Executes an XQuery expression against a live eXist-db instance via the REST API
AI agents invoke existdb_execute_query to trigger actions in Existdb. 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.
This tool triggers external operations (XQuery execution) whose effects depend entirely on the arguments provided. XQuery can read data (Read), modify documents (Write), delete resources (Destructive), or call custom functions (Execute). Since the tool accepts arbitrary XQuery expressions and the severity of outcomes depends on what query is executed, this is classified as Execute.
From the tool's definition Tool description explicitly states 'Executes an XQuery expression against a live eXist-db instance.' XQuery is a full programming language capable of querying, modifying, and transforming data, and in eXist-db can perform arbitrary operations including data…
Documented attack patterns abuse exactly the kind of access existdb_execute_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Existdb, and nothing reaches the server without passing your rules. This is the rule we recommend for existdb_execute_query:
{
"version": "1",
"default": "deny",
"tools": {
"existdb_execute_query": {
"limits": [
{
"counter": "existdb_execute_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} existdb_execute_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.
Free to start. No card required.
Executes an XQuery expression against a live eXist-db instance via the REST API. It is categorised as a Execute tool in the Existdb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Existdb MCP server in PolicyLayer and add a rule for existdb_execute_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 Existdb. Nothing to install.
existdb_execute_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the existdb_execute_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.
Set action: deny in the PolicyLayer policy for existdb_execute_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.
existdb_execute_query is provided by the Existdb MCP server (orazionelson/existdb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Existdb, 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.
12 Existdb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.