jq
Processes and transforms JSON using jq expressions. Accepts JSON from a file path or inline string. Returns the transformed result.
This record as markdown: /tools/io-github-dave-london-github/jq.md
What jq does on Github
AI agents invoke jq to trigger actions in Github. 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.
Why jq is rated High
This tool runs jq expressions, which are a Turing-complete filter/transformation language. While jq is typically read-only in nature (it doesn't modify files by default), it executes arbitrary code-like expressions and could be used to process sensitive data or, with certain jq flags, write output to files. The execution of arbitrary expressions elevates this beyond a simple Read tool.
From the tool's definition 'Processes and transforms JSON using jq expressions' — executes arbitrary jq filter expressions against JSON data
Attacks that exploit this kind of access
The rule that runs jq safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For jq, this is the rule to start with:
jq 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every jq call is checked against it from then on.
Questions about jq
Processes and transforms JSON using jq expressions. Accepts JSON from a file path or inline string. Returns the transformed result. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Github MCP server in PolicyLayer and add a rule for jq: 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 Github. Nothing to install.
jq 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 jq 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 jq. 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.
jq is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
Across the catalogue