blawx_get_model_part
AI agents call blawx_get_model_part to retrieve information from Blawx MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves model attributes and ontology information from the Blawx API without modifying state. No sibling tools suggest this performs modifications (update/delete operations are separate). The 'get' prefix is characteristic of Read operations.
From the tool's definition Tool name 'blawx_get_model_part' uses the verb 'get', which indicates retrieval of data. The server description mentions 'browse project content and drill down into model attributes', consistent with read-only discovery operations.
Attacks that exploit this kind of access
blawx_get_model_part. It is categorised as a Read tool in the Blawx MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Blawx MCP Server MCP server in PolicyLayer and add a rule for blawx_get_model_part: 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 Blawx MCP Server. Nothing to install.
blawx_get_model_part is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the blawx_get_model_part 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 blawx_get_model_part. 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.
blawx_get_model_part is provided by the Blawx MCP Server MCP server (lexpedite/blawx_mcp). 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 →