AI agents use write_project_file to create or update resources in Task Trellis MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Task Trellis MCP environment.
This tool creates or modifies text files within the project directory. It is reversible (files can be edited or deleted later), making it a Write operation rather than Destructive. The severity is medium because unchecked file writes could overwrite important project files or inject malicious code, but the impact is still containable through version control or deletion.
From the tool's definition Tool name 'write_project_file' and description 'Writes a UTF-8 text file at the project' indicate creation/modification of files. The verb 'Writes' confirms reversible data creation.
Documented attack patterns abuse exactly the kind of access write_project_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Task Trellis MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for write_project_file:
{
"version": "1",
"default": "deny",
"tools": {
"write_project_file": {
"limits": [
{
"counter": "write_project_file_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}write_project_file 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.
Writes a UTF-8 text file at the project. It is categorised as a Write tool in the Task Trellis MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Task Trellis MCP server in PolicyLayer and add a rule for write_project_file: 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 Task Trellis MCP. Nothing to install.
write_project_file 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 write_project_file 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 write_project_file. 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.
write_project_file is provided by the Task Trellis MCP server (langadventurellc/task-trellis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Task Trellis 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.
16 Task Trellis MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.