update_block

Update a SiYuan note block with new content while preserving IAL metadata

SERVERMartin MCP Toolbox SOURCE2234839/mcpserver

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade C, identity unverified Pull the record →

This record as markdown: /tools/2234839-mcpserver/update-block.md

WHAT IT DOES

What update_block does on Martin MCP Toolbox

AI agents use update_block to create or update resources in Martin MCP Toolbox, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Martin MCP Toolbox environment.

RISK

Why update_block is rated Medium

This tool modifies data reversibly by updating note block content. It is a Write operation because it changes existing information without permanently deleting it. Severity is medium because unintended modifications to notes could disrupt a user's note-taking system, but the operation is reversible (can be undone or re-edited).

From the tool's definition Tool name is 'update_block' and description states it 'Update[s] a SiYuan note block with new content'. The action modifies existing data (note content) in the SiYuan Notes system.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs update_block safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Martin MCP Toolbox, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_block, this is the rule to start with:

update_block Rate-limited

update_block stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_block": {
      "limits": [
        {
          "counter": "update_block_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Martin MCP Toolbox, apply this rule, and every update_block call is checked against it from then on.

FAQ

Questions about update_block

What does the update_block tool do? +

Update a SiYuan note block with new content while preserving IAL metadata. It is categorised as a Write tool in the Martin MCP Toolbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_block? +

Register the Martin MCP Toolbox MCP server in PolicyLayer and add a rule for update_block: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Martin MCP Toolbox. Nothing to install.

What risk level is update_block? +

update_block is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_block? +

Yes. Add a rate_limit block to the update_block rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block update_block completely? +

Set action: deny in the PolicyLayer policy for update_block. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides update_block? +

update_block is provided by the Martin MCP Toolbox MCP server (2234839/mcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Martin MCP Toolbox, and thousands of servers like it.

This server

All 14 Martin MCP Toolbox tools →

Across the catalogue

aroflo_create_or_update_record on AroFlo MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →