AI agents use mcp_update to create or update resources in 1MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 1MCP Server environment.
The tool modifies MCP server state, which could alter behavior, dependencies, or configurations. While updates are typically reversible (can be downgraded), the high blast radius justifies 'high' severity: a malicious update could inject malicious MCP servers into the aggregator or break connectivity for all clients relying on this unified server.
From the tool's definition Tool name 'mcp_update' and description 'Update an MCP server' indicate modification of existing MCP server configurations or state. This is a reversible write operation on system-critical infrastructure.
Documented attack patterns abuse exactly the kind of access mcp_update gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 1MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mcp_update:
{
"version": "1",
"default": "deny",
"tools": {
"mcp_update": {
"limits": [
{
"counter": "mcp_update_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mcp_update 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 MCP server. It is categorised as a Write tool in the 1MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 1MCP Server MCP server in PolicyLayer and add a rule for mcp_update: 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 1MCP Server. Nothing to install.
mcp_update 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 mcp_update 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 mcp_update. 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.
mcp_update is provided by the 1MCP Server MCP server (1mcp-app/agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 1MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 1MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.