manage_agent_skills
Safely inspect, install, update, or uninstall the small bundled tdmcp skill catalog for Codex or Claude. Mutations default to dry-run, use exact manifest ownership, reject unowned conflicts and symlinks, and roll back partial filesystem changes. Only package-bundled skills are accepted; this is n...
This record as markdown: /tools/io-github-pantani-tdmcp/manage-agent-skills.md
What manage_agent_skills does on tdmcp — TouchDesigner MCP server
AI agents use manage_agent_skills to create or update resources in tdmcp — TouchDesigner MCP server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your tdmcp — TouchDesigner MCP server environment.
Why manage_agent_skills is rated Medium
This tool modifies the bundled skill catalog through install, update, and uninstall operations. While these are filesystem-level changes, the description emphasizes safety guardrails (dry-run defaults, rollback capability, owned manifest validation, rejection of symlinks) that prevent irreversible damage. The scope is limited to 'package-bundled skills only', not arbitrary remote code.
From the tool's definition Tool description explicitly states it can 'install, update, or uninstall' skills, indicating reversible modification of system state.
Attacks that exploit this kind of access
The rule that runs manage_agent_skills safely
PolicyLayer is an MCP gateway: it sits between your AI agents and tdmcp — TouchDesigner MCP server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_agent_skills, this is the rule to start with:
manage_agent_skills 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 tdmcp — TouchDesigner MCP server, apply this rule, and every manage_agent_skills call is checked against it from then on.
Questions about manage_agent_skills
Safely inspect, install, update, or uninstall the small bundled tdmcp skill catalog for Codex or Claude. Mutations default to dry-run, use exact manifest ownership, reject unowned conflicts and symlinks, and roll back partial filesystem changes. Only package-bundled skills are accepted; this is not a remote or arbitrary skill installer. It is categorised as a Write tool in the tdmcp — TouchDesigner MCP server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the tdmcp — TouchDesigner MCP server MCP server in PolicyLayer and add a rule for manage_agent_skills: 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 tdmcp — TouchDesigner MCP server. Nothing to install.
manage_agent_skills 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 manage_agent_skills 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 manage_agent_skills. 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.
manage_agent_skills is provided by the tdmcp — TouchDesigner MCP server MCP server (@dpantani/tdmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on tdmcp — TouchDesigner MCP server, and thousands of servers like it.
This server
Across the catalogue