search_artifacts
AI agents call search_artifacts to retrieve information from Task Context MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries artifact data without modifying, creating, or deleting it. Full-text search is a read operation with no side effects. Severity is low because search operations cannot cause harm even if misused—they only return existing data. Confidence is high despite the empty description because the name and server context clearly indicate a retrieval function.
From the tool's definition Tool name 'search_artifacts' combined with server description stating it provides 'full-text search across historical best practices' and 'storing reusable task contexts with associated artifacts'.
Attacks that exploit this kind of access
search_artifacts. It is categorised as a Read tool in the Task Context MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Task Context MCP Server MCP server in PolicyLayer and add a rule for search_artifacts: 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 Task Context MCP Server. Nothing to install.
search_artifacts 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 search_artifacts 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 search_artifacts. 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.
search_artifacts is provided by the Task Context MCP Server MCP server (l0kifs/task-context-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 →