Create a semantic table inside a semantic catalog in the Peaka project. The table is backed by an existing saved query, so the catalog/schema/table identifiers become a queryable view over that query. Use peaka_create_query (or peaka_list_queries) to obtain the queryId, and peaka_create_semantic_...
AI agents use peaka_create_semantic_table to create or update resources in Peaka — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Peaka environment.
This tool creates a new semantic table within a catalog, which is a write operation that modifies the project's data structures. It is reversible (can be deleted via peaka_delete_semantic_table), so it does not qualify as Destructive. While it enables query capabilities, the primary action is creation of metadata/structure rather than code execution or arbitrary command running.
From the tool's definition Tool description states 'Create a semantic table' - the verb 'create' indicates a write operation that adds new data structure/metadata to the Peaka project. The tool 'becomes a queryable view' which is a reversible structural addition.
Attacks that exploit this kind of access
Create a semantic table inside a semantic catalog in the Peaka project. The table is backed by an existing saved query, so the catalog/schema/table identifiers become a queryable view over that query. Use peaka_create_query (or peaka_list_queries) to obtain the queryId, and peaka_create_semantic_catalog (or peaka_list_catalogs) for the catalogId. ${PROJECT_ID_HINT}. It is categorised as a Write tool in the Peaka MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Peaka MCP server in PolicyLayer and add a rule for peaka_create_semantic_table: 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 Peaka. Nothing to install.
peaka_create_semantic_table is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the peaka_create_semantic_table 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 peaka_create_semantic_table. 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.
peaka_create_semantic_table is provided by the Peaka MCP server (@peaka/mcp-server-peaka). 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 →