context.build
AI agents use context.build to create or update resources in Kelnix Datamind Curator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kelnix Datamind Curator environment.
Based on the tool name 'context.build' and the server's description which mentions 'build AI-ready context packages', this tool likely assembles or creates context packages from existing data. This maps to Write (creates data reversibly). However, the empty description significantly lowers confidence. It could also involve Execute-level operations if it triggers pipelines.
From the tool's definition Tool name: context.build; description is empty and uninformative.
Attacks that exploit this kind of access
context.build. It is categorised as a Write tool in the Kelnix Datamind Curator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kelnix Datamind Curator MCP server in PolicyLayer and add a rule for context.build: 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 Kelnix Datamind Curator. Nothing to install.
context.build is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the context.build 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 context.build. 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.
context.build is provided by the Kelnix Datamind Curator MCP server (kelnixsolutions/kelnix-datamind-curator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the 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 →