// SCAN REPORT

Pulse

5 tools. 3 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

3 can modify or destroy data

2 read-only

5 tools total

Community server · catalogue entry verified 29/06/2026

How to control Pulse ↓

TOOL MAP

What Pulse exposes to your agents

Read (2) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Pulse tools

Write · Low pulse_add_task This tool creates new task records, which is a Write operation. Write · Low pulse_manage_tags While the tool includes a delete operation, it applies only to tags (metadata), not to tasks themselves or critical data. Write · Medium pulse_update_task This tool creates or modifies data reversibly by allowing updates to task attributes (title, description, status, tags).

3 of Pulse's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Pulse

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

Rate limit write operations

{
  "pulse_add_task": {
    "limits": [
      {
        "counter": "pulse_add_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "pulse_get_info": {
    "limits": [
      {
        "counter": "pulse_get_info_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 Pulse — 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 PULSE →

Instant setup, no code required.

FULL CATALOGUE

All 5 Pulse tools

WRITE 3 tools

Write pulse_add_task Create a new task or subtask Write pulse_manage_tags Manage tags (list, update, delete) Write pulse_update_task Update a task or subtask (title/status; description is task-only). At least one update field (title, descripti

READ 2 tools

Read pulse_get_info Get system information (directory, version) Read pulse_get_tasks List tasks, get details, or find the next task

FAQ

Questions about Pulse

How do I prevent bulk modifications through Pulse? +

The Pulse server has 3 write tools including pulse_add_task, pulse_manage_tags, pulse_update_task. 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 Pulse.

How many tools does the Pulse MCP server expose? +

5 tools across 2 categories: Read, Write. 2 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Pulse? +

Register the Pulse 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 Pulse tool call.

Deterministic rules across all 5 Pulse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PULSE →

Instant setup, no code required.

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