AI agents use update-tool to create or update resources in Dynamic MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dynamic MCP Server environment.
This tool modifies tool configurations/definitions reversibly. While not destructive (changes can be undone/reverted), it could have significant blast radius if an agent modifies critical tools to perform unintended actions, inject malicious behavior, or alter tool parameters in ways that affect downstream execution. Severity is high because tool definitions control what actions are available in the system.
From the tool's definition Tool name is 'update-tool' with description 'Update an existing tool'. The verb 'update' indicates modification of an existing resource (a tool definition).
Documented attack patterns abuse exactly the kind of access update-tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dynamic MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update-tool:
{
"version": "1",
"default": "deny",
"tools": {
"update-tool": {
"limits": [
{
"counter": "update-tool_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-tool 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.
Free to start. No card required.
Update an existing tool. It is categorised as a Write tool in the Dynamic MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dynamic MCP Server MCP server in PolicyLayer and add a rule for update-tool: 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 Dynamic MCP Server. Nothing to install.
update-tool is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-tool 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.
Set action: deny in the PolicyLayer policy for update-tool. 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.
update-tool is provided by the Dynamic MCP Server MCP server (scitara-cto/dynamic-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dynamic MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 Dynamic MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.