AI agents call search_medical_content to retrieve information from MedAdapt Content Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Medical content search is a retrieval operation with no side effects. It queries external medical databases (PubMed, NCBI Bookshelf) and user documents to return information. There is no indication this tool modifies, executes external code, deletes data, or handles financial transactions.
From the tool's definition Tool name 'search_medical_content' combined with sibling tools (extract_article_key_points, get_resource_content, get_topic_overview, suggest_learning_resources) all follow read-only patterns.
Documented attack patterns abuse exactly the kind of access search_medical_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MedAdapt Content Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_medical_content:
{
"version": "1",
"default": "deny",
"tools": {
"search_medical_content": {}
}
}search_medical_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search_medical_content. It is categorised as a Read tool in the MedAdapt Content Server MCP Server, which means it retrieves data without modifying state.
Register the MedAdapt Content Server MCP server in PolicyLayer and add a rule for search_medical_content: 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 MedAdapt Content Server. Nothing to install.
search_medical_content 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_medical_content 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_medical_content. 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_medical_content is provided by the MedAdapt Content Server MCP server (ryoureddy/medadapt-content-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MedAdapt Content Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 MedAdapt Content Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.