// SCAN REPORT

Substrate

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

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

Last updated: 4 Jul 2026

5 can modify or destroy data

8 read-only

13 tools total

Community server · catalogue entry verified 04/07/2026

How to control Substrate ↓

TOOL MAP

What Substrate exposes to your agents

Read (8) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Substrate tools

Destructive · High delete_ref This tool performs an irreversible deletion operation on references within the Substrate foundation. Execute · High execute The tool explicitly uses the verb 'execute' and describes transformation operations. Execute · High sampling_callback A 'sampling callback' in MCP context typically involves handling model sampling responses and continuing execution pipelines. Write · Medium create_ref This tool creates or updates references, which is a write operation that can be undone or modified later.

5 of Substrate's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Substrate

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

Deny destructive operations

{
  "delete_ref": {
    "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_ref": {
    "limits": [
      {
        "counter": "create_ref_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "documentation": {
    "limits": [
      {
        "counter": "documentation_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 Substrate — 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 SUBSTRATE →

Instant setup, no code required.

FULL CATALOGUE

All 13 Substrate tools

DESTRUCTIVE 1 tools

Destructive delete_ref Delete a reference

EXECUTE 2 tools

Execute execute Execute transformation using templates/personas Execute sampling_callback Handle sampling callback responses

WRITE 2 tools

Write create_ref Create or update a reference Write update_ref Update existing reference

READ 8 tools

Read documentation Access system architecture and methodology documentation Read get_server_info Get server capabilities and documentation Read list_docs List all available documentation Read list_refs List all references with optional prefix filter Read read_ref Read reference content Read show_workflows Discover available cognitive manipulation workflows Read suggest_next Get smart suggestions for next tool based on current context Read workflow_guide Get step-by-step guidance for a specific workflow

EXPLORE

Related servers

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

FAQ

Questions about Substrate

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

Yes. The Substrate server exposes 1 destructive tools including delete_ref. 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 Substrate? +

The Substrate server has 2 write tools including create_ref, update_ref. 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 Substrate.

How many tools does the Substrate MCP server expose? +

13 tools across 4 categories: Destructive, Execute, Read, Write. 8 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Substrate? +

Register the Substrate 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 Substrate tool call.

Deterministic rules across all 13 Substrate tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SUBSTRATE →

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from Substrate's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →