This record as markdown: /tools/io-github-nograai-nogra-mcp/update-run.md
What update_run does on Nogra
AI agents use update_run to create or update resources in Nogra, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nogra environment.
Why update_run is rated Medium
The 'update' verb suggests reversible modification of an existing record (Write), not deletion (Destructive) or code execution (Execute). Given the server context (AI-assisted work verification layer), 'run' likely refers to execution records or task state. Update operations on such records are typically reversible, supporting Write classification.
From the tool's definition Tool named 'update_run' with empty description. The name 'update_' prefix indicates modification of data (a run record or execution state), placing it in the Write category rather than Read.
Attacks that exploit this kind of access
The rule that runs update_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nogra, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_run, this is the rule to start with:
update_run 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 Nogra, apply this rule, and every update_run call is checked against it from then on.
Questions about update_run
update_run is a write tool on the Nogra MCP server. It is categorised as a Write tool in the Nogra MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nogra MCP server in PolicyLayer and add a rule for update_run: 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 Nogra. Nothing to install.
update_run 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_run 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_run. 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_run is provided by the Nogra MCP server (@nograai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nogra, and thousands of servers like it.
This server
Across the catalogue