pg_vector_embed
Generate text embeddings. Returns a simple hash-based embedding for demos (use external APIs for production).
This record as markdown: /tools/io-github-neverinfamous-postgres-mcp/pg-vector-embed.md
What pg_vector_embed does on PostgreSQL MCP Server
AI agents invoke pg_vector_embed to trigger actions in PostgreSQL MCP Server. 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.
Why pg_vector_embed is rated High
The tool executes an embedding generation process (hash-based locally or via external APIs). It doesn't merely read stored data — it performs a computation/transformation on input text, potentially calling external services. This places it in Execute rather than Read. Severity is medium since misuse could involve unintended external API calls or resource consumption, but blast radius is limited.
From the tool's definition 'Generate text embeddings' and 'use external APIs for production' indicate this tool triggers an external operation or computation process
Attacks that exploit this kind of access
The rule that runs pg_vector_embed safely
PolicyLayer is an MCP gateway: it sits between your AI agents and PostgreSQL MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pg_vector_embed, this is the rule to start with:
pg_vector_embed 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.
The button opens the PolicyLayer dashboard: create your workspace, connect PostgreSQL MCP Server, apply this rule, and every pg_vector_embed call is checked against it from then on.
Questions about pg_vector_embed
Generate text embeddings. Returns a simple hash-based embedding for demos (use external APIs for production). It is categorised as a Execute tool in the PostgreSQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PostgreSQL MCP Server MCP server in PolicyLayer and add a rule for pg_vector_embed: 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 PostgreSQL MCP Server. Nothing to install.
pg_vector_embed 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 pg_vector_embed 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 pg_vector_embed. 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.
pg_vector_embed is provided by the PostgreSQL MCP Server MCP server (@neverinfamous/postgres-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on PostgreSQL MCP Server, and thousands of servers like it.
Across the catalogue