AI agents call read_query to retrieve information from literateMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it executes read-only queries, placing it in the Read category. Severity is medium because arbitrary SQL read queries could expose sensitive academic notes, sources, and structured data across the entire SQLite database, even if no writes are permitted.
From the tool's definition "Execute a read-only query on the literature database"
Documented attack patterns abuse exactly the kind of access read_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and literateMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_query:
{
"version": "1",
"default": "deny",
"tools": {
"read_query": {}
}
}read_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a read-only query on the literature database. It is categorised as a Read tool in the literateMCP MCP Server, which means it retrieves data without modifying state.
Register the literate MCP server in PolicyLayer and add a rule for read_query: 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 literateMCP. Nothing to install.
read_query 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 read_query 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 read_query. 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.
read_query is provided by the literate MCP server (zongmin-yu/sqlite-literature-management-fastmcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from literateMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 literateMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.