Взаимодействовать с Confluence
Это MCP-сервер на основе TypeScript, который предоставляет инструменты для взаимодействия с Confluence. Он демонстрирует основные концепции MCP, предоставляя:
Инструменты для выполнения CQL-запросов на страницах поиска
Инструменты для извлечения содержимого страниц Confluence
Инструменты для обновления контента на страницах Confluence
Related MCP server: Confluence MCP Server
execute_cql_searchЦель : Выполнить CQL-запрос для поиска страниц Confluence.
Параметры : cql , limit (по умолчанию: 10).
get_page_contentЦель : Извлечь содержимое страницы Confluence.
Параметры : pageId .
update_page_contentЦель : Обновление содержимого страницы Confluence.
Параметры : pageId , content , title (необязательно, если вы хотите его изменить).
Установить зависимости:
npm installСборка сервера:
npm run buildДля разработки с автоматической пересборкой:
npm run watchЧтобы автоматически установить Confluence Communication Server MCP Server для Claude Desktop через Smithery :
npx -y @smithery/cli install @KS-GEN-AI/confluence-mcp-server --client claudeДля использования с Claude Desktop добавьте конфигурацию сервера:
На MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
В Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"Confluence communication server": {
"command": "node",
"args": ["/PATH_TO_THE_PROJECT/build/index.js"],
"env": {
"CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net/wiki",
"CONFLUENCE_API_MAIL": "Your email",
"CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens"
}
}
}
}Поскольку серверы MCP взаимодействуют через stdio, отладка может быть сложной. Мы рекомендуем использовать MCP Inspector , который доступен как пакетный скрипт:
npm run inspectorИнспектор предоставит URL-адрес для доступа к инструментам отладки в вашем браузере.
Execute a CQL query on Confluence to search pages
| Name | Required | Description | Default |
|---|---|---|---|
| cql | Yes | CQL query string | |
| limit | No | Number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states the basic function, omitting details like read-only status, authentication needs, rate limits, or result format.
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 concise sentence with no waste. However, it is very minimal and could include more useful details without losing conciseness.
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 has 2 parameters, no output schema, and no annotations, the description is incomplete. It does not hint at response format, pagination behavior, or any special CQL syntax requirements.
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 coverage is 100% with descriptions for both parameters (cql and limit). The description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
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 (Execute), resource (CQL query), and target (Confluence to search pages). It differentiates from siblings like execute_jql_search by mentioning Confluence, but could be more explicit about CQL being Confluence-specific.
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 on when to use this tool versus alternatives. Siblings include JQL search and page retrieval tools, but the description provides no context on when CQL search is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the content of a Confluence page
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | Confluence Page ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the burden of behavioral disclosure. It only says 'Get the content', failing to mention read-only nature, permissions, or return format.
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 concise sentence, but it omits important context, making it underinformative 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 lack of output schema, the description should clarify what 'content' entails (e.g., body, metadata, attachments) and whether it is read-only, but it provides no such details.
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 coverage is 100%, and the description adds no additional meaning beyond the schema's 'Confluence Page ID' for the pageId parameter, meeting the baseline but not exceeding it.
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 verb 'Get' and the resource 'the content of a Confluence page', distinguishing it from sibling tools that operate on Jira issues or create/update pages.
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 like create_page or update_page, nor does it mention any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update the content of a Confluence page
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | Confluence Page ID | |
| content | Yes | HTML content to update the page with | |
| title | No | Page title (optional, if you want to change it) |
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 'update' which implies a mutation, but doesn't disclose critical traits like required permissions, whether changes are reversible, rate limits, or what happens on success/failure. This leaves significant gaps for a tool that modifies content.
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 zero waste. It's front-loaded with the core action and resource, making it easy to parse quickly. Every word earns its place without redundancy.
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 complexity of a mutation tool with no annotations and no output schema, the description is incomplete. It lacks behavioral context (e.g., permissions, side effects), usage guidelines, and details on return values or errors. For updating page content, this leaves too many unknowns for effective tool selection.
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 clear descriptions for all parameters (pageId, content, title). The description adds no additional meaning beyond what the schema provides, such as format details for content or title constraints. Baseline 3 is appropriate since 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 verb 'update' and resource 'content of a Confluence page', making the purpose immediately understandable. It distinguishes from sibling tools like 'get_page_content' (read vs. write) and 'execute_cql_search' (search vs. update), though it doesn't explicitly mention these distinctions in the description itself.
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 prerequisites (e.g., needing page ID), exclusions, or compare it to sibling tools like 'get_page_content' for reading or 'execute_cql_search' for finding pages. Usage is implied by the action but not explicitly defined.
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.
execute_cql_searchget_page_contentupdate_page_contentScored across 3 tools
Each tool has a clearly distinct purpose: execute_cql_search handles search queries, get_page_content retrieves page content, and update_page_content modifies page content. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.
All tools follow a consistent verb_noun pattern (execute_cql_search, get_page_content, update_page_content) with clear action verbs and descriptive nouns. This uniformity enhances readability and predictability across the tool set.
With only 3 tools, the set feels thin for a Confluence server, lacking operations like creating or deleting pages, managing comments, or handling attachments. While the tools cover basic read/update/search, the scope is limited and may require workarounds for full domain coverage.
The tool set is significantly incomplete for Confluence communication, missing essential CRUD operations such as create_page and delete_page, as well as functionalities for comments, spaces, or user management. This will likely cause agent failures when attempting comprehensive workflows.
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
Connect Claude to your Platform7n workspaces — chat, links, and tasks. One-click OAuth.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Search, read, create and edit your Memol notes from Claude. Team note-taking with AI search.
