resolve_problem

THE RISK

Medium Risk

Why resolve_problem needs a policy

This tool performs a reversible state change: marking a Problem as closed and recording metadata. It does not execute external code, delete data irreversibly, or move money. The modification can theoretically be undone by reopening the problem or editing the record.

From the tool's definition Tool description states it 'Marks a Problem as closed and records the resolution' — this creates/modifies a record in the knowledge graph by changing a Problem's status and storing resolution data.

Documented attack patterns abuse exactly the kind of access resolve_problem gives an agent:

POLICY

How to control resolve_problem

PolicyLayer is an MCP gateway — it sits between your AI agents and Memex, and nothing reaches the server without passing your rules. This is the rule we recommend for resolve_problem:

policy.json

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

resolve_problem 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.

Create a free account and register Memex — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Memex tools

Destructive invalidate_edge Explicitly invalidates a graph edge when it is discovered to be stale or incorrect. Return Write record_decision Creates a Decision node in the graph. Call this when making or discovering architectural c Write record_problem Creates a Problem node in the graph. Call this when discovering bugs or technical debt. Re Read explain_change Cross-references a git commit Read get_context_briefing Returns a ranked, token-capped briefing of the most important Read get_open_problems Returns currently open technical problems and TODOs sorted by severity as a Markdown strin Read get_project_context Returns a compressed briefing of the project as a Markdown string: active modules, recent Read get_recent_decisions Returns architectural and technical decisions from the past N days as a Markdown string.

All 13 Memex tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about resolve_problem

What does the resolve_problem tool do? +

Marks a Problem as closed and records the resolution. Returns a status string. It is categorised as a Write tool in the Memex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on resolve_problem? +

Register the Memex MCP server in PolicyLayer and add a rule for resolve_problem: 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 Memex. Nothing to install.

What risk level is resolve_problem? +

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

Can I rate-limit resolve_problem? +

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

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

resolve_problem is provided by the Memex MCP server (stifler7/memex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Memex tool call.

Start from Memex, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →