// SCAN REPORT

0xpdf

13 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 16 Jul 2026

7 can modify or destroy data

6 read-only

13 tools total

Community server · catalogue entry checked 16/07/2026

How to control 0xpdf ↓

TOOL MAP

What 0xpdf exposes to your agents

Read (6) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous 0xpdf tools

Destructive · High reset_mcp_runtime_metrics Reset MCP runtime transport metrics counters. Execute · Medium parse_pdf_stream Parse one PDF as SSE stream through /api/v1/pdf/parse-stream. Execute · Medium parse_pdf_sync Parse one PDF synchronously through /api/v1/pdf/parse. Execute · Medium wait_for_batch_completion wait_for_batch_completion

7 of 0xpdf's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control 0xpdf

PolicyLayer is an MCP gateway — it sits between your AI agents and 0xpdf, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "reset_mcp_runtime_metrics": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "submit_parse_batch": {
    "limits": [
      {
        "counter": "submit_parse_batch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_mcp_runtime_metrics": {
    "limits": [
      {
        "counter": "get_mcp_runtime_metrics_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register 0xpdf — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON 0XPDF →

Instant setup, no code required.

FULL CATALOGUE

All 13 0xpdf tools

DESTRUCTIVE 1 tools

Destructive reset_mcp_runtime_metrics Reset MCP runtime transport metrics counters.

EXECUTE 4 tools

Execute parse_pdf_stream Parse one PDF as SSE stream through /api/v1/pdf/parse-stream. Execute parse_pdf_sync Parse one PDF synchronously through /api/v1/pdf/parse. Execute wait_for_batch_completion wait_for_batch_completion Execute wait_for_job_completion wait_for_job_completion

WRITE 2 tools

Write submit_parse_batch Submit multiple PDFs for async batch parsing via /api/v1/pdf/batch. Write submit_parse_job Submit one PDF for async processing via /api/v1/pdf/upload.

READ 6 tools

Read get_mcp_runtime_metrics Get MCP runtime transport metrics for optimization/debugging. Read get_parse_batch_status Get status for an async parse batch created by submit_parse_batch. Read get_parse_job_status Get status for an async parse job created by submit_parse_job. Read get_pricing_current Get current billing/pricing status for the authenticated user. Read health_check Health check for backend connectivity. Useful before running parse tools. Read list_schemas List user schemas from /api/v1/schemas.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about 0xpdf

Can an AI agent delete data through the 0xpdf MCP server? +

Yes. The 0xpdf server exposes 1 destructive tools including reset_mcp_runtime_metrics. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through 0xpdf? +

The 0xpdf server has 2 write tools including submit_parse_batch, submit_parse_job. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach 0xpdf.

How many tools does the 0xpdf MCP server expose? +

13 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on 0xpdf? +

Register the 0xpdf MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every 0xpdf tool call.

Deterministic rules across all 13 0xpdf tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON 0XPDF →

Instant setup, no code required.

13 0xpdf tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from 0xpdf's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →