Insert lines after the specified target line in a Cosense page. If the target line is not found, append to the end of the page.
AI agents use insert_lines to create or update resources in Cosense — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cosense environment.
This tool creates or modifies data (page content in Cosense) reversibly—lines can be edited or deleted later. It is not destructive (does not irreversibly delete data), not Execute (does not run code or external operations), and not Financial.
From the tool's definition insert_lines: 'Insert lines after the specified target line in a Cosense page. If the target line is not found, append to the end of the page.' This explicitly modifies page content by adding new lines.
Documented attack patterns abuse exactly the kind of access insert_lines gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cosense, and nothing reaches the server without passing your rules. This is the rule we recommend for insert_lines:
{
"version": "1",
"default": "deny",
"tools": {
"insert_lines": {
"limits": [
{
"counter": "insert_lines_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}insert_lines 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.
Insert lines after the specified target line in a Cosense page. If the target line is not found, append to the end of the page. It is categorised as a Write tool in the Cosense MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cosense MCP server in PolicyLayer and add a rule for insert_lines: 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 Cosense. Nothing to install.
insert_lines 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 insert_lines 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 insert_lines. 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.
insert_lines is provided by the Cosense MCP server (yosider/cosense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cosense, 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.
4 Cosense tools catalogued and risk-classified — across an index of 43,000+ MCP servers.