filter_table_names
AI agents call filter_table_names to retrieve information from MCP Alchemy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name, this tool likely filters or searches the list of table names in the database, which is a read-only metadata operation. Sibling tools include 'all_table_names' (clearly a read operation) and 'execute_query'/'schema_definitions', suggesting this is a filtered variant of 'all_table_names'. No side effects are expected. Confidence is reduced due to the empty description.
From the tool's definition Tool name 'filter_table_names' suggests filtering/querying a list of table names; description is empty and uninformative.
Attacks that exploit this kind of access
filter_table_names. It is categorised as a Read tool in the MCP Alchemy MCP Server, which means it retrieves data without modifying state.
Register the MCP Alchemy MCP server in PolicyLayer and add a rule for filter_table_names: 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 MCP Alchemy. Nothing to install.
filter_table_names 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 filter_table_names 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 filter_table_names. 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.
filter_table_names is provided by the MCP Alchemy MCP server (runekaagaard/mcp-alchemy). 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 →