tcm_smart_plan
A write tool on the OpenTCM_Discovery MCP server.
This record as markdown: /tools/opentcm-discovery/tcm-smart-plan.md
What tcm_smart_plan does on OpenTCM_Discovery
AI agents use tcm_smart_plan to create or update resources in OpenTCM_Discovery, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenTCM_Discovery environment.
Why tcm_smart_plan is rated Medium
An AI agent can call tcm_smart_plan faster than any human can review: one bad instruction and it creates or modifies resources in OpenTCM_Discovery by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs tcm_smart_plan safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenTCM_Discovery, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tcm_smart_plan, this is the rule to start with:
tcm_smart_plan 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.
The button opens the PolicyLayer dashboard: create your workspace, connect OpenTCM_Discovery, apply this rule, and every tcm_smart_plan call is checked against it from then on.
Questions about tcm_smart_plan
tcm_smart_plan is a write tool on the OpenTCM_Discovery MCP server. It is categorised as a Write tool in the OpenTCM_Discovery MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenTCM_Discovery MCP server in PolicyLayer and add a rule for tcm_smart_plan: 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 OpenTCM_Discovery. Nothing to install.
tcm_smart_plan 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 tcm_smart_plan 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 tcm_smart_plan. 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.
tcm_smart_plan is provided by the OpenTCM_Discovery MCP server (S0mbraD/OpenTCM_Discovery). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenTCM_Discovery, and thousands of servers like it.
This server
Across the catalogue