Perform vector similarity search on an OceanBase table. Args: table_name: Name of the table to search. vector_data: Query vector. vec_column_name: column name containing vectors to search. distance_func: The index distance algorithm used when comparing the distance between two vectors. with_dista...
AI agents call oceanbase_vector_search to retrieve information from Mcp Oceanbase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a database query tool that searches and retrieves vector data based on similarity metrics. It has no side effects—it only reads and returns results. The operation is non-destructive and non-mutative, fitting the Read category for data retrieval tools.
From the tool's definition Tool performs 'vector similarity search' which retrieves matching data from a table. Parameters include query inputs (vector_data, table_name, distance_func) and output controls (topk, output_column_name, with_distance), all typical of read-only search…
Documented attack patterns abuse exactly the kind of access oceanbase_vector_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Oceanbase, and nothing reaches the server without passing your rules. This is the rule we recommend for oceanbase_vector_search:
{
"version": "1",
"default": "deny",
"tools": {
"oceanbase_vector_search": {}
}
}oceanbase_vector_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Perform vector similarity search on an OceanBase table. Args: table_name: Name of the table to search. vector_data: Query vector. vec_column_name: column name containing vectors to search. distance_func: The index distance algorithm used when comparing the distance between two vectors. with_distance: Whether to output distance data. topk: Number of results returned. output_column_name: Returned table fields. It is categorised as a Read tool in the Mcp Oceanbase MCP Server, which means it retrieves data without modifying state.
Register the Mcp Oceanbase MCP server in PolicyLayer and add a rule for oceanbase_vector_search: 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 Oceanbase. Nothing to install.
oceanbase_vector_search 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 oceanbase_vector_search 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 oceanbase_vector_search. 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.
oceanbase_vector_search is provided by the Mcp Oceanbase MCP server (oceanbase/awesome-oceanbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 134 Mcp Oceanbase tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
134 Mcp Oceanbase tools catalogued and risk-classified — across an index of 42,500+ MCP servers.