Search Alexandria's learnings memory for insights relevant to a query. Uses RAPTOR hierarchical search — returns a mix of specific leaf learnings, topic-cluster summaries, and cross-agent domain patterns so you get both concrete examples and high-level context. Use BEFORE starting a task to see w...
Accepts freeform code/query input (query)
Part of the Alexandria MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call alexandria_recommend_learnings to retrieve information from Alexandria 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 alexandria_recommend_learnings 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:
alexandria_recommend_learnings:
rules:
- action: allowSee the full Alexandria policy for all 20 tools.
Agents calling read-class tools like alexandria_recommend_learnings 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.
Search Alexandria's learnings memory for insights relevant to a query. Uses RAPTOR hierarchical search — returns a mix of specific leaf learnings, topic-cluster summaries, and cross-agent domain patterns so you get both concrete examples and high-level context. Use BEFORE starting a task to see what Alexandria already knows, or to find historical solutions to similar problems.. It is categorised as a Read tool in the Alexandria MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for alexandria_recommend_learnings. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Alexandria MCP server.
alexandria_recommend_learnings 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 alexandria_recommend_learnings 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 alexandria_recommend_learnings. 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.
alexandria_recommend_learnings is provided by the Alexandria MCP server (mcp-server-alexandria). 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