Search for symbols in an initialized project workspace.
AI agents call workspace_symbols to retrieve information from Jons Mcp Java without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves symbol information from a workspace without modifying, executing, or deleting anything. It is a passive query operation for code navigation and analysis, posing minimal security risk if misused by an AI agent.
From the tool's definition Tool name is 'workspace_symbols' with description 'Search for symbols in an initialized project workspace.' The verb 'search' and context of Java development utilities (Eclipse JDT.LS) indicate read-only symbol lookup.
Attacks that exploit this kind of access
Search for symbols in an initialized project workspace. It is categorised as a Read tool in the Jons Mcp Java MCP Server, which means it retrieves data without modifying state.
Register the Jons Mcp Java MCP server in PolicyLayer and add a rule for workspace_symbols: 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 Jons Mcp Java. Nothing to install.
workspace_symbols 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 workspace_symbols 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 workspace_symbols. 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.
workspace_symbols is provided by the Jons Mcp Java MCP server (jonmmease/jons-mcp-java). 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 →