Merges content from multiple files into a single output file.
AI agents use merge_content to create or update resources in Code Merge MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Merge MCP environment.
The tool creates or modifies data (a merged output file) in a reversible manner. While it combines existing content, the result is a new or overwritten file. This is a Write operation rather than Read (no query-only behavior), Execute (no arbitrary code/command execution), Destructive (the original files appear unmodified; the operation is reversible by deleting the output), or Financial.
From the tool's definition Tool description states it 'Merges content from multiple files into a single output file,' which creates or modifies a file with combined content.
Documented attack patterns abuse exactly the kind of access merge_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Merge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for merge_content:
{
"version": "1",
"default": "deny",
"tools": {
"merge_content": {
"limits": [
{
"counter": "merge_content_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}merge_content 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.
Merges content from multiple files into a single output file. It is categorised as a Write tool in the Code Merge MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Code Merge MCP server in PolicyLayer and add a rule for merge_content: 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 Code Merge MCP. Nothing to install.
merge_content 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 merge_content 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 merge_content. 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.
merge_content is provided by the Code Merge MCP server (yy1588133/code-merge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Merge MCP, 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.
3 Code Merge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.