run_read_query · SQLite Project Memory MCP: Risk & Policy

WHAT IT DOES

What run_read_query does on SQLite Project Memory MCP

AI agents invoke run_read_query to trigger actions in SQLite Project Memory MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_read_query needs a policy

Although described as read-only, this tool executes arbitrary SQL queries supplied as arguments, placing it in the Execute category. The 'constrained' qualifier lowers severity since DDL/DML should be blocked, but the ability to run ad hoc SQL still carries meaningful risk (data exfiltration, expensive queries, potential bypass of constraints).

From the tool's definition "Run a constrained read-only SQL query" — executes arbitrary SQL against the database

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_read_query Rate-limited

run_read_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_read_query": {
      "limits": [
        {
          "counter": "run_read_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about run_read_query

What does the run_read_query tool do? +

Run a constrained read-only SQL query for diagnostics, analytics, and ad hoc retrieval. It is categorised as a Execute tool in the SQLite Project Memory MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_read_query? +

Register the SQLite Project Memory MCP server in PolicyLayer and add a rule for run_read_query: 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 SQLite Project Memory MCP. Nothing to install.

What risk level is run_read_query? +

run_read_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_read_query? +

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

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

run_read_query is provided by the SQLite Project Memory MCP server (webrtcgame/sqlite-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.