Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add whatevertogo/FeiShuSkill --skill lark-mcpgit clone --depth 1 https://github.com/whatevertogo/FeiShuSkillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/whatevertogo/feishuskill/lark-mcp)<a href="https://agentmods.dev/skills/whatevertogo/feishuskill/lark-mcp"><img src="https://agentmods.dev/badge/skills/whatevertogo/feishuskill/lark-mcp.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk warn
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.01260 |
| Opus 5 | $0.00036 | $0.00630 |
| Sonnet 5 | $0.00014 | $0.00252 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
lark-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lark MCP
⚠️ 重要提醒
搜索文档/知识库必须配置 OAuth：
docx_builtin_search→ 需要--oauthwiki_v1_node_search→ 需要--oauth
否则返回 99991663 错误。配置方法见 installation.md
核心规则
# 工具命名（连字符，非下划线）
✅ mcp__lark-mcp__tool_name
❌ mcp__lark_mcp__tool_name
# 参数结构
path: {app_token, table_id} # URL路径参数
params: {page_size, ...} # 查询参数
data: {fields, ...} # 请求体
useUAT: false # true=用户身份, false=租户身份
常见陷阱
# content 必须是 JSON 字符串
❌ content: {"text": "hello"}
✅ content: '{"text": "hello"}'
# 过滤条件 value 必须是数组
❌ value: "已完成"
✅ value: ["已完成"]
# 创建群组必须指定 owner_id，否则群主为机器人
owner_id: "ou_xxxxx"
# 参数名差异
docx_builtin_search: search_key # 不是 query
wiki_v1_node_search: query # 不是 search_key
# token 类型
wiki_v2_space_getNode: 用 wikcn... # 不能用 doxcn...
docx_v1_document_rawContent: 用 doxcn...
useUAT 选择
| 场景 | useUAT |
|---|---|
| 创建资源（想让用户可访问） | true |
| 搜索文档/知识库 | true |
| 访问用户私有数据 | true |
| 查询公共数据 | false |
工具速查
| 类别 | 工具 | 文档 |
|---|---|---|
| 消息 | im_v1_message_create, im_v1_message_list |
im.md |
| 群组 | im_v1_chat_create, im_v1_chat_list, im_v1_chatMembers_get |
chat.md |
| 多维表格 | bitable_v1_app_create, bitable_v1_appTableRecord_search/create/update |
bitable.md |
| 文档 | docx_builtin_search, docx_v1_document_rawContent, docx_builtin_import |
documents.md |
| 知识库 | wiki_v1_node_search, wiki_v2_space_getNode |
wiki.md |
ID 类型
| 前缀 | 类型 | 来源 |
|---|---|---|
ou_ |
用户ID | API返回 |
oc_ |
群聊ID | im_v1_chat_list |
bascn |
多维表格 | URL中 base/ 后 |
tbl |
数据表 | URL参数 table= |
doxcn |
文档 | 搜索结果或URL |
wikcn |
知识库节点 | 知识库URL |
快速示例
# 发送消息
工具: mcp__lark-mcp__im_v1_message_create
data:
receive_id: "oc_xxxxx"
msg_type: "text"
content: '{"text": "消息内容"}'
params:
receive_id_type: "chat_id"
# 创建群组
工具: mcp__lark-mcp__im_v1_chat_create
data:
name: "群名"
chat_mode: "group"
owner_id: "ou_xxxxx"
user_id_list: ["ou_xxxxx"]
params:
user_id_type: "open_id"
# 创建多维表格记录
工具: mcp__lark-mcp__bitable_v1_appTableRecord_create
path:
app_token: "bascnxxxxxx"
table_id: "tblxxxxxx"
data:
fields:
文本字段: "值"
单选字段: "选项名"
useUAT: true
# 搜索文档
工具: mcp__lark-mcp__docx_builtin_search
data:
search_key: "关键词"
count: 10
useUAT: true
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/bitable-queries.md 1.1 KB
- examples/message-formats.md 726 B
- plugin.json 1.1 KB
- reference/bitable.md 2.7 KB
- reference/chat.md 1.1 KB
- reference/common.md 1.2 KB
- reference/contact.md 801 B
- reference/documents.md 1.8 KB
- reference/im.md 1.7 KB
- reference/installation.md 2.7 KB
- reference/permissions.md 1.0 KB
- reference/troubleshooting.md 2.2 KB
- reference/wiki.md 1.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 138 lines · 71 tokens per session scan A 85254e4948b1
lark-mcp is a skill published in the GitHub repository whatevertogo/FeiShuSkill (38 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 1,260 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
google-workspace
Access Google Workspace APIs (Drive, Docs, Calendar, Gmail, Sheets, Slides, Chat, People) via local helper scripts without MCP. Handles OAuth login and direct API calls.
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
wecomcli-sheet
A tool for managing WeCom online spreadsheets, including spreadsheet files, data, and subtables. WeCom is an enterprise collaboration platform.
googleworkspace
Manage Google Drive, Gmail, Calendar, Sheets, Docs, and Chat via the gws CLI.