Low Risk

query_knowledge_base

Use this when the user needs to find information from their organization's private knowledge repository. Performs semantic search across company documents, wikis, policies, meeting notes, and uploaded files. Returns the most relevant matches with similarity scores. Perfect for questions like "Wha...

Risk signalsAccepts freeform code/query input (query)

Part of the Athenic server.

query_knowledge_base is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE ATHENIC →

Free to start. No card required.

AI agents call query_knowledge_base to retrieve information from Athenic without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though query_knowledge_base only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_knowledge_base": {}
  }
}

See the full Athenic policy for all 5 tools.

Get this rule live on your own Athenic server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY ATHENIC →

These attack patterns abuse exactly the kind of access query_knowledge_base gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so query_knowledge_base only ever does what you allow.

SECURE ATHENIC →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the query_knowledge_base tool do? +

Use this when the user needs to find information from their organization's private knowledge repository. Performs semantic search across company documents, wikis, policies, meeting notes, and uploaded files. Returns the most relevant matches with similarity scores. Perfect for questions like "What's our remote work policy?", "Find product specifications for X", or "Search meeting notes about the Q4 strategy".. It is categorised as a Read tool in the Athenic MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on query_knowledge_base? +

Register the Athenic 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 Athenic. Nothing to install.

What risk level is query_knowledge_base? +

query_knowledge_base is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit query_knowledge_base? +

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.

How do I block query_knowledge_base completely? +

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.

What MCP server provides query_knowledge_base? +

query_knowledge_base is provided by the Athenic MCP server (maxbeech/athenic). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Athenic tool call.

Deterministic rules across all 5 Athenic tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.