AI agents call file_parse to retrieve information from Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
format | string | — | Input format (default: auto-detect) |
content | string | Yes | File content (raw text or base64 with encoding param) |
options | object | — | |
encoding | string | — | Content encoding (default: utf-8) |
filename | string | — | Filename for format detection (optional) |
Parameters from the server's own tool schema.
The tool only reads and parses file content into structured JSON. It performs no writes, deletions, or external operations — it is purely a data extraction/transformation read operation with no side effects.
From the tool's definition Parse CSV/TSV/JSON/XML file content to structured JSON. Auto-detects format and column types. Returns columns, data rows, and preview.
Risk signalsAccepts file system path (filename) · Accepts raw HTML/template content (content)
Attacks that exploit this kind of access
Parse CSV/TSV/JSON/XML file content to structured JSON. Auto-detects format and column types. Returns columns, data rows, and preview. It is categorised as a Read tool in the Tools MCP Server, which means it retrieves data without modifying state.
file_parse accepts 5 parameters: format, content, options, encoding, filename. Required: content. The full parameter table on this page comes from the server's own tool schema.
Register the Tools MCP server in PolicyLayer and add a rule for file_parse: 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 Tools. Nothing to install.
file_parse 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 file_parse 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 file_parse. 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.
file_parse is provided by the Tools MCP server (https://www.jiebang.site/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →