Skip to main content
Glama
wuwu119

biji-mcp

by wuwu119
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Get笔记 MCP Server

在 Claude 中搜索 Get笔记 知识库内容。

安装

# 克隆项目
git clone <repo>
cd biji-mcp

# 安装依赖
uv sync

Related MCP server: Get笔记 MCP Server

配置

首次运行会自动创建配置文件 ~/.biji-mcp/config.json，请编辑填入你的API配置：

{
  "knowledge_bases": {
    "工作": {
      "token": "your-api-token",
      "topic_id": "your-topic-id",
      "description": "工作相关笔记"
    }
  },
  "default": "工作",
  "settings": {
    "default_top_k": 10,
    "timeout": 30
  }
}

获取API配置：进入 Get笔记 Web版知识库 → 点击"API设置"按钮。

Claude Desktop 配置

在 ~/Library/Application Support/Claude/claude_desktop_config.json 添加：

{
  "mcpServers": {
    "biji": {
      "command": "uv",
      "args": ["--directory", "/path/to/biji-mcp", "run", "biji-mcp"]
    }
  }
}

可用工具

biji_search

在知识库中搜索，返回AI生成的答案。

参数：

  • question (必需): 搜索问题

  • kb: 知识库名称

  • deep_seek: 启用深度思考

  • with_refs: 返回引用来源

biji_recall

召回原始内容片段，不经AI处理。

参数：

  • question (必需): 搜索问题

  • kb: 知识库名称

  • top_k: 返回结果数量

  • intent_rewrite: 意图改写

biji_list_kb

列出已配置的知识库。

调试

设置环境变量启用调试日志：

BIJI_MCP_DEBUG=1 uv run biji-mcp

API限制

  • QPS: 2

  • 日调用: 5000次

  • 公测期免费

Available Tools

3 tools
biji_list_kbA

列出所有已配置的Get笔记知识库

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description carries the burden of behavioral transparency. The verb 'list' implies a read-only operation, and the lack of parameters further suggests a harmless call. However, the description does not disclose return format, potential errors, or any side effects, leaving some ambiguity for such a trivial 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 sentence in Chinese, directly stating the action and object without any redundancy or filler. It is both concise and informative, earning every word.

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 list operation with no parameters and no output schema, the description provides the core function: listing all configured knowledge bases. It lacks explicit return value details, but the nature of the tool makes it reasonable to expect a list of knowledge base identifiers. This is adequate for the tool's complexity.

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, and the input schema is empty. According to the rubric, a baseline of 4 applies for 0-param tools. The description adds no parameter information because none exists, which is appropriate and sufficient.

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 '列出' (list) and a clear resource '所有已配置的Get笔记知识库' (all configured Get note knowledge bases). This clearly distinguishes it from sibling tools biji_search and biji_recall, which perform search and recall operations rather than listing available knowledge bases.

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 this tool versus the sibling tools. There is no mention of prerequisites, typical use cases, or contexts where listing knowledge bases is preferred over searching or recalling. The agent must infer usage purely from the tool's name and basic function.

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

biji_recallA

召回知识库原始内容片段，不经AI处理，返回相关度排序的结果列表

ParametersJSON Schema
NameRequiredDescriptionDefault
kbNo知识库名称（可选，默认使用配置的默认知识库）
top_kNo返回结果数量（可选，默认10）
questionYes搜索问题
intent_rewriteNo是否进行意图改写（可选，默认false）

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries full burden. It discloses that the tool performs no AI processing and returns a relevance-sorted list, but it does not mention side effects, error behavior, authentication needs, or result format details. This is moderate transparency.

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 efficiently communicates the core purpose. Every word earns its place, with no redundant or filler content.

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?

The tool has no output schema and no annotations, so the description must compensate. It explains the general result type (relevance-sorted list) but lacks detail on result fields, edge cases, or interactions between parameters like intent_rewrite and the retrieval behavior. Adequate but not 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%, with all parameters described in the input schema. The description adds no additional parameter-specific meaning beyond what the schema already provides, so it meets the baseline but does not elevate it.

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 tool recalls raw knowledge base content fragments without AI processing and returns a relevance-sorted list. This specific verb+resource+scope distinguishes it from sibling tools like biji_search (likely AI-processed) and biji_list_kb.

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: use this tool when raw content fragments are needed and no AI processing is desired. However, it does not explicitly mention alternatives or when not to use this tool, so it lacks full exclusion guidance.

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.

  1. 3 tool updatesv0.1.0
    • First observedbiji_list_kb
    • First observedbiji_recall
    • First observedbiji_search
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: biji_search returns AI-generated answers with citations, biji_recall returns raw content snippets ranked by relevance, and biji_list_kb lists configured knowledge bases. There is no overlap between these operations, so an agent can confidently choose the right tool based on whether it needs processed or raw results.

Naming Consistency5/5

All tool names follow the biji_ prefix and a simple verb pattern: search, recall, list_kb. This is consistent and predictable. The only minor deviation is that list_kb uses an underscore while the others are single verbs, but the overall convention is uniform.

Tool Count5/5

With 3 tools, the server is well-scoped for a knowledge base search service. Each tool serves a distinct need—AI search, raw recall, and KB discovery—without unnecessary extras. This is within the ideal 3-15 range and feels complete for its niche purpose.

Completeness4/5

The server covers the core functionality of searching and recalling knowledge base content, plus listing available KBs. A minor gap is the lack of a tool to retrieve metadata or browse specific documents within a KB, but that is beyond the primary search/recall workflow and can be worked around.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers