Low Risk

extract_tables

Extract tables from any supported document format as structured JSON. Handles PDF tables, HTML tables, CSV-like structures in text. Returns clean tabular data perfect for agent analysis and processing.

Risk signalsAccepts file system path (file_path) · Accepts raw HTML/template content (content)

Part of the Document Parser server.

extract_tables is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE DOCUMENT PARSER →

Free to start. No card required.

AI agents call extract_tables to retrieve information from Document Parser without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though extract_tables only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "extract_tables": {}
  }
}

See the full Document Parser policy for all 5 tools.

Get this rule live on your own Document Parser server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY DOCUMENT PARSER →

These attack patterns abuse exactly the kind of access extract_tables gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so extract_tables only ever does what you allow.

SECURE DOCUMENT PARSER →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the extract_tables tool do? +

Extract tables from any supported document format as structured JSON. Handles PDF tables, HTML tables, CSV-like structures in text. Returns clean tabular data perfect for agent analysis and processing.. It is categorised as a Read tool in the Document Parser MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on extract_tables? +

Register the Document Parser MCP server in PolicyLayer and add a rule for extract_tables: 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 Document Parser. Nothing to install.

What risk level is extract_tables? +

extract_tables is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit extract_tables? +

Yes. Add a rate_limit block to the extract_tables 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.

How do I block extract_tables completely? +

Set action: deny in the PolicyLayer policy for extract_tables. 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.

What MCP server provides extract_tables? +

extract_tables is provided by the Document Parser MCP server (@agenson-horrowitz/document-parser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Document Parser tool call.

Deterministic rules across all 5 Document Parser tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.