// SCAN REPORT

Pearlog

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

1 destructive tool with no built-in limits. Policy required.

Last updated: 5 Jul 2026

5 can modify or destroy data

5 read-only

10 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 10 of 10 tools

How to control Pearlog ↓

TOOL MAP

What Pearlog exposes to your agents

Read (5) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Pearlog costs in tokens

1,313 tokens of tool definitions, loaded on every request

0.7% of a 200k context window

282 heaviest tool: create_ticket

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Pearlog tools

Destructive · High delete_ticket This tool permanently deletes tickets, which is an irreversible operation that cannot be undone. Write · Medium create_ticket The tool creates new tickets/tasks, which is a reversible write operation. Write · Medium move_ticket This tool modifies ticket state by relocating it across projects, which is a reversible change. Write · Medium patch_ticket The tool modifies ticket properties in a controlled, non-destructive manner.

5 of Pearlog'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 Pearlog

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

Deny destructive operations

{
  "delete_ticket": {
    "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

{
  "create_ticket": {
    "limits": [
      {
        "counter": "create_ticket_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_status_labels": {
    "limits": [
      {
        "counter": "get_status_labels_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 Pearlog — 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 PEARLOG →

Instant setup, no code required.

FULL CATALOGUE

All 10 Pearlog tools

DESTRUCTIVE 1 tools

Destructive delete_ticket Delete a ticket permanently.

WRITE 4 tools

Write create_ticket Create a new ticket (task/bug/feature/etc.) in a Pearlog project. Write move_ticket Move a ticket to a different project. Write patch_ticket Partially update a ticket — only the fields you provide are changed. Ideal for changing status, reassigning, u Write update_ticket Fully update a ticket. You must supply all fields you want to keep — omitted optional fields may be cleared. U

READ 5 tools

Read get_status_labels Get the kanban column / status labels for a project. Use this to discover valid status IDs before changing a t Read get_ticket Get a single ticket by its ID. Read list_projects List all Pearlog projects accessible to the authenticated user. Read list_tickets List tickets with optional filters. Use this to browse tickets by project, assignee, status, or type. Read list_users List all users in the Pearlog instance. Use this to find user IDs for ticket assignment.

EXPLORE

Related servers

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

FAQ

Questions about Pearlog

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

Yes. The Pearlog server exposes 1 destructive tools including delete_ticket. 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 Pearlog? +

The Pearlog server has 4 write tools including create_ticket, move_ticket, patch_ticket. 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 Pearlog.

How many tools does the Pearlog MCP server expose? +

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

How do I enforce a policy on Pearlog? +

Register the Pearlog 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 Pearlog tool call.

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

ENFORCE POLICY ON PEARLOG →

Instant setup, no code required.

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