// SCAN REPORT

Structured-sh

9 tools. 6 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

6 can modify or destroy data

3 read-only

9 tools total

Community server · catalogue entry verified 29/06/2026

How to control Structured-sh ↓

TOOL MAP

What Structured-sh exposes to your agents

Read (3) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Structured-sh tools

Destructive · High delete_memory This tool irreversibly deletes data (a memory and all its associated data). Execute · Medium flush_memory This tool triggers an explicit I/O operation — forcing buffered in-memory records to be written out to Parquet storage. Execute · High query_memory This tool executes arbitrary DuckDB SQL queries, making it Execute category. Write · Medium create_memory This tool creates new memory schemas and structures for persistent storage.

6 of Structured-sh's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Structured-sh

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

Deny destructive operations

{
  "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

{
  "create_memory": {
    "limits": [
      {
        "counter": "create_memory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "describe_memory": {
    "limits": [
      {
        "counter": "describe_memory_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 Structured-sh — 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 STRUCTURED-SH →

Instant setup, no code required.

FULL CATALOGUE

All 9 Structured-sh tools

DESTRUCTIVE 1 tools

Destructive delete_memory Delete a memory and all its data.

EXECUTE 2 tools

Execute flush_memory Force flush buffered records to Parquet. Execute query_memory Run a DuckDB SQL query across memories. Use memory names as table names. Example: SELECT FROM user_preference

WRITE 3 tools

Write create_memory Create a new structured memory with typed fields. This defines a schema for storing structured data as Parquet Write store_document Store an unstructured JSON document in a collection. Write write_memory Write structured records to a memory. Records are buffered and automatically flushed to Parquet.

READ 3 tools

Read describe_memory Get detailed information about a memory including its schema, stats, and sample data. Read get_document Retrieve a document by its ID. Read list_memories List all structured memories with their schemas, record counts, and storage usage.

EXPLORE

Related servers

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

FAQ

Questions about Structured-sh

Can an AI agent delete data through the Structured-sh MCP server? +

Yes. The Structured-sh server exposes 1 destructive tools including delete_memory. 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 Structured-sh? +

The Structured-sh server has 3 write tools including create_memory, store_document, write_memory. 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 Structured-sh.

How many tools does the Structured-sh MCP server expose? +

9 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Structured-sh? +

Register the Structured-sh 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 Structured-sh tool call.

Deterministic rules across all 9 Structured-sh tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON STRUCTURED-SH →

Instant setup, no code required.

9 Structured-sh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.