all_table_names
AI agents call all_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.
The tool name strongly implies it retrieves a list of all table names from the connected database — a read-only metadata operation with no side effects. The sibling tool 'filter_table_names' further confirms this is a listing/query operation. Empty description lowers confidence slightly, but the naming pattern is clear. Blast radius is low as it only exposes schema metadata.
From the tool's definition Tool name 'all_table_names' combined with server context of database exploration tools (filter_table_names, schema_definitions) suggests listing/retrieval of table names. Description is empty.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
all_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 all_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.
all_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 all_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 all_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.
all_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 →