// SCAN REPORT

Pathrule

30 tools. 12 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

12 can modify or destroy data

18 read-only

30 tools total

Community server · catalogue entry verified 03/07/2026

How to control Pathrule ↓

TOOL MAP

What Pathrule exposes to your agents

Read (18) Write / Execute (9) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Pathrule tools

Destructive · High pathrule_delete_memory The tool performs an irreversible deletion operation on stored memories within the path-scoped team context. Destructive · High pathrule_delete_rule The 'delete' prefix is strong evidence of a destructive action that cannot be undone. Destructive · High pathrule_delete_skill The tool deletes a skill from the path-scoped team memories system, which is irreversible. Write · Medium pathrule_create_workspace The 'create' prefix indicates a Write operation that generates new data structures.

12 of Pathrule's 30 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Pathrule

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

Deny destructive operations

{
  "pathrule_delete_memory": {
    "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

{
  "pathrule_create_workspace": {
    "limits": [
      {
        "counter": "pathrule_create_workspace_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "pathrule_get_context": {
    "limits": [
      {
        "counter": "pathrule_get_context_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 Pathrule — 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 PATHRULE →

Instant setup, no code required.

FULL CATALOGUE

All 30 Pathrule tools

DESTRUCTIVE 3 tools

Destructive pathrule_delete_memory pathrule_delete_memory Destructive pathrule_delete_rule pathrule_delete_rule Destructive pathrule_delete_skill pathrule_delete_skill

WRITE 9 tools

Write pathrule_create_workspace pathrule_create_workspace Write pathrule_resolve_refresh pathrule_resolve_refresh Write pathrule_setup pathrule_setup Write pathrule_update_memory pathrule_update_memory Write pathrule_update_rule pathrule_update_rule Write pathrule_update_skill pathrule_update_skill Write pathrule_write_memory pathrule_write_memory Write pathrule_write_rule pathrule_write_rule Write pathrule_write_skill pathrule_write_skill

READ 18 tools

Read pathrule_get_context pathrule_get_context Read pathrule_get_local_runtime_upgrade pathrule_get_local_runtime_upgrade Read pathrule_get_node pathrule_get_node Read pathrule_get_refresh_brief pathrule_get_refresh_brief Read pathrule_get_tree pathrule_get_tree Read pathrule_goto pathrule_goto Read pathrule_list_memories pathrule_list_memories Read pathrule_list_organizations pathrule_list_organizations Read pathrule_list_pending_refreshes pathrule_list_pending_refreshes Read pathrule_list_snapshots pathrule_list_snapshots Read pathrule_list_workspaces pathrule_list_workspaces Read pathrule_log_activity pathrule_log_activity Read pathrule_ping pathrule_ping Read pathrule_read_memory pathrule_read_memory Read pathrule_read_rule pathrule_read_rule Read pathrule_read_skill pathrule_read_skill Read pathrule_read_snapshot pathrule_read_snapshot Read pathrule_take_snapshot pathrule_take_snapshot

EXPLORE

Related servers

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

FAQ

Questions about Pathrule

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

Yes. The Pathrule server exposes 3 destructive tools including pathrule_delete_memory, pathrule_delete_rule, pathrule_delete_skill. 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 Pathrule? +

The Pathrule server has 9 write tools including pathrule_create_workspace, pathrule_resolve_refresh, pathrule_setup. 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 Pathrule.

How many tools does the Pathrule MCP server expose? +

30 tools across 3 categories: Destructive, Read, Write. 18 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Pathrule? +

Register the Pathrule 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 Pathrule tool call.

Deterministic rules across all 30 Pathrule tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PATHRULE →

Instant setup, no code required.

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