AI agents use update_tag to create or update resources in Roadmap Skill — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Roadmap Skill environment.
This tool creates or modifies data (tags) in a reversible manner, fitting the Write category. It is not Read (no retrieval-only operation), not Execute (no code/command execution), not Destructive (changes are reversible), not Financial (no money movement), and not Other.
From the tool's definition Tool name 'update_tag' and description 'Update an existing tag' indicate modification of existing data. The server manages tasks, tags, and dependency graphs stored locally. Updating a tag modifies metadata but is reversible.
Documented attack patterns abuse exactly the kind of access update_tag gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Roadmap Skill, and nothing reaches the server without passing your rules. This is the rule we recommend for update_tag:
{
"version": "1",
"default": "deny",
"tools": {
"update_tag": {
"limits": [
{
"counter": "update_tag_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_tag 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 tag. It is categorised as a Write tool in the Roadmap Skill MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Roadmap Skill MCP server in PolicyLayer and add a rule for update_tag: 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 Roadmap Skill. Nothing to install.
update_tag 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_tag 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_tag. 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_tag is provided by the Roadmap Skill MCP server (shiquda/roadmap-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 32 Roadmap Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
32 Roadmap Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.