query_graph

THE RISK

High Risk

Why query_graph needs a policy

Executing arbitrary Cypher queries against a graph database is an Execute-level action. While Cypher is often used for reads, direct query execution allows arbitrary operations including writes and deletes (CREATE, MERGE, DELETE, DETACH DELETE) depending on what's permitted.

From the tool's definition "Run a direct Cypher query against the codebase graph database"

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

POLICY

How to control query_graph

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

policy.json

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

query_graph 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.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More GraphHub tools

Destructive forget Delete observations from memory. Can delete by ID, session, project, type, or date. Write remember_bugfix Record a resolved bug so future agents can reuse the fix pattern. Stores symptom, root cau Write remember_skill_choice Cache which .skill.md / SKILL.md file was used for a task so similar future tasks route to Write remember Save a learning, decision, finding, or other observation to persistent memory. Searchable Write update_observation Update an existing observation Read batch_context Get definition + caller/callee counts for multiple symbols in one call. Replaces N get_con Read changed_symbols List the symbols in files changed by the current branch (or working tree / staged diff). E Read check_arch_rules Enforce architecture boundary rules — detect files that import across forbidden layer boun

All 32 GraphHub tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in GraphHub → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about query_graph

What does the query_graph tool do? +

Run a direct Cypher query against the codebase graph database. Use this to find complex relationships. It is categorised as a Execute tool in the GraphHub MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_graph? +

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

What risk level is query_graph? +

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

Can I rate-limit query_graph? +

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

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

query_graph is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GraphHub tool call.

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

CHECK YOUR STACK →