MANDATORY: Call this tool before writing any code, proposing any pattern, or making any architectural or dependency decision.
AI agents call query_knowledge_base to retrieve information from MarkdownLM 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 information about architecture rules, security standards, and testing requirements from a persistent memory system. It has no side effects—it only reads and returns existing documentation. While it may inform subsequent decisions, the tool itself performs only data retrieval, placing it squarely in the Read category with low severity risk.
From the tool's definition Tool name 'query_knowledge_base' and description indicate querying/retrieving documented architecture rules and team standards. The word 'query' combined with 'knowledge base' clearly indicates data retrieval with no modifications.
Documented attack patterns abuse exactly the kind of access query_knowledge_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MarkdownLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_knowledge_base:
{
"version": "1",
"default": "deny",
"tools": {
"query_knowledge_base": {}
}
}query_knowledge_base 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.
MANDATORY: Call this tool before writing any code, proposing any pattern, or making any architectural or dependency decision. It is categorised as a Read tool in the MarkdownLM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MarkdownLM MCP Server MCP server in PolicyLayer and add a rule for query_knowledge_base: 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 MarkdownLM MCP Server. Nothing to install.
query_knowledge_base 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 query_knowledge_base 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 query_knowledge_base. 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.
query_knowledge_base is provided by the MarkdownLM MCP Server MCP server (markdownlm/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MarkdownLM MCP 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.
3 MarkdownLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.