Filter JSON data using a shape object to extract only the fields you want. Provide filePath (local file or HTTP/HTTPS URL) and shape parameters.
AI agents call json_filter to retrieve information from JSON Filter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and filters JSON data from local files or remote URLs. It only retrieves/extracts data without modifying it. Severity is medium because it can access arbitrary local file paths or remote URLs, which could expose sensitive data if misused by an AI agent.
From the tool's definition Filter JSON data...to extract only the fields you want. Provide filePath (local file or HTTP/HTTPS URL) and shape parameters.
Documented attack patterns abuse exactly the kind of access json_filter gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and JSON Filter MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for json_filter:
{
"version": "1",
"default": "deny",
"tools": {
"json_filter": {}
}
}json_filter is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Filter JSON data using a shape object to extract only the fields you want. Provide filePath (local file or HTTP/HTTPS URL) and shape parameters. It is categorised as a Read tool in the JSON Filter MCP MCP Server, which means it retrieves data without modifying state.
Register the JSON Filter MCP server in PolicyLayer and add a rule for json_filter: 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 JSON Filter MCP. Nothing to install.
json_filter is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the json_filter 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 json_filter. 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.
json_filter is provided by the JSON Filter MCP server (kehvinbehvin/json-mcp-filter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from JSON Filter MCP, 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 JSON Filter MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.