AI agents invoke build_query to trigger actions in Tree Sitter. 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.
Although the description is empty (lowering confidence slightly), the tool name and server context suggest this constructs and likely executes queries against code. Query execution on arbitrary codebases is an Execute action—the effects depend on what query is built. It's not Read alone because query building often precedes execution.
From the tool's definition Tool named 'build_query' with empty description on a code analysis server (tree-sitter). Sibling tools include 'adapt_query' and 'analyze_project', suggesting query construction and execution capabilities.
Documented attack patterns abuse exactly the kind of access build_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tree Sitter, and nothing reaches the server without passing your rules. This is the rule we recommend for build_query:
{
"version": "1",
"default": "deny",
"tools": {
"build_query": {
"limits": [
{
"counter": "build_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}build_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.
build_query. It is categorised as a Execute tool in the Tree Sitter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tree Sitter MCP server in PolicyLayer and add a rule for build_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 Tree Sitter. Nothing to install.
build_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 build_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 build_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.
build_query is provided by the Tree Sitter MCP server (wrale/mcp-server-tree-sitter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 26 Tree Sitter tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
26 Tree Sitter tools catalogued and risk-classified — across an index of 42,500+ MCP servers.