Asset Aware

63 tools. 20 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

20 can modify or destroy data
43 read-only
63 tools total

Community server · catalogue entry verified 03/07/2026

How to control Asset Aware ↓

What Asset Aware exposes to your agents

Read (43) Write / Execute (17) Destructive / Financial (2)
Critical Risk

The most dangerous Asset Aware tools

20 of Asset Aware's 63 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Asset Aware

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

Deny destructive operations
{
  "delete_document": {
    "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
{
  "convert_document": {
    "limits": [
      {
        "counter": "convert_document_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "citation_bundle": {
    "limits": [
      {
        "counter": "citation_bundle_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Asset Aware — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ASSET AWARE →

Instant setup, no code required.

All 63 Asset Aware tools

READ 43 tools
Read citation_bundle citation_bundle Read consult_knowledge_graph consult_knowledge_graph Read detect_etl_profile Auto-detect a suitable built-in ETL profile from a PDF or text sample. Read discover_sources discover_sources Read document Consolidated PDF document entrypoint. Read document_asset Consolidated document asset and section entrypoint. Read docx Consolidated DOCX/DFM entrypoint. Read docx_chart_data docx_chart_data Read docx_table Consolidated DOCX table bridge entrypoint. Read docx_table_from_context docx_table_from_context Read docx_table_to_context docx_table_to_context Read docx_validate_roundtrip docx_validate_roundtrip Read etl_profile Consolidated ETL profile entrypoint. Read evidence Consolidated citation evidence entrypoint. Read export_document_segmentation 匯出整合 manifest、blocks、assets、reading order 的 segmentation schema。 Read fetch_document_asset fetch_document_asset Read find_evidence_spans Search citation-ready evidence spans with exact locator metadata. Read get_current_etl_profile Get the currently active ETL profile used for document ingestion. Read get_docx_content 取得 docx 文件的可編輯 DFM 內容。 Read get_etl_profile Get detailed configuration of a specific ETL profile. Read get_job_status get_job_status Read get_section_blocks get_section_blocks Read get_section_content 📖 Section-level 快取:直接讀取特定章節內容。 Read get_section_detail get_section_detail Read inspect_document_manifest inspect_document_manifest Read job Consolidated job entrypoint over get/list/cancel. Read knowledge Consolidated knowledge-graph entrypoint. Read list_documents List all processed documents with summaries. Read list_docx_blocks 列出 docx 文件中所有區塊的摘要。 Read list_docx_documents 列出所有已攝入的 DOCX/DFM 文件。 Read list_etl_profiles list_etl_profiles Read list_jobs List ETL jobs. Read list_section_tree list_section_tree Read load_etl_profile_from_json load_etl_profile_from_json Read search_sections search_sections Read search_source_location 搜尋文件中的來源位置(頁碼 + bbox)。 Read section Consolidated section navigation entrypoint. Read table_cite table_cite Read table_data table_data Read table_draft table_draft Read table_history table_history Read verify_citation_ref Verify a span-level AssetRef against the persisted citation index. Read visualize_document_layout 產生 PDF page overlay,直接檢查 block bbox、類型與 reading order。

Related servers

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

Questions about Asset Aware

Can an AI agent delete data through the Asset Aware MCP server? +

Yes. The Asset Aware server exposes 2 destructive tools including delete_document, delete_docx. 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 Asset Aware? +

The Asset Aware server has 14 write tools including convert_document, convert_docx_to_doc, convert_docx_to_odt. 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 Asset Aware.

How many tools does the Asset Aware MCP server expose? +

63 tools across 4 categories: Destructive, Execute, Read, Write. 43 are read-only. 20 can modify, create, or delete data.

How do I enforce a policy on Asset Aware? +

Register the Asset Aware 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 Asset Aware tool call.

Deterministic rules across all 63 Asset Aware tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

63 Asset Aware tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.