// SCAN REPORT

Locus

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

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

Last updated: 12 Jun 2026

5 can modify or destroy data

12 read-only

17 tools total

Community server · catalogue entry verified 12/06/2026

How to control Locus ↓

TOOL MAP

What Locus exposes to your agents

Read (12) Write / Execute (1) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Locus tools

Destructive · High memory_purge The name 'memory_purge' in a persistent storage context strongly indicates irreversible deletion of memory/context data. Destructive · High memory_compact 'Compact' operations typically consolidate or remove data irreversibly (e.g., compacting a database removes deleted records permanently). Destructive · High memory_forget The name 'memory_forget' strongly implies irreversible removal of stored memory/context data. Write · Medium memory_import_codex The tool appears to import external data (likely code context or knowledge) into Locus's local persistent memory store, which constitutes creation or modification of stored data.

5 of Locus's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Locus

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

Deny destructive operations

{
  "memory_purge": {
    "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

{
  "memory_import_codex": {
    "limits": [
      {
        "counter": "memory_import_codex_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "memory_audit": {
    "limits": [
      {
        "counter": "memory_audit_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 Locus — 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 LOCUS →

Free to start. No card required.

FULL CATALOGUE

All 17 Locus tools

DESTRUCTIVE 3 tools

Destructive memory_purge memory_purge Destructive memory_compact memory_compact Destructive memory_forget memory_forget

WRITE 1 tools

Write memory_import_codex memory_import_codex

READ 12 tools

Read memory_audit memory_audit Read memory_calendar memory_calendar Read memory_doctor memory_doctor Read memory_explore memory_explore Read memory_project_state memory_project_state Read memory_recall memory_recall Read memory_remember memory_remember Read memory_review memory_review Read memory_scan memory_scan Read memory_search memory_search Read memory_status memory_status Read memory_timeline memory_timeline

OTHER 1 tools

Other memory_config memory_config

EXPLORE

Related servers

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

FAQ

Questions about Locus

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

Yes. The Locus server exposes 3 destructive tools including memory_purge, memory_compact, memory_forget. 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 Locus? +

The Locus server has 1 write tools including memory_import_codex. 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 Locus.

How many tools does the Locus MCP server expose? +

17 tools across 3 categories: Destructive, Read, Write. 12 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Locus? +

Register the Locus 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 Locus tool call.

Deterministic rules across all 17 Locus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LOCUS →

Free to start. No card required.

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