github_create_issue
AI agents use github_create_issue to create or update resources in Integrations MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Integrations MCP environment.
Creating a GitHub issue modifies data (adds a new issue to a repository) but the action is reversible (the issue can be deleted). This is a Write operation. Severity is medium because misuse could spam repositories with unwanted issues, affecting team workflows, but causes no permanent damage or financial impact.
From the tool's definition Tool name 'github_create_issue' indicates creation of a new GitHub issue, which is a reversible write operation. Description is empty, reducing confidence slightly.
Attacks that exploit this kind of access
github_create_issue. It is categorised as a Write tool in the Integrations MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Integrations MCP server in PolicyLayer and add a rule for github_create_issue: 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 Integrations MCP. Nothing to install.
github_create_issue 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 github_create_issue 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 github_create_issue. 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.
github_create_issue is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →