en es ja ko zh

Bitable MCP Server

Name: Bitable MCP Server
Author: lloydzhou

by lloydzhou

Overview Schema Source Related Servers Discussions Admin

Python

Remote

Bitable MCP 服务器

该 MCP 服务器通过模型上下文协议 (MCP) 提供对 Lark Bitable 的访问。它允许用户使用预定义的工具与 Bitable 表进行交互。

一键安装和配置

克劳德

要安装和配置服务器，请使用以下命令：

PERSONAL_BASE_TOKEN=your_personal_base_token APP_TOKEN=your_app_token uv run --with uv --with bitable-mcp bitable-mcp-install

将your_personal_base_token和your_app_token替换为您的实际令牌。

光标

即将推出

风帆冲浪

即将推出

Related MCP server: Lark Base MCP Server

可用工具

list_table - 列出当前 Bitable 的表。
- 返回：JSON 编码的表名列表。
describe_table - 通过表名描述表。
- 参数：
  - name (str): 要描述的表的名称。
- 返回：表中列的 JSON 编码列表。
read_query - 执行 SQL 查询以从表中读取数据。
- 参数：
  - sql （str）：要执行的 SQL 查询。
- 返回：查询结果的 JSON 编码列表。

手动安装和配置

安装前请确保已安装uvx 。

添加到您的 Claude 设置：

使用 uvx

"mcpServers": {
  "bitable-mcp": {
    "command": "uvx",
    "args": ["bitable-mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
}

使用 pip 安装
通过 pip 安装bitable-mcp ：

pip install bitable-mcp

修改您的 Claude 设置

"mcpServers": {
  "bitable-mcp": {
    "command": "python",
    "args": ["-m", "bitable_mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
}

为 Zed 配置

添加到您的 Zed settings.json：

使用 uvx

"context_servers": [
  "bitable-mcp": {
    "command": "uvx",
    "args": ["bitable-mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
],

使用 pip 安装

"context_servers": {
  "bitable-mcp": {
    "command": "python",
    "args": ["-m", "bitable_mcp"],
    "env": {
        "PERSONAL_BASE_TOKEN": "your-personal-base-token",
        "APP_TOKEN": "your-app-token"
    }
  }
},

调试

您可以使用 MCP 检查器来调试服务器。对于 uvx 安装：

npx @modelcontextprotocol/inspector uvx bitable-mcp

Available Tools

3 tools

describe_tableD

describe_table by table name

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes

TDQS

D1.5/5.0

Behavior1/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. The description reveals nothing about what the tool actually does behaviorally: whether it's a read operation, what information it returns, if it requires specific permissions, potential side effects, error conditions, or performance characteristics. 'describe_table' implies a read operation, but this isn't explicitly stated or detailed.

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

Conciseness3/5

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

The description is extremely concise at just three words, which could be appropriate if it were more informative. However, this brevity results in under-specification rather than efficient communication. While it's front-loaded with the core action, the single phrase doesn't earn its place by providing sufficient value.

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?

Given a tool with 1 parameter (0% schema coverage), no annotations, no output schema, and sibling tools that suggest database/query operations, the description is completely inadequate. It doesn't explain what the tool returns, how it differs from siblings, what 'describe' means in this context, or any behavioral characteristics. For a tool that presumably returns table metadata or schema information, this leaves critical gaps.

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

Parameters1/5

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

Schema description coverage is 0%, so the description must compensate for undocumented parameters. The description mentions 'by table name' which hints at the 'name' parameter, but adds no semantic meaning beyond what's obvious from the parameter name itself. It doesn't explain what constitutes a valid table name, format expectations, or how the parameter influences the tool's behavior.

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

Purpose2/5

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

The description 'describe_table by table name' is essentially a tautology that restates the tool name with minimal additional information. It mentions the action ('describe_table') and the parameter ('by table name'), but doesn't specify what describing entails (e.g., returning schema, metadata, statistics) or what resource is being described. It doesn't distinguish this tool from its sibling 'list_table' or 'read_query' beyond the obvious name difference.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to use describe_table instead of list_table (which might list tables without details) or read_query (which might execute queries). There are no prerequisites, exclusions, or contextual cues about appropriate usage scenarios.

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

list_tableC

list table for current bitable

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

C2.7/5.0

Behavior2/5

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 only states the action ('list table') without details on permissions, rate limits, pagination, or what 'current bitable' entails. This is inadequate for a tool with zero annotation coverage, as it lacks critical behavioral context.

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

Conciseness3/5

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

The description is a single phrase ('list table for current bitable'), which is concise but potentially under-specified. It lacks structure or front-loading of key details, making it efficient but not optimally informative for an agent.

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?

Given the tool's simplicity (0 parameters, no output schema), the description is incomplete. It doesn't explain what 'current bitable' means, how results are returned, or differentiate from siblings, leaving gaps in context despite low 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 0 parameters, and the schema description coverage is 100% (though empty). The description doesn't need to add parameter semantics, so it meets the baseline of 4 for tools with no parameters, as there's nothing to compensate for.

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

Purpose3/5

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

The description states the tool's purpose as 'list table for current bitable', which clearly indicates a listing operation on tables. However, it doesn't specify what 'current bitable' means or how this differs from sibling tools like 'describe_table' and 'read_query', making it somewhat vague about scope and differentiation.

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 alternatives like 'describe_table' or 'read_query'. It doesn't mention any prerequisites, context for 'current bitable', or exclusions, leaving the agent without usage instructions.

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

read_queryD

read_query by sql

ParametersJSON Schema

Name	Required	Description	Default
`sql`	Yes

TDQS

D1.3/5.0

Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description reveals nothing about what this tool actually does behaviorally - whether it executes SQL queries, what permissions are required, whether it's read-only or has side effects, what happens with invalid SQL, or what format results are returned in. 'read_query by sql' is completely inadequate for a tool that presumably executes database queries.

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?

While technically concise with just three words, this is under-specification rather than effective conciseness. The description is so sparse that it fails to communicate essential information. Every word should earn its place, but here the words don't provide enough value to justify their inclusion - they create ambiguity rather than clarity.

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?

For a SQL query execution tool with no annotations, no output schema, and a single undocumented parameter, the description is completely inadequate. It doesn't explain what the tool returns, what errors might occur, what database context it operates in, or any behavioral characteristics. This leaves the agent with insufficient information to use the tool effectively.

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

Parameters1/5

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

With 0% schema description coverage and one required parameter (sql), the description provides no meaningful information about the parameter. It doesn't explain what SQL syntax is expected, what database it runs against, whether it supports parameterized queries, or any constraints on the SQL. The description fails completely to compensate for the lack of schema documentation.

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

Purpose2/5

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

The description 'read_query by sql' is a tautology that essentially restates the tool name with minimal additional information. It mentions 'read' and 'sql' but doesn't specify what resource is being read (tables? databases? specific data?), nor does it distinguish this tool from its siblings (describe_table, list_table). The purpose remains vague rather than specific.

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?

There is absolutely no guidance about when to use this tool versus the sibling tools (describe_table, list_table). The description provides no context about appropriate use cases, prerequisites, or alternatives. This leaves the agent with no information to make an informed selection between available tools.

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.

3 tool updatesAug 15, 2025
- First observeddescribe_table
- First observedlist_table
- First observedread_query

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

C2.2/5.0

Scored 2026-04-18 11:10 across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: describe_table inspects table structure, list_table enumerates available tables, and read_query executes SQL queries. An agent can easily differentiate between metadata operations and data querying.

Naming Consistency4/5

The naming follows a consistent verb_noun pattern (describe_table, list_table, read_query) with minor deviation where 'read_query' uses 'read' instead of a more typical CRUD verb like 'execute'. All names use snake_case consistently.

Tool Count3/5

With only 3 tools, the server feels thin for a database/bitable domain. While core operations are covered, typical expectations might include create/update/delete tools. The count is borderline but functional for basic querying and inspection.

Completeness2/5

The toolset is severely incomplete for a bitable server. There are no tools for creating, updating, or deleting tables or records, which are fundamental CRUD operations. Agents will hit dead ends when trying to modify data, limiting this to read-only use cases.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Sheet Best MCP
io.github.sheetbest
Connect AI assistants to Google Sheets through controlled tools for reading and updating rows.
Workplace & Productivity App Automation
1
Astra DBOAuth
io.github.erichare
Astra DB tools for agents: schema, find, vector search, guarded writes, and interactive views.
Databases Vector Databases
1
HutchDBOAuth
com.hutchdb
Store, query, and update structured data from any AI agent
Databases Knowledge & Memory
115
Quadratic A
io.github.quadratichq
AI access to Quadratic spreadsheets: open files, run Python/SQL, query connected databases.
Data Platforms Databases Code Execution
52

Related MCP Servers

Feishu MCP Server
Content Management Systems Documentation Access RAG Systems
cso1z
A
license
Not graded
quality
B
maintenance
Provides access to Feishu (Lark) documents for AI-driven coding tools like Cursor, Windsurf, and Cline based on Model Context Protocol implementation.
Updated a month ago (2026-08-17 07:09 UTC)
291 npm
741
MIT
Lark Base MCP Serverofficial
Databases Developer Tools
Lark-Base-Team
F
license
Not graded
quality
D
maintenance
A Model Context Protocol server that provides LLMs with read and write access to Feishu Base (飞书多维表格) databases, enabling them to inspect schemas and manipulate records through natural language.
Updated a year ago (2025-05-26 14:19 UTC)
31 npm
10
-
Grist MCP Server
Databases Workplace & Productivity App Automation
gwhthompson
F
license
A
quality
D
maintenance
Enables interaction with Grist documents, workspaces, and records via the Model Context Protocol. It supports comprehensive operations including SQL querying, schema management, and record CRUD functionality.
Updated 8 months ago (2026-01-30 15:16 UTC)
11
161 npm
3
-
Feishu Base MCP Server
Databases Workplace & Productivity
Darkstar326
F
license
Not graded
quality
C
maintenance
Enables LLMs to interact with Feishu Base (Lark) databases by providing comprehensive tools for managing records, tables, and schemas. It supports full CRUD operations on database entries and structural modifications to table fields through the Model Context Protocol.
Updated 10 months ago (2025-12-05 07:13 UTC)
2 npm
-

Appeared in Searches

Information about larks

Bitable MCP 服务器

一键安装和配置

克劳德

光标

风帆冲浪

可用工具

手动安装和配置

为 Zed 配置

调试

Available Tools

TDQS

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Feishu MCP Server

Lark Base MCP Serverofficial

Grist MCP Server

Feishu Base MCP Server

Appeared in Searches