Low Risk

memory_search

🔍 Search memories previously saved for the current user. Run semantic search across stored context to quickly retrieve preferences, project history, or tagged notes.

Accepts freeform code/query input (query)

Part of the DataGen MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

kuoyusheng/datagendev Read Risk 2/5

AI agents call memory_search to retrieve information from DataGen 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 memory_search 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.

kuoyusheng-datagendev.yaml
tools:
  memory_search:
    rules:
      - action: allow

See the full DataGen policy for all 20 tools.

Tool Name memory_search
Category Read
MCP Server DataGen MCP Server
Risk Level Low

View all 20 tools →

Agents calling read-class tools like memory_search have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the memory_search tool do? +

🔍 Search memories previously saved for the current user. Run semantic search across stored context to quickly retrieve preferences, project history, or tagged notes.. It is categorised as a Read tool in the DataGen MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory_search? +

Add a rule in your Intercept YAML policy under the tools section for memory_search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the DataGen MCP server.

What risk level is memory_search? +

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

Can I rate-limit memory_search? +

Yes. Add a rate_limit block to the memory_search 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.

How do I block memory_search completely? +

Set action: deny in the Intercept policy for memory_search. 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 memory_search? +

memory_search is provided by the DataGen MCP server (kuoyusheng/datagendev). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on DataGen

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.