Search symbols from the SQLite workspace index.
AI agents call search_symbols to retrieve information from Syntax Map without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries indexed symbol data from SQLite. It has no side effects, does not execute code, does not modify data, and does not trigger external operations. It is a standard read/search operation in a code analysis context, making it low-severity even if misused by an AI agent, as the worst outcome is returning unwanted symbol information.
From the tool's definition Tool description states it 'Search[es] symbols from the SQLite workspace index' — a pure query operation against indexed data with no modification, creation, or execution capability.
Attacks that exploit this kind of access
Search symbols from the SQLite workspace index. It is categorised as a Read tool in the Syntax Map MCP Server, which means it retrieves data without modifying state.
Register the Syntax Map MCP server in PolicyLayer and add a rule for search_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 Syntax Map. Nothing to install.
search_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 search_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 search_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.
search_symbols is provided by the Syntax Map MCP server (kht6163/syntax-map-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 →