Use this when you need to upgrade an older .prj file to a newer CONTAM project format using prjup.
AI agents use upgrade_contam_project to create or update resources in CONTAM MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CONTAM MCP environment.
This tool modifies an existing project file by converting/upgrading it to a newer format. It is a Write operation as it rewrites the file contents. While it could overwrite the original file (potentially destructive), upgrades typically produce a new or updated version rather than irreversibly destroying data, so Write is most appropriate.
From the tool's definition 'upgrade an older .prj file to a newer CONTAM project format using prjup'
Attacks that exploit this kind of access
Use this when you need to upgrade an older .prj file to a newer CONTAM project format using prjup. It is categorised as a Write tool in the CONTAM MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CONTAM MCP server in PolicyLayer and add a rule for upgrade_contam_project: 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 CONTAM MCP. Nothing to install.
upgrade_contam_project 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 upgrade_contam_project 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 upgrade_contam_project. 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.
upgrade_contam_project is provided by the CONTAM MCP server (summer521521/contam_plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →