search_fields
AI agents call search_fields 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.
The tool name 'search_fields' most naturally denotes searching or retrieving field metadata/definitions from Jira or Confluence, which is a non-destructive data retrieval operation. Even if it were to list or filter issues by fields, that would remain a Read action. No indication of write, execute, or destructive capabilities.
From the tool's definition Tool name 'search_fields' and context of sibling tools (get_issue, get_comments, get_labels, get_all_projects) suggest a query/retrieval operation.
Attacks that exploit this kind of access
search_fields. 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 search_fields: 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.
search_fields 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 search_fields 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 search_fields. 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.
search_fields is provided by the MCP Atlassian MCP server (thienntdev/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 →