neon_execute_sql

Execute a SQL query against a Neon database endpoint.

Server UnClick @unclick/mcp-server
Category Execute
Risk class High
Parameters 65 required

What neon_execute_sql does on UnClick

AI agents invoke neon_execute_sql to trigger actions in UnClick. 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.

ParameterTypeRequiredDescription
query string Yes SQL query to execute
api_key string
branch_id string Yes
project_id string Yes
endpoint_id string Yes
database_name string Yes Target database name

Parameters from the server's own tool schema.

Why neon_execute_sql needs a policy

This tool permits execution of SQL commands against a live database. While the description does not explicitly mention destructive capabilities (DELETE, DROP, etc.), SQL execution inherently includes the ability to perform reads, writes, and destructive operations depending on the query passed by the agent. The most severe potential use case governs classification.

From the tool's definition Tool name 'neon_execute_sql' and description 'Execute a SQL query against a Neon database endpoint' explicitly indicate execution of arbitrary SQL queries against a live database.

Risk signalsAccepts freeform code/query input (query) · Handles credentials or secrets (api_key)

Questions about neon_execute_sql

What does the neon_execute_sql tool do? +

Execute a SQL query against a Neon database endpoint. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does neon_execute_sql accept? +

neon_execute_sql accepts 6 parameters: query, api_key, branch_id, project_id, endpoint_id, database_name. Required: query, branch_id, project_id, endpoint_id, database_name. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on neon_execute_sql? +

Register the UnClick MCP server in PolicyLayer and add a rule for neon_execute_sql: 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 UnClick. Nothing to install.

What risk level is neon_execute_sql? +

neon_execute_sql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit neon_execute_sql? +

Yes. Add a rate_limit block to the neon_execute_sql 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.

How do I block neon_execute_sql completely? +

Set action: deny in the PolicyLayer policy for neon_execute_sql. 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.

What MCP server provides neon_execute_sql? +

neon_execute_sql is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.