execute_jql

THE RISK

High Risk

Why execute_jql needs a policy

JQL query execution is an Execute-category action because it runs queries against a database-like system that could have side effects depending on how results are used downstream, or if JQL features permit state modification. While JQL itself is primarily a read operation for querying tickets, the 'execute' verb and the capability to run arbitrary complex queries justifies Execute classification.

From the tool's definition Tool executes JQL (Jira Query Language) queries against the Jira API search endpoint. JQL is a powerful query language that can retrieve, filter, and potentially be chained with other operations.

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

POLICY

How to control execute_jql

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

policy.json

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

execute_jql 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 Jira MCP Server — 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 Jira MCP Server tools

Destructive delete_ticket Delete a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}. Do not use markdown i Write add_attachment_from_confluence Add an attachment to a ticket on Jira from a Confluence page by its name on the api /rest/ Write add_attachment_from_public_url Add an attachment from a public url to a ticket on Jira on the api /rest/api/3/issue/{issu Write assign_ticket Assign a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}/assignee. Do not use m Write create_ticket Create a ticket on Jira on the api /rest/api/3/issue. Do not use markdown in any field. Write edit_ticket Edit a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}. Do not use markdown in Read get_all_statuses Get all the status on Jira on the api /rest/api/3/status. Do not use markdown in your quer Read get_only_ticket_name_and_description Get the name and description of the requested tickets on the api /rest/api/3/search/jql. D

All 11 Jira MCP Server 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 Jira MCP Server → 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 execute_jql

What does the execute_jql tool do? +

Execute a JQL query on Jira on the api /rest/api/3/search/jql. Do not use markdown in your query. It is categorised as a Execute tool in the Jira MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_jql? +

Register the Jira MCP Server MCP server in PolicyLayer and add a rule for execute_jql: 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 Jira MCP Server. Nothing to install.

What risk level is execute_jql? +

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

Can I rate-limit execute_jql? +

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

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

execute_jql is provided by the Jira MCP Server MCP server (ks-gen-ai/jira-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Jira MCP Server tool call.

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

CHECK YOUR STACK →