Perform semantic search across article content using vector embeddings
AI agents call semanticSearch to retrieve information from Article Manager MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Semantic search retrieves or queries data using vector embeddings without side effects. It does not create, modify, delete, or execute arbitrary operations. The worst-case misuse would be information disclosure of article content the agent is already authorized to search, which has limited blast radius.
From the tool's definition Tool performs 'semantic search across article content' with no modification capability. Belongs to a read-focused operation on the 'self-hosted file-based system' as described in server capabilities.
Attacks that exploit this kind of access
Perform semantic search across article content using vector embeddings. It is categorised as a Read tool in the Article Manager MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Article Manager MCP Server MCP server in PolicyLayer and add a rule for semanticSearch: 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 Article Manager MCP Server. Nothing to install.
semanticSearch 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 semanticSearch 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 semanticSearch. 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.
semanticSearch is provided by the Article Manager MCP Server MCP server (joelmnz/mcp-markdown-manager). 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 →