mcp.json or ~/.config/cursor/mcp.json):

Automatic installation via npx (Recommended)

Use npx for automatic installation and running of the package. If the package is not installed, npx will automatically download and run it:

{
  "mcpServers": {
    "openproject": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-openproject-standalone"
      ],
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Advantages:

  • ✅ Automatic package installation on first run

  • ✅ No pre-installation required

  • ✅ Automatic update to latest version

  • ✅ Package caching for subsequent runs

Note: The -y flag automatically confirms package installation without prompting.

If installed via npm (globally or locally)

If you have already installed the package globally:

npm install -g mcp-openproject-standalone

Then in the configuration you can use:

{
  "mcpServers": {
    "openproject": {
      "command": "mcp-openproject-standalone",
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Note: With global installation (npm install -g), the mcp-openproject-standalone command will be available from anywhere. With local installation, use the full path to node_modules/.bin/mcp-openproject-standalone or use npx mcp-openproject-standalone.

If using local version from source

Option 1: Via npm link

npm link

Then in the configuration you can use:

{
  "mcpServers": {
    "openproject": {
      "command": "mcp-openproject-standalone",
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Option 2: Direct path to file

{
  "mcpServers": {
    "openproject": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-openproject-standalone/index.js"
      ],
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

Available Functions

  1. list_projects - Get a list of all projects

  2. get_project - Get project details by ID

  3. list_work_packages - Get a list of work packages in a project

  4. get_work_package - Get work package details by ID

  5. create_work_package - Create a new work package

  6. update_work_package - Update an existing work package

  7. list_statuses - Get a list of all available statuses in OpenProject

  8. get_available_statuses - Get available statuses for a specific work package (workflow). Returns the current status and all statuses that can be set for this work package

Environment Variables

Environment variables can be set in two ways:

1. In MCP Configuration (Recommended)

Add the env section to the MCP configuration in the file ~/.cursor/mcp.json or ~/.config/cursor/mcp.json:

{
  "mcpServers": {
    "openproject": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-openproject-standalone/index.js"],
      "env": {
        "OPENPROJECT_BASE_URL": "https://your-openproject-instance.com",
        "OPENPROJECT_API_KEY": "your-api-token-here"
      }
    }
  }
}

This method is convenient as all settings are stored in one place.

2. Via System Environment Variables

You can also set environment variables in the system before running:

export OPENPROJECT_BASE_URL="https://your-openproject-instance.com"
export OPENPROJECT_API_KEY="your-api-token-here"

Supported variables:

  • OPENPROJECT_BASE_URL or OPENPROJECT_URL - URL of your OpenProject instance

  • OPENPROJECT_API_KEY or OPENPROJECT_API_TOKEN - API token from OpenProject

Usage

After configuration, you can use in Cursor:

  • "Show me all projects from OpenProject"

  • "Show all work packages in project with ID 123"

  • "Create a work package in project 1 with title 'New Task'"

  • "Update work package #123"

  • "Show all available statuses"

  • "What statuses can be set for work package #123?"

Advantages

  • ✅ Fully standalone - works locally

  • ✅ No deployment on Netlify required

  • ✅ Read and write support (CRUD operations)

  • ✅ Simple installation and configuration

  • ✅ Full control over the code

Available Tools

9 tools
add_commentB

Add a comment to a work package

ParametersJSON Schema
NameRequiredDescriptionDefault
commentYesThe comment text (markdown format)
work_package_idYesThe ID of the work package

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral disclosure. It implies a write operation ('Add') but does not mention prerequisites, side effects, or response behavior—important gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with zero unnecessary words. It is concise and directly states the action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description should compensate by explaining return values or side effects, but it only provides the most basic action. It also lacks context about prerequisites (e.g., work package must exist) and what happens after the comment is added.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides complete descriptions for both parameters (work_package_id and comment), so the description adds no additional parameter semantics. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Add' with the resource 'comment' and the target 'work package', making its function immediately clear. It distinguishes itself from sibling tools like create_work_package and update_work_package.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives, but the tool name and the sibling list make the intended use (adding a comment to a work package) reasonably obvious. No explicit exclusions or alternative references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

create_work_packageC

Create a new work package in a project

ParametersJSON Schema
NameRequiredDescriptionDefault
subjectYesThe subject/title of the work package
type_idNoThe type ID (default: 1)
status_idNoThe ID of the status
project_idYesThe ID of the project
assignee_idNoThe ID of the assignee user
descriptionNoThe description of the work package

TDQS

C2.4/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full behavioral burden but only states 'Create', which is inherent to the tool name. It does not disclose side effects, required permissions, return behavior, or any other operational characteristics beyond the obvious mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence and concise, but it is under-specification rather than efficient communication. It merely restates the tool's purpose with no additional value, so it does not 'earn its place' beyond the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters and no output schema, but the description provides no behavioral or operational context. For a mutation tool with zero annotations, it is severely incomplete — it lacks information about what happens after creation, required permissions, or any side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema; it does not elaborate on any parameters, but the schema already provides complete field descriptions, so no deduction is warranted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource ('Create a new work package in a project') which clearly distinguishes it from siblings like list_work_packages, get_work_package, and update_work_package. It unambiguously states the tool's creation purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

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 such as update_work_package or get_work_package. The description gives no contextual cues about prerequisites, typical use cases, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_available_statusesA

Get available status transitions for a specific work package (workflow). Returns current status and all statuses that can be set for this work package.

ParametersJSON Schema
NameRequiredDescriptionDefault
work_package_idYesThe ID of the work package

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the burden. It discloses that it returns current status and all settable statuses, indicating a read-only operation, but it does not mention error handling, authorization needs, or any edge cases. It adds some context ('workflow') but lacks deeper behavioral details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the main purpose, and every clause adds value. It is concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description adequately covers what the tool does and what it returns. It does not explain return format, but that is acceptable for a simple getter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (work_package_id is clearly described as 'The ID of the work package'). The description adds minimal parameter-specific meaning beyond mentioning 'specific work package', so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Get') and resource ('available status transitions for a specific work package'), and differentiates from siblings by focusing on a specific work package and workflow context. It also explains the return value in a distinct way.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys clear usage context: when you need status transitions for a specific work package. It does not explicitly mention alternatives or exclusions, but the context is sufficient to distinguish it from list_statuses and other sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_projectA

Get details of a specific project by ID

ParametersJSON Schema
NameRequiredDescriptionDefault
project_idYesThe ID of the project

TDQS

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only states the obvious (retrieves a project) and does not disclose return format, possible errors (e.g., 404), or any side effects. For a read operation, it adds minimal behavioral context beyond the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no waste. It is front-loaded with the action and resource, and every word contributes to meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description provides a minimal but adequate explanation. However, it leaves gaps: it does not specify what 'details' includes or what happens if the project is not found. For a getter, this is passable but not thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already fully describes the only parameter (project_id as 'The ID of the project'), with 100% schema coverage. The description adds no extra meaning beyond what the schema provides, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Get') and resource ('project'), and clearly scopes it to 'a specific project by ID'. This distinguishes it from sibling tools like list_projects, which would retrieve multiple projects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'by ID' clearly indicates when to use this tool (when you have a specific project ID), but it does not explicitly mention alternatives or when not to use it, such as pointing to list_projects for all projects.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_work_packageA

Get details of a specific work package by ID

ParametersJSON Schema
NameRequiredDescriptionDefault
work_package_idYesThe ID of the work package

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. The verb 'Get' implies a read-only operation, which is useful, but the description does not elaborate on return format, error behavior, or whether the details include nested related resources. It is not contradictory, but adds minimal context beyond the verb itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence of nine words that front-loads the action and resource. Every word is meaningful, with no redundant phrasing or unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get-by-ID operation with one parameter and straightforward schema, the description is adequate. However, since there are no annotations and no output schema, a bit more context about return shape or behavior on missing IDs would improve completeness. Still, the tool's simplicity keeps it close to complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the work_package_id parameter is described as 'The ID of the work package'. The tool description adds only 'by ID', which restates the schema. Thus the schema does the heavy lifting, and the description adds no additional semantic value beyond the parameter explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Get' with a clear resource ('work package') and identifies the scope ('specific', 'by ID'). This inherently distinguishes it from sibling tools like list_work_packages (which retrieves multiple) and create/update_work_package.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when you have a work package ID and need its details, but it does not explicitly state when NOT to use this tool or mention alternatives like list_work_packages for browsing. The context is clear from 'by ID', but no explicit guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_projectsA

List all visible OpenProject projects

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description alone must disclose behavior. It notes that only 'visible' projects are returned, implying permission-based filtering, which is useful. However, it does not mention pagination, whether archived projects are included, or the response structure, leaving behavioral gaps for a list operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that states exactly what the tool does without redundancy. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple: no parameters, no output schema, and the description clearly states the tool's purpose. It does not describe the return format, but given the low complexity and the broad scope of 'visible projects', this is an adequate level of completeness for an AI agent to select the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema is fully covered (100%) and there is no param semantic burden. The baseline for no-param tools is 4, and the description does not need to add parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'List' and a clear resource 'all visible OpenProject projects'. It distinguishes itself from sibling tools like get_project (which fetches a single project) and list_work_packages (which lists a different resource type).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'all visible OpenProject projects' clearly conveys the context: use this tool to enumerate all projects the user can see. There is no explicit statement about when not to use it or alternatives, but the scope is clear enough for typical list scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_statusesA

List all available statuses in OpenProject

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. 'List all available statuses' implies a read-only operation with no side effects, but it does not describe pagination, response structure, or any access constraints. This is acceptable for a simple list tool but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundant information. It is concise and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, list-style tool, the description is sufficient to inform the agent of its purpose and scope. There is no output schema, but the return value (a list of statuses) is implicit. The description is appropriately complete given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool accepts zero parameters, so there are no parameter semantics to explain. The description correctly makes no mention of parameters, and the input schema confirms that none are required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and the resource ('statuses'), scoped to 'all available' within OpenProject. However, it does not differentiate from the sibling tool 'get_available_statuses', which appears to perform a similar operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 list_statuses versus get_available_statuses or other tools. It does not mention any preconditions, typical scenarios, or exclusions, leaving the agent to infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_work_packagesA

List all work packages in a given project

ParametersJSON Schema
NameRequiredDescriptionDefault
project_idYesThe ID of the project

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must convey behavioral traits. 'List all work packages' clearly implies a read-only operation and the scope is specified. However, it doesn't disclose potential details like pagination, ordering, or permission requirements, which are not critical for a simple list but could be relevant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that immediately states the action, resource, and scope without any filler or unnecessary detail. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description is nearly complete. It tells the user what to expect (a list of work packages for a project), though it doesn't mention the return format or pagination. Still, the essential context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a clear description for project_id. The tool description merely restates the parameter by saying 'given project', adding no additional meaning beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'List' and the resource 'work packages' with a scope ('in a given project'), which distinguishes it from siblings like get_work_package (single item) and list_projects (different resource). It is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage is implied (use when you need all work packages for a project), but there is no explicit guidance on when to use this versus get_work_package or when not to. The description provides context but lacks alternative suggestions or exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

update_work_packageA

Update an existing work package. Automatically validates status transitions according to OpenProject workflow rules. If you try to set an invalid status (e.g., directly from "Новый" to "Выполнено"), it will return an error with available statuses. Use get_available_statuses to see valid transitions.

ParametersJSON Schema
NameRequiredDescriptionDefault
subjectNoThe subject/title of the work package
status_idNoThe ID of the status. Must be a valid status transition according to OpenProject workflow. Use get_available_statuses to see which statuses can be set from the current status.
descriptionNoThe description of the work package
lock_versionYesThe lock version (required for updates)
work_package_idYesThe ID of the work package

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must disclose behavioral traits itself. It does this by explaining that status transitions are validated automatically, using a concrete example of an invalid jump, and stating that an error will be returned with available statuses. This goes beyond the schema and gives the agent critical expectations for error handling. It doesn't cover all possible side effects, but the key behavior is well disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences: the first states the action, the second explains the validation behavior with a specific example, and the third points to a sibling tool for valid transitions. It is front-loaded, every sentence earns its place, and there is no redundant wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an update tool with no output schema and no annotations, the description covers the core functionality, the critical validation rule, error behavior, and a reference to a relevant sibling tool. It doesn't mention return values, but that is often implicit for updates, and the lock_version requirement is already in the schema. The description is sufficiently complete for an agent to invoke the tool correctly, though it could potentially mention optimistic locking implications.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides descriptive comments for all five parameters, covering 100% of them. The description adds a general note about status validation but does not materially expand on the schema's per-parameter semantics. Baseline 3 is appropriate when the schema does the heavy lifting, and the description adds minimal extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Update an existing work package,' which clearly specifies the verb (update) and resource (work package) and distinguishes it from sibling tools like create_work_package, get_work_package, and list_work_packages. No ambiguity remains about what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool (updating existing work packages) and explicitly instructs using get_available_statuses to see valid transitions, which is a direct reference to an alternative for a subtask. It doesn't explicitly exclude create or list operations, but the purpose statement already differentiates. The guidance is sufficient, though not exhaustive.

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.

  1. 9 tool updatesv1.0.3
    • First observedadd_comment
    • First observedcreate_work_package
    • First observedget_available_statuses
    • First observedget_project
    • First observedget_work_package
    • First observedlist_projects
    • First observedlist_statuses
    • First observedlist_work_packages
    • First observedupdate_work_package
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: projects have list/get, work packages have list/get/create/update, statuses have list and available transitions, and comments have add. There's no overlap that would confuse an agent.

Naming Consistency5/5

All tools follow the verb_noun pattern consistently: list_*, get_*, create_*, update_*, add_*. All names are lowercase snake_case, and the verbs clearly indicate the operation.

Tool Count5/5

The 9 tools are well-scoped for the OpenProject domain, covering projects, work packages, statuses, and comments without excessive fragmentation or missing essentials.

Completeness4/5

Core work package lifecycle is covered (create, read, update), and status workflows are well supported. Missing delete operations and project creation are minor gaps that don't severely impact typical usage.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

Related MCP Servers

Latest Blog Posts

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/leandr92/mcp-openproject-standalone'

If you have feedback or need assistance with the MCP directory API, please join our Discord server