Count records in a table, optionally filtered.
AI agents call count_records to retrieve information from Instant Db without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The count_records tool queries and aggregates existing data from a table. It has no side effects; it does not create, modify, or delete records. Even with optional filtering, it remains a retrieval operation. The severity is low because misuse causes no data loss or unintended modifications—only potential information disclosure of record counts, which is a minor risk in most contexts.
From the tool's definition Tool performs a count operation on records in a table with optional filtering—a read-only query that retrieves aggregate data without modifying state. Description explicitly states 'Count records' with no mention of creation, deletion, or modification.
Attacks that exploit this kind of access
Count records in a table, optionally filtered. It is categorised as a Read tool in the Instant Db MCP Server, which means it retrieves data without modifying state.
Register the Instant Db MCP server in PolicyLayer and add a rule for count_records: 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 Instant Db. Nothing to install.
count_records 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 count_records 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 count_records. 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.
count_records is provided by the Instant Db MCP server (urbushey/mcp-db). 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 →