Start a workflow session - a stateful checklist management system that drives agents through systematic, file-by-file processing. Workflows provide: - File inventory with per-file checklists - Dynamic checklist expansion based on analysis - Pattern scanning for migrations (e.g., Error→ErrorInfo) ...
AI agents invoke workflow_start to trigger actions in Bc Code Intelligence. 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.
While the tool itself appears to be a session manager, it explicitly triggers 'batch operations for large-scale changes' and 'pattern scanning for migrations' across files, meaning it initiates code transformation operations whose effects depend on workflow parameters and analysis. This is Execute rather than Write because it drives automated agent actions with side effects that propagate across the codebase.
From the tool's definition 'Start a workflow session' that 'drives agents through systematic, file-by-file processing' with 'batch operations for large-scale changes' and 'pattern scanning for migrations'.
Documented attack patterns abuse exactly the kind of access workflow_start gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bc Code Intelligence, and nothing reaches the server without passing your rules. This is the rule we recommend for workflow_start:
{
"version": "1",
"default": "deny",
"tools": {
"workflow_start": {
"limits": [
{
"counter": "workflow_start_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}workflow_start 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 a workflow session - a stateful checklist management system that drives agents through systematic, file-by-file processing. Workflows provide: - File inventory with per-file checklists - Dynamic checklist expansion based on analysis - Pattern scanning for migrations (e.g., Error→ErrorInfo) - Batch operations for large-scale changes - Progress tracking and session persistence The workflow drives the agent with explicit next-action instructions. Example usage: - Start a code review: workflow_type=. It is categorised as a Execute tool in the Bc Code Intelligence MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bc Code Intelligence MCP server in PolicyLayer and add a rule for workflow_start: 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 Bc Code Intelligence. Nothing to install.
workflow_start 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 workflow_start 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 workflow_start. 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.
workflow_start is provided by the Bc Code Intelligence MCP server (jeremyvyska/bc-code-intelligence-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bc Code Intelligence, 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.
27 Bc Code Intelligence tools catalogued and risk-classified — across an index of 43,000+ MCP servers.