Low Risk

execute_cql_search

Execute a CQL query on Confluence to search pages

How to control execute_cql_search ↓

What execute_cql_search does on Confluence Communication Server

AI agents call execute_cql_search to retrieve information from Confluence Communication Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why execute_cql_search needs a policy

Despite the word 'execute' in the name, the tool performs a read-only search query against Confluence. CQL (Confluence Query Language) is a search/filter language analogous to SQL SELECT, not a data modification mechanism. The server description also frames the server's purpose as 'querying and retrieving content'. No write, delete, or destructive side effects are indicated.

From the tool's definition 'Execute a CQL query on Confluence to search pages' — the tool searches and retrieves pages using CQL (Confluence Query Language); no mutation described.

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

How to control execute_cql_search

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_cql_search": {}
  }
}

execute_cql_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Confluence Communication Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about execute_cql_search

What does the execute_cql_search tool do? +

Execute a CQL query on Confluence to search pages. It is categorised as a Read tool in the Confluence Communication Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on execute_cql_search? +

Register the Confluence Communication Server MCP server in PolicyLayer and add a rule for execute_cql_search: 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 Confluence Communication Server. Nothing to install.

What risk level is execute_cql_search? +

execute_cql_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit execute_cql_search? +

Yes. Add a rate_limit block to the execute_cql_search 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_cql_search completely? +

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

execute_cql_search is provided by the Confluence Communication Server MCP server (ks-gen-ai/confluence-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 Confluence Communication Server tool call.

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

Free to start. No card required.

3 Confluence Communication Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.