update_lead
Update a native Huly lead by funnel ID or exact name and LEAD-<number> identifier. Supported fields are title, Markdown description, a workflow status matched exactly after normalization (trimmed, case-insensitive, and ignoring spaces, hyphens, and underscores), employee assignee, start date, due...
This record as markdown: /tools/io-github-dearlordylord-huly-mcp/update-lead.md
What update_lead does on Huly
AI agents use update_lead to create or update resources in Huly, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Huly environment.
Why update_lead is rated Medium
Tool modifies lead fields reversibly (title, description, status, assignee, dates) without deletion or financial impact.
From the tool's definition Update a native Huly lead by funnel ID or exact name and LEAD-<number> identifier.
Attacks that exploit this kind of access
The rule that runs update_lead safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Huly, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_lead, this is the rule to start with:
update_lead 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Huly, apply this rule, and every update_lead call is checked against it from then on.
Questions about update_lead
Update a native Huly lead by funnel ID or exact name and LEAD-<number> identifier. Supported fields are title, Markdown description, a workflow status matched exactly after normalization (trimmed, case-insensitive, and ignoring spaces, hyphens, and underscores), employee assignee, start date, due date, and Customer mixin description. Omitted fields are unchanged; pass null explicitly to clear description, assignee, dates, or customer description. Existing people are resolved exactly and ambiguous identifiers fail. It is categorised as a Write tool in the Huly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Huly MCP server in PolicyLayer and add a rule for update_lead: 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 Huly. Nothing to install.
update_lead 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_lead 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_lead. 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_lead is provided by the Huly MCP server (@firfi/huly-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Huly, and thousands of servers like it.
This server
Across the catalogue