extract_from_content
Extract EDM artifact from text content and optional image. Returns structured data following the EDM v0.8.3 schema.
This record as markdown: /tools/deepadata-edm/extract-from-content.md
What extract_from_content does on Deepadata Edm
AI agents call extract_from_content to retrieve information from Deepadata Edm without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
save | boolean | — | Whether to save the extracted artifact to storage |
text | string | Yes | The text content to extract data from |
image | string | — | Base64-encoded image data (optional) |
metadata | object | — | Additional metadata to include in the artifact |
contentType | string | — | Type hint for the content being extracted |
Parameters from the server's own tool schema.
Why extract_from_content is rated Low
The tool performs text/image parsing and data extraction, transforming unstructured input into EDM-compliant structured output. This is fundamentally a Read operation: it queries/analyzes provided content and returns results with no side effects, no data modification, no code execution, and no irreversible changes.
From the tool's definition Tool name is 'extract_from_content' and description states it 'Extract[s] EDM artifact from text content and optional image.
Attacks that exploit this kind of access
The rule that runs extract_from_content safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Deepadata Edm, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_from_content, this is the rule to start with:
extract_from_content is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Deepadata Edm, apply this rule, and every extract_from_content call is checked against it from then on.
Questions about extract_from_content
Extract EDM artifact from text content and optional image. Returns structured data following the EDM v0.8.3 schema. It is categorised as a Read tool in the Deepadata Edm MCP Server, which means it retrieves data without modifying state.
extract_from_content accepts 5 parameters: save, text, image, metadata, contentType. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the Deepadata Edm MCP server in PolicyLayer and add a rule for extract_from_content: 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 Deepadata Edm. Nothing to install.
extract_from_content 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 extract_from_content 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 extract_from_content. 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.
extract_from_content is provided by the Deepadata Edm MCP server (deepadata-edm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deepadata Edm, and thousands of servers like it.
This server
Across the catalogue