readQuery
AI agents call readQuery to retrieve information from ArangoDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name explicitly contains 'read' and is differentiated from 'readWriteQuery', strongly implying it retrieves data without side effects. Combined with the server's stated capability to query ArangoDB, this is classified as a Read operation with low severity since it only accesses data without modification risk.
From the tool's definition Tool name 'readQuery' and sibling tool listing including 'readWriteQuery' indicates this is a read-only query tool. Server description mentions 'perform queries' and 'list databases and collections'.
Attacks that exploit this kind of access
readQuery. It is categorised as a Read tool in the ArangoDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ArangoDB MCP Server MCP server in PolicyLayer and add a rule for readQuery: 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 ArangoDB MCP Server. Nothing to install.
readQuery 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 readQuery 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 readQuery. 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.
readQuery is provided by the ArangoDB MCP Server MCP server (lucas-deangelis/arango-mcp-server). 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 →