Retrieves a value from ResilientDB by key using HTTP REST API (Crow server on port 18000).
AI agents call get to retrieve information from ResilientDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple key-value retrieval from a database without modifying, deleting, or executing code. It is a query/fetch operation consistent with the Read category. Severity is low because retrieval operations have minimal blast radius unless the retrieved data itself is sensitive (but that is a data sensitivity issue, not a tool capability issue).
From the tool's definition Tool name 'get' and description states 'Retrieves a value from ResilientDB by key' — a read-only operation with no side effects.
Attacks that exploit this kind of access
Retrieves a value from ResilientDB by key using HTTP REST API (Crow server on port 18000). It is categorised as a Read tool in the ResilientDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ResilientDB MCP Server MCP server in PolicyLayer and add a rule for get: 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 ResilientDB MCP Server. Nothing to install.
get 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 get 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 get. 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.
get is provided by the ResilientDB MCP Server MCP server (rahulkanagaraj786/resilientdb-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 →