save_research_data · Kavi Research Assistant MCP

WHAT IT DOES

What save_research_data does on Kavi Research Assistant

AI agents use save_research_data to create or update resources in Kavi Research Assistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kavi Research Assistant environment.

WHY IT NEEDS A POLICY

Why save_research_data needs a policy

This tool creates or modifies data in a vector database, fitting the Write category. Severity is medium because while the data storage is reversible (can be deleted via the sibling delete_research_topic tool), malicious use could flood the database with unwanted research content, create confusion in the knowledge base, or consume storage resources.

From the tool's definition Tool description states 'Save research content to vector database for future retrieval,' which creates new records in the database. The name 'save_research_data' and action of storing content to a database is a reversible modification operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_research_data Rate-limited

save_research_data stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_research_data": {
      "limits": [
        {
          "counter": "save_research_data_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Kavi Research Assistant, so you can run agents against it safely.

FAQ

Questions about save_research_data

What does the save_research_data tool do? +

Save research content to vector database for future retrieval. It is categorised as a Write tool in the Kavi Research Assistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_research_data? +

Register the Kavi Research Assistant MCP server in PolicyLayer and add a rule for save_research_data: 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 Kavi Research Assistant. Nothing to install.

What risk level is save_research_data? +

save_research_data is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_research_data? +

Yes. Add a rate_limit block to the save_research_data 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 save_research_data completely? +

Set action: deny in the PolicyLayer policy for save_research_data. 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 save_research_data? +

save_research_data is provided by the Kavi Research Assistant MCP server (machhakiran/kavi-research-assistant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.