AI agents use link_github_commit to create or update resources in Scrumdo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scrumdo environment.
This tool creates a new association between a ScrumDo card and a GitHub commit, modifying card metadata. While it doesn't delete or execute external code, it does perform a persistent write operation that links external version control data to the card. The action is reversible (the link could be removed), placing it in the Write category rather than Execute.
From the tool's definition The tool 'link_github_commit' performs an 'Attach' operation, which creates or modifies metadata on a ScrumDo card by associating it with a GitHub commit SHA.
Attacks that exploit this kind of access
Attach a commit SHA to a card. It is categorised as a Write tool in the Scrumdo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scrumdo MCP server in PolicyLayer and add a rule for link_github_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 Scrumdo. Nothing to install.
link_github_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_github_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_github_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_github_commit is provided by the Scrumdo MCP server (scrumdollc/scrumdo-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 →