// SCAN REPORT

Workhour

10 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 8 Jul 2026

2 can modify or destroy data

8 read-only

10 tools total

Community server · catalogue entry checked 08/07/2026

How to control Workhour ↓

TOOL MAP

What Workhour exposes to your agents

Read (8) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Workhour tools

Execute · High sql_query This tool accepts natural language and translates it into database queries. Write · Medium save_workhour The tool saves/writes timesheet data to persistent storage.

2 of Workhour's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Workhour

PolicyLayer is an MCP gateway — it sits between your AI agents and Workhour, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "save_workhour": {
    "limits": [
      {
        "counter": "save_workhour_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "compute_statistics": {
    "limits": [
      {
        "counter": "compute_statistics_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Workhour — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON WORKHOUR →

Instant setup, no code required.

FULL CATALOGUE

All 10 Workhour tools

EXECUTE 1 tools

Execute sql_query 自然语言查询数据库（复杂分析场景）。

WRITE 1 tools

Write save_workhour save_workhour

READ 8 tools

Read compute_statistics 工时统计分析（汇总/分组）。 Read generate_weekly_report 生成周报（基于本人工时）。 Read kb_keyword_search BM25 关键词检索（精确术语/编号/数字）。 Read kb_outline 知识库目录大纲（标题+h2+metadata），问题模糊时先看全貌。 Read kb_read_section 精读指定文档某 h2 章节（含前后相邻章节）。 Read kb_semantic_search 向量语义检索（自然语言/近义概念）。 Read query_project 查询项目信息。 Read query_timesheet 查询工时填报记录（按人/项目/时间范围；不传则当前用户近30天）。

FAQ

Questions about Workhour

How do I prevent bulk modifications through Workhour? +

The Workhour server has 1 write tools including save_workhour. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Workhour.

How many tools does the Workhour MCP server expose? +

10 tools across 2 categories: Read, Write. 8 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Workhour? +

Register the Workhour MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Workhour tool call.

Deterministic rules across all 10 Workhour tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON WORKHOUR →

Instant setup, no code required.

10 Workhour tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Workhour's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →