Agent Data Tools: Documents to text
io.github.Nutshell2000/agent-data-tools-documents
MCP Bill of Materials
A machine-readable inventory of what this server exposes and depends on: tools with their effects, transports, packages, findings and provenance (schema version 1.0). Third-party text in it is escaped. Also available from the REST API at /api/v1/servers/5e340e33-1050-42d8-a36d-cc3bdb49aebe/mcbom.
MCP Bill of Materials
root{21}
schema_version: "1.0"
bom_format: "squatch-mcbom"
generator{3}
name: "squatch-mcp"
classifier_version: "rules_v1@2026-10-11.1"
unicode_version: "18.0.0"
server{7}
name: "io.github.Nutshell2000/agent-data-tools-documents"
title: "Agent Data Tools: Documents to text"
description: "5 tools: PDF, Word, Excel, PowerPoint and web pages to Markdown; invoice fields as JSON."
version: "1.195.0"
homepage_url: "https://agent-data-tools.revmesh2074.workers.dev/"
source: "official_registry"
upstream_status: "active"
publisher{4}
namespace: "io.github.Nutshell2000"
display_name: "io.github.Nutshell2000"
type: "registry_namespace"
status: "unclaimed"
organization: null
repository{5}
url: "https://github.com/Nutshell2000/agent-data-tools"
provider: "github"
owner: "Nutshell2000"
name: "agent-data-tools"
verified: false
packages[0]
transports[1]
0{5}
kind: "remote"
type: "streamable-http"
endpoint_url: "https://agent-data-tools.revmesh2074.workers.dev/mcp/documents"
endpoint_host: "agent-data-tools.revmesh2074.workers.dev"
auth_type: "none"
auth{3}
type: "none"
authorization_servers[0]
scopes[0]
protocol{4}
era: "legacy"
negotiated_version: "2025-11-25"
supported_versions[0]
transport_type: "streamable-http"
tools[5]
0{9}
name: "document_extract"
title: "Extract data from a document: invoice, receipt, contract fields as JSON"
effect: "READ"
effect_confidence: 0.888
capabilities[3]
0{2}
capability: "EXTERNAL_COMMUNICATION"
confidence: 0.76
1{2}
capability: "FILE_ACCESS"
confidence: 0.765
2{2}
capability: "PAYMENT"
confidence: 0.718
risk_severity: "LOW"
fingerprint: "7baa222e2a9b71d3305a2ada31d4ae35995ef85e63ab1a00aa30d78d7734136b"
input_schema_fingerprint: "d6ae4d203ff546ad4b47062da9271b96e3d660fe866721c73efc104adc8aca75"
annotations{5}
title: "Extract data from a document: invoice, receipt, contract fields as JSON"
readOnlyHint: true
destructiveHint: false
idempotentHint: false
openWorldHint: true
1{9}
name: "document_text"
title: "Document to text: Word, Excel, PowerPoint, PDF"
effect: "READ"
effect_confidence: 0.682
capabilities[2]
0{2}
capability: "EXTERNAL_COMMUNICATION"
confidence: 0.661
1{2}
capability: "FILE_ACCESS"
confidence: 0.724
risk_severity: "INFO"
fingerprint: "78c83f31a2909e5d35a839c40d19121a13cf2b594aedcd6343678bf190327456"
input_schema_fingerprint: "40f6793e9050ddbe3b323fb70fb35c5f015d16a1d06af3ffa3f95828daac1fcb"
annotations{5}
title: "Document to text: Word, Excel, PowerPoint, PDF"
readOnlyHint: true
destructiveHint: false
idempotentHint: false
openWorldHint: true
2{9}
name: "extract"
title: "Scrape website page to Markdown: page URL into clean Markdown or text for LLMs"
effect: "READ"
effect_confidence: 0.933
capabilities[1]
0{2}
capability: "EXTERNAL_COMMUNICATION"
confidence: 0.91
risk_severity: "INFO"
fingerprint: "dd3e268996179ab11b06e0fcfc8ff177bb8e225da2dfaae40b6c506bb8a21e7d"
input_schema_fingerprint: "bd48adc3aa058a282290b2b8626b758e8a60312aed248f9a69cd5e370b8523a5"
annotations{5}
title: "Scrape website page to Markdown: page URL into clean Markdown or text for LLMs"
readOnlyHint: true
destructiveHint: false
idempotentHint: false
openWorldHint: true
3{9}
name: "extract_rendered"
title: "Web page to Markdown, rendered: a JavaScript-rendered page as text or Markdown"
effect: "READ"
effect_confidence: 0.798
capabilities[1]
0{2}
capability: "EXTERNAL_COMMUNICATION"
confidence: 0.53
risk_severity: "INFO"
fingerprint: "ed5631b32be8a11453400450f25739090677e07e1ded80db1bb4e1596b2d896b"
input_schema_fingerprint: "6aa4f30b0272ccb44d47e3b8aa5a8411f7aac9b6baf11950b60afc1d0063cec7"
annotations{5}
title: "Web page to Markdown, rendered: a JavaScript-rendered page as text or Markdown"
readOnlyHint: true
destructiveHint: false
idempotentHint: false
openWorldHint: true
4{9}
name: "pdf_text"
title: "PDF to text, PDF text extraction: extract the text of a PDF document from a URL, page by page"
effect: "READ"
effect_confidence: 0.626
capabilities[1]
0{2}
capability: "EXTERNAL_COMMUNICATION"
confidence: 0.844
risk_severity: "INFO"
fingerprint: "aa610b66050af0f22e206d654b3606aa04928f6db3860397d629f1935cd44d42"
input_schema_fingerprint: "3a229a7639881c20340994e59e1e8ce07fe1e1a16ff13583dc8ccc971b529d7a"
annotations{5}
title: "PDF to text, PDF text extraction: extract the text of a PDF document from a URL, page by page"
readOnlyHint: true
destructiveHint: false
idempotentHint: false
openWorldHint: true
resources[0]
prompts[0]
extensions[0]
data{6}
privacy_completeness: "not_provided"
data_categories[0]
ai_training: null
retention_policy: null
processing_regions[0]
subprocessors[0]
external_integrations[1]
0{3}
host: "agent-data-tools.revmesh2074.workers.dev"
registrable_domain: "revmesh2074.workers.dev"
source: "transport"
findings[3]
0{6}
check_id: "SQ-SERVER-INSTRUCTIONS-INJECTION"
category: "prompt_injection"
severity: "HIGH"
title: "Server instructions contain directives to the AI model"
subject_type: "server"
subject_name: null
1{6}
check_id: "SQ-TOOL-EXFIL-DESTINATION"
category: "prompt_injection"
severity: "HIGH"
title: "External data-collection destination in model-facing text"
subject_type: "tool"
subject_name: "document_text"
2{6}
check_id: "SQ-TOOL-EXFIL-DIRECTIVE"
category: "prompt_injection"
severity: "HIGH"
title: "Asks the AI model to pass conversation data or secrets"
subject_type: "tool"
subject_name: "document_text"
trust{9}
registry_namespace: "verified_upstream"
publisher_identity: "unverified"
organization: "unverified"
domain: "unverified"
repository: "unverified"
source_provenance: "partial"
security_scan: "findings_detected"
privacy_transparency: "not_provided"
monitoring: "active"
provenance{4}
registry_name: "io.github.Nutshell2000/agent-data-tools-documents"
registry_content_sha256: "c657d9d3c19794540af694af30d385974f67ff501bca245aadf3204384691bc6"
scan_snapshot_fingerprint: "6e9d4212958e8381e6c5a19c9d0495224b95f2f19db5ebb974c3e32c11224ddd"
scanner_version: "1.0.0"
timestamps{4}
generated_at: "2026-11-15T02:09:32.158Z"
observed_at: "2026-11-15T00:18:50.682+00:00"
registry_published_at: "2026-11-14T21:50:51.784871+00:00"
registry_updated_at: null