AI agents invoke start_working to trigger actions in Redmine MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name indicates it triggers an action that changes issue state in Redmine. While not irreversible (state can be changed again), it is more than a simple Read operation since it modifies data. It falls short of Destructive since state changes are reversible. Execute is appropriate because it triggers a state transition whose concrete effects depend on the Redmine instance's workflow configuration.
From the tool's definition Tool name 'start_working' suggests a state-changing action on a Redmine issue (likely marking it as 'in progress' or similar).
Documented attack patterns abuse exactly the kind of access start_working gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Redmine MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_working:
{
"version": "1",
"default": "deny",
"tools": {
"start_working": {
"limits": [
{
"counter": "start_working_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_working stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
start_working. It is categorised as a Execute tool in the Redmine MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Redmine MCP Server MCP server in PolicyLayer and add a rule for start_working: 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 Redmine MCP Server. Nothing to install.
start_working is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_working 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 start_working. 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.
start_working is provided by the Redmine MCP Server MCP server (snowild/redmine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Redmine 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.
35 Redmine MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.