Search memories using natural language. Returns relevant decisions, solutions, patterns, and notes.
AI agents call doclea_search to retrieve information from Doclea MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries stored architectural information without creating, modifying, deleting, or executing anything. It is a pure read operation with minimal security impact. The worst-case misuse would be unauthorized information disclosure of internal architectural decisions, which is lower severity than write or execute actions.
From the tool's definition The tool 'doclea_search' is described as searching memories using natural language and returning results (decisions, solutions, patterns, notes). The verb 'search' and 'returns' indicate read-only retrieval with no modification or side effects.
Attacks that exploit this kind of access
Search memories using natural language. Returns relevant decisions, solutions, patterns, and notes. It is categorised as a Read tool in the Doclea MCP MCP Server, which means it retrieves data without modifying state.
Register the Doclea MCP server in PolicyLayer and add a rule for doclea_search: 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 Doclea MCP. Nothing to install.
doclea_search 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 doclea_search 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 doclea_search. 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.
doclea_search is provided by the Doclea MCP server (quanticstudios/doclea-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 →