Everhour

41 tools. 23 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated:

23 can modify or destroy data
18 read-only
41 tools total

Community server · catalogue entry verified 29/06/2026

How to control Everhour ↓

What Everhour exposes to your agents

Read (18) Write / Execute (16) Destructive / Financial (7)
Critical Risk

The most dangerous Everhour tools

23 of Everhour's 41 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Everhour

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

Deny destructive operations
{
  "everhour_delete_client": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "everhour_add_time_to_task": {
    "limits": [
      {
        "counter": "everhour_add_time_to_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "everhour_get_client": {
    "limits": [
      {
        "counter": "everhour_get_client_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Everhour — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON EVERHOUR →

Instant setup, no code required.

All 41 Everhour tools

READ 18 tools
Read everhour_get_client Get details of a specific client by ID. Read everhour_get_current_timer Get the currently running timer, if any. Read everhour_get_current_user Get the current user profile using the /me endpoint. Read everhour_get_project Get details of a specific project by ID. Read everhour_get_running_timer Get the currently running timer using the /timer/running endpoint. Read everhour_get_section Get details of a specific section by ID. Read everhour_get_task Get details of a specific task by ID. Read everhour_get_tasks_for_project Get all tasks for a specific project using the /tasks/for_project/{project_id} endpoint. Read everhour_get_time_record Get details of a specific time record by ID. Read everhour_get_user_time Get time records for a specific user with date range and pagination support. Read everhour_list_all_sections List all sections from Everhour by iterating through all projects. Supports pagination and search query. Read everhour_list_clients List all clients from Everhour. Supports pagination and search query. Read everhour_list_projects List all projects from Everhour. Supports filtering by status, client, and search query. Read everhour_list_tasks Search tasks from Everhour. Requires either a query or project parameter. Supports filtering by status, projec Read everhour_list_team_users List all team users using the /team/users endpoint. Supports selective property filtering via props parameter. Read everhour_list_time_records List time records from Everhour. Supports filtering by project, assignee, and date range. Read everhour_list_timers List timer history from Everhour. Supports filtering by project, assignee, and date range. Read everhour_timer_status Get a summary of timer status and activity.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Everhour

Can an AI agent delete data through the Everhour MCP server? +

Yes. The Everhour server exposes 7 destructive tools including everhour_delete_client, everhour_delete_project, everhour_delete_section. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Everhour? +

The Everhour server has 13 write tools including everhour_add_time_to_task, everhour_create_client, everhour_create_project. 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 Everhour.

How many tools does the Everhour MCP server expose? +

41 tools across 4 categories: Destructive, Execute, Read, Write. 18 are read-only. 23 can modify, create, or delete data.

How do I enforce a policy on Everhour? +

Register the Everhour 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 Everhour tool call.

Deterministic rules across all 41 Everhour tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

41 Everhour tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.