Create a new card in a project column
AI agents use create_project_card to create or update resources in Mcp Github — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Github environment.
The tool creates new project management data within GitHub. This is a Write-category action because it creates a new resource (project card) that can be modified or deleted later. Severity is medium because misuse could clutter project boards or create confusion, but the impact is limited to project organization metadata and is fully reversible.
From the tool's definition Tool description states 'Create a new card in a project column' — this creates a new entity (card) in GitHub's project management system, a reversible operation.
Attacks that exploit this kind of access
Create a new card in a project column. It is categorised as a Write tool in the Mcp Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Github MCP server in PolicyLayer and add a rule for create_project_card: 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 Mcp Github. Nothing to install.
create_project_card 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 create_project_card 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 create_project_card. 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.
create_project_card is provided by the Mcp Github MCP server (@missionsquad/mcp-github). 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 →