AI agents use update-project to create or update resources in Linear MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linear MCP Server environment.
The tool updates project data, which is a reversible modification operation (Write category). It is not destructive since updates are generally undoable. Severity is medium because unintended project updates could disrupt team workflows, timelines, and planning, but are not inherently financial or permanently destructive.
From the tool's definition Tool name is 'update-project' and server description indicates it 'allow[s] users to manage initiatives, projects, issues, and their relationships through features like creation, viewing, updating, and prioritization.' The tool is explicitly listed among…
Documented attack patterns abuse exactly the kind of access update-project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Linear MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update-project:
{
"version": "1",
"default": "deny",
"tools": {
"update-project": {
"limits": [
{
"counter": "update-project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-project 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-project. It is categorised as a Write tool in the Linear MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Linear MCP Server MCP server in PolicyLayer and add a rule for update-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 Linear MCP Server. Nothing to install.
update-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 update-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 update-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.
update-project is provided by the Linear MCP Server MCP server (samcfinan/linear-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Linear MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 Linear MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.