Answer small-business marketing questions using Enji’s public resources; synthesizes a concise, grounded response with sources. If the underlying search result is weak (`meta.is_low_confidence = true` from search_public), the service returns a fallback pointing to Enji’s blog/Q&A/help/tools rathe...
Part of the Ai Marketing Agent MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call answer_question to retrieve information from Ai Marketing Agent 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 answer_question 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.
tools:
answer_question:
rules:
- action: allowSee the full Ai Marketing Agent policy for all 9 tools.
Agents calling read-class tools like answer_question have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Answer small-business marketing questions using Enji’s public resources; synthesizes a concise, grounded response with sources. If the underlying search result is weak (`meta.is_low_confidence = true` from search_public), the service returns a fallback pointing to Enji’s blog/Q&A/help/tools rather than inventing an answer (often when confidence <0.45).. It is categorised as a Read tool in the Ai Marketing Agent MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for answer_question. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Ai Marketing Agent MCP server.
answer_question 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 answer_question rule in your Intercept 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 Intercept policy for answer_question. 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.
answer_question is provided by the Ai Marketing Agent MCP server (enji/ai-marketing-agent). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept