Lark ToolsSAFE
MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件,读取文档、发送消息、合同审批、数据处理.....
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件 通过打通飞书与cursor,向LLM提供读取文档、发送消息、合同审批、数据处理..... 可能会有意想不到的组合方式
创建自建应用
MCP服务运行基于token,需要创建一个应用并做发布 https://open.feishu.cn/document/server-docs/api-call-guide/terminolog
然后对应用进行文档授权,这一步较为繁琐,参考文档,选择合适的方案:https://open.feishu.cn/document/uAjLw4CM/ugTN1YjL4UTN24CO1UjN/trouble-shooting/how-to-add-permissions-to-app
运行服务
- 拷贝 .env.example 为 .env 文件
- 修改 .env 文件中的 FEISHUAPPID 为飞书自建应用的 app_id
- 修改 .env 文件中的 FEISHUAPPSECRET 为飞书自建应用的 app_secret
- 运行 MCP Server
- Add MCP to cursor
- Agent 模式下,输入飞书文档链接,让AI帮你阅读与整理内容
效果
tools
getfeishudoc
获取飞书文档信息(纯文本)
4b5e865dd1dcOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add lark-tools-mcp --env FEISHU_APP_SECRET=${FEISHU_APP_SECRET} -- npx -y [email protected]{
"mcpServers": {
"lark-tools-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"FEISHU_APP_SECRET": "${FEISHU_APP_SECRET}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_feishu_doc_raw | read | Retrieve the content of Feishu document based on documentId |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
.gitignore copy
@larksuiteoapi/node-sdk, @modelcontextprotocol/sdk, cross-env, dotenv, express, nodemon, remeda, yargs
Gates applied: no_behavioural_pass.
4b5e865dd1dcfull audit observations/trust-audit/mcp-server/li-vien__lark-tools.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 4b5e865dd1dc | SAFE | B | 89 | first audit |
Questions
What is the Lark Tools MCP server?
MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件,读取文档、发送消息、合同审批、数据处理.....
What tools does Lark Tools expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Lark Tools safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Lark Tools need?
It reads FEISHU_APP_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Lark Tools run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on npm as lark-tools-mcp at 0.0.1.
How current is this page?
The grade is for one exact copy of the source (4b5e865dd1dc), read on 2026-10-08. The repository is watched and re-audited when it changes.