AI agents use link_commit to create or update resources in Framedeck — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Framedeck environment.
This tool modifies card state by adding a link and automatically creating a comment. It is a write operation that changes card metadata and adds data reversibly. It does not execute code, delete data, or move money. While it references git commits (external state), it does not execute git commands or checkout code—it merely associates existing commit information with a card for tracking purposes.
From the tool's definition "Link a git commit to a card. Automatically adds commit info as a comment." — creates a link between a git commit and a card, and adds a comment automatically.
Attacks that exploit this kind of access
Link a git commit to a card. Automatically adds commit info as a comment. It is categorised as a Write tool in the Framedeck MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Framedeck MCP server in PolicyLayer and add a rule for link_commit: 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 Framedeck. Nothing to install.
link_commit 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 link_commit 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 link_commit. 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.
link_commit is provided by the Framedeck MCP server (lukaris/framedeck-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →