K-means clustering for vector data (requires implementation)
AI agents invoke vector_cluster to trigger actions in Postgres Mcp Legacy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
K-means clustering involves executing a potentially expensive computational operation over database vector data. It doesn't clearly delete or modify data (so not Destructive/Write), nor does it simply retrieve static data (the algorithm executes iteratively). However, the description notes '(requires implementation)', meaning the tool is incomplete/stub-like, which significantly lowers confidence.
From the tool's definition 'K-means clustering for vector data' — runs a computational clustering algorithm against vector data in the database
Documented attack patterns abuse exactly the kind of access vector_cluster gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Postgres Mcp Legacy, and nothing reaches the server without passing your rules. This is the rule we recommend for vector_cluster:
{
"version": "1",
"default": "deny",
"tools": {
"vector_cluster": {
"limits": [
{
"counter": "vector_cluster_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}vector_cluster stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
K-means clustering for vector data (requires implementation). It is categorised as a Execute tool in the Postgres Mcp Legacy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Postgres Mcp Legacy MCP server in PolicyLayer and add a rule for vector_cluster: 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 Postgres Mcp Legacy. Nothing to install.
vector_cluster is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vector_cluster 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 vector_cluster. 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.
vector_cluster is provided by the Postgres Mcp Legacy MCP server (neverinfamous/postgres-mcp-legacy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Postgres Mcp Legacy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
60 Postgres Mcp Legacy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.