Set current project directory and load debug configurations from .vscode/launch.json.
AI agents use set_project to create or update resources in Openocd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openocd environment.
This tool performs a reversible state modification: it changes which project directory is active and loads configuration data from disk. While it doesn't delete data or execute arbitrary code directly, it alters the debugging context that subsequent tools will operate within.
From the tool's definition Tool description states it 'Set current project directory and load debug configurations from .vscode/launch.json' — this modifies the internal state of the MCP server by changing the active project context and loading configuration files.
Documented attack patterns abuse exactly the kind of access set_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openocd, and nothing reaches the server without passing your rules. This is the rule we recommend for set_project:
{
"version": "1",
"default": "deny",
"tools": {
"set_project": {
"limits": [
{
"counter": "set_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_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.
Set current project directory and load debug configurations from .vscode/launch.json. It is categorised as a Write tool in the Openocd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openocd MCP server in PolicyLayer and add a rule for set_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 Openocd. Nothing to install.
set_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 set_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 set_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.
set_project is provided by the Openocd MCP server (luiox/openocd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openocd, 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.
14 Openocd tools catalogued and risk-classified — across an index of 43,000+ MCP servers.