MCP.so
登录
K

Knowerage MCP Server

@MTimma

基本信息

分类

其他

传输方式

stdio

作者

MTimma

提交者

Martins Timma

关于 Knowerage MCP Server

Local MCP server that allows your agent to track documentation coverage over code repository.

Knowerage MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "knowerage": {
      "command": "npx",
      "args": [
        "@mtimma/knowerage"
      ],
      "env": {
        "KNOWERAGE_WORKSPACE_ROOT": "${workspaceFolder}",
        "KNOWERAGE_AUTO_FULL_RECONCILE": "true"
      }
    }
  }
}

Knowerage MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Knowerage?

Knowerage is an MCP server that manages AI analysis coverage of a codebase. It tracks which files and line ranges have been analysed by an AI assistant, storing results as markdown documents and a registry. It is intended for developers using AI coding assistants who want to measure and manage what parts of their project have been covered.

How to use Knowerage?

Register the server in your MCP host configuration using npx @mtimma/knowerage and set the KNOWERAGE_WORKSPACE_ROOT environment variable to your project root. Once configured, you talk to your AI assistant in normal sentences—for example, “analyse the logical algorithm workflow in main.java” or “what part of this codebase is not yet analysed?”. The assistant creates or updates analysis documents under knowerage/analysis/ and records coverage in knowerage/registry.json.

Key features of Knowerage

  • Create or update analysis documents with YAML frontmatter
  • Reconcile analysis records for freshness (SHA‑256 hash based)
  • Query file status: analysed vs. missing line ranges
  • List stale or problematic registry records
  • Export a coverage snapshot (JSON, YAML, TXT, or HTML)
  • Generate a bundled export of selected analyses

Use cases of Knowerage

  • Analyse a specific file, class, or algorithm and record the result
  • Get an overall coverage percentage for a project
  • Identify which parts of a codebase are not yet analysed
  • Export a coverage report for auditing or sharing
  • Detect stale analysis documents after source code changes

常见问题

1

What are the runtime requirements for Knowerage?

Node.js 18 or newer is required, and `npx` must be on your `PATH`.

2

How do I enable automatic file watching?

Set the environment variable `KNOWERAGE_AUTO_FULL_RECONCILE` to a truthy value (`1`, `true`, `yes`, or `on`). The server then watches the `knowerage/` directory and runs a short debounced full reconciliation on filesystem changes.

3

How does Knowerage avoid infinite loops from registry writes?

The file watcher ignores writes to `registry.json`, so saving the registry does not trigger another reconciliation.

4

Where does Knowerage store analysis data?

All analysis markdown files live under `knowerage/analysis/`, and the coverage registry is stored at `knowerage/registry.json` in the project root.

5

What security measures does Knowerage implement?

All file paths are validated against the workspace root; path traversal (`..`) is rejected. Registry writes use atomic file operations for crash safety. No secrets are stored in analysis files or reports.

评论

其他 分类下的更多 MCP 服务器