get_personal_repos
AI agents call get_personal_repos to retrieve information from Mcp Atlassian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user repositories without modifying or deleting data. The 'get_' prefix and sibling tools indicate this is a retrieval operation. Severity is medium rather than low because repository access in Atlassian systems may expose sensitive code, configuration, or organizational structure that could be misused if an agent over-collects data or exfiltrates it.
From the tool's definition Tool name 'get_personal_repos' indicates retrieval of personal repositories; sibling tools like 'get_attachments', 'get_all_projects', and 'download_attachment' are all Read operations in the context of Atlassian systems.
Attacks that exploit this kind of access
get_personal_repos. It is categorised as a Read tool in the Mcp Atlassian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Atlassian MCP server in PolicyLayer and add a rule for get_personal_repos: 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 Atlassian. Nothing to install.
get_personal_repos is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_personal_repos 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 get_personal_repos. 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.
get_personal_repos is provided by the Mcp Atlassian MCP server (voarsh2/mcp-atlassian). 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 →