// SCAN REPORT

Lattice

15 tools. 8 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

8 can modify or destroy data

7 read-only

15 tools total

Community server · catalogue entry verified 11/06/2026

How to control Lattice ↓

TOOL MAP

Read (7) Write / Execute (6) Destructive / Financial (2)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · Medium lattice_reset This tool irreversibly clears all handles and bindings accumulated during an analysis session. Destructive · High lattice_memo_delete This tool irreversibly removes data (memos) from the Lattice engine's working memory. Execute · High nucleus_execute This tool executes arbitrary commands in the Nucleus DSL language on documents. Execute · Medium analyze_document This tool executes an analysis operation using an RLM engine on a document, which involves running a computational process (the Lattice/Nucleus DSL engine) against input data.

8 of Lattice's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL LATTICE

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

Deny destructive operations

{
  "lattice_memo_delete": {
    "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

{
  "lattice_close": {
    "limits": [
      {
        "counter": "lattice_close_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "lattice_bindings": {
    "limits": [
      {
        "counter": "lattice_bindings_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 Lattice — 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 LATTICE →

Free to start. No card required.

ALL 15 LATTICE TOOLS

DESTRUCTIVE 2 tools

Destructive lattice_memo_delete Delete a memo that is no longer needed to free memory. Use this when context becomes stale or irrelevant (e.g Destructive lattice_reset Clear all handles and bindings but keep the document loaded. Use this to start fresh analysis.

EXECUTE 5 tools

Execute nucleus_execute Execute Nucleus commands directly on a document without LLM orchestration. Execute analyze_document Analyze a document using the Recursive Language Model (RLM). Execute lattice_llm_batch_respond Resolve a pending (llm_batch …) suspension with all N responses at once. (llm_batch COLL (lambda x (llm_query Execute lattice_llm_respond Resolve a pending (llm_query …) suspension with a single string response. When lattice_query hits (llm_query Execute lattice_query Execute a Nucleus query on the loaded document.

WRITE 1 tools

Write lattice_close Close the current session and free memory.

READ 7 tools

Read lattice_bindings Show current handle bindings. Returns all active handles with their stubs: $grep_error: Array(500) [preview Read lattice_expand Get full data from a handle when you need to inspect actual results. USE THIS WHEN: - You need to see actual Read lattice_help Get complete Nucleus command reference documentation. Read lattice_load Load a document for analysis. Call this first before querying. Read lattice_stats Get statistics about the currently loaded document. Read lattice_status Get current session status including document info, active handles, and timeout. Read nucleus_commands Get reference documentation for available Nucleus commands.

RELATED SERVERS

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

FAQ

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

Yes. The Lattice server exposes 2 destructive tools including lattice_memo_delete, lattice_reset. 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 Lattice? +

The Lattice server has 1 write tools including lattice_close. 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 Lattice.

How many tools does the Lattice MCP server expose? +

15 tools across 4 categories: Destructive, Execute, Read, Write. 7 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Lattice? +

Register the Lattice 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 Lattice tool call.

Deterministic rules across all 15 Lattice tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LATTICE →

Free to start. No card required.

15 Lattice tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Lattice

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL LATTICE

// ALL 15 LATTICE TOOLS

// RELATED SERVERS

// FAQ