This function takes a user prompt of what they think a projection should do and then asks the LLM to build a projection in the following format.
AI agents invoke build_projection to trigger actions in KurrentDB 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.
This tool orchestrates an LLM call to generate projection code/logic. While primarily a code-generation step, it triggers an external LLM operation whose output depends on the prompt argument. It doesn't directly write to KurrentDB (that would be create_projection), but it executes an LLM-driven generation process.
From the tool's definition "asks the LLM to build a projection" — generates and constructs a projection definition based on a user prompt
Documented attack patterns abuse exactly the kind of access build_projection gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and KurrentDB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for build_projection:
{
"version": "1",
"default": "deny",
"tools": {
"build_projection": {
"limits": [
{
"counter": "build_projection_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}build_projection 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.
This function takes a user prompt of what they think a projection should do and then asks the LLM to build a projection in the following format. It is categorised as a Execute tool in the KurrentDB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the KurrentDB MCP Server MCP server in PolicyLayer and add a rule for build_projection: 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 KurrentDB MCP Server. Nothing to install.
build_projection 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 build_projection 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 build_projection. 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.
build_projection is provided by the KurrentDB MCP Server MCP server (kurrent-io/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KurrentDB MCP Server, 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.
8 KurrentDB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.