bol-ai MCP server
io.github.peter-schout/bol-aipeter-schoutstreamable-httpv1.0.0Scanned
Extract structured data from Bills of Lading: parties, ports, containers, incoterms. EU-hosted.
8 tools: 4 change things and 4 only read.
- Reads private data · 3
- Reads text others write · 2
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
4 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.
What the bol-ai MCP server can do
The bol-ai MCP server is published by the GitHub account peter-schout. It has 8 tools. It can create or change data (4 tools: extract_bol, extract_batch, save_corrections and export_documents), but cannot delete data. 4 tools only read.
3 tools read private data (list_documents, get_document and get_related_documents); 2 tools bring in text other people can write (extract_bol and extract_batch); 2 tools can send data out of your system (extract_bol and extract_batch). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 4Claude Code: ask
export_documentsExport completed extractions as TMS/ERP-ready normalized line rows (one row per container / invoice line / package / goods line), newest first.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Export completed extractions as TMS/ERP-ready normalized line rows (one row per container / invoice line / package / goods line), newest first. Optional doc_type filter and max_rows cap. Corrected data wins over the original extraction. For CSV/XLSX files use GET /api/bol/export on the REST API.
Annotations the server declares
- readOnlyHint: true
extract_batchExtract up to 10 freight documents in one call.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract up to 10 freight documents in one call. Provide an array of fetchable URLs; each document is processed and billed independently, and the response reports a per-document outcome so partial success (e.g. running out of credits mid-batch) is explicit.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
extract_bolExtract structured data from a freight document (PDF, PNG or JPG, max 10 MB): Bill of Lading, commercial invoice, packing list, or CMR road waybill.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract structured data from a freight document (PDF, PNG or JPG, max 10 MB): Bill of Lading, commercial invoice, packing list, or CMR road waybill. The document type is detected automatically and returned as `doc_type`. Provide either a fetchable `url` or `base64` file content. Fields not present in the document are null — never guessed. Each successful extraction bills one document.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
save_correctionsSave corrected field values for an extracted document.No findings
Why it is in this group
- The name "save_corrections" says "save": a word for a change.
Description, as the server wrote it Save corrected field values for an extracted document. The original extraction is kept alongside the corrections; corrected data takes precedence in get_document, exports and reconciliation. Pass the complete corrected fields object (same shape as returned by get_document).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
Only reads 4Show 4 read-only tools
get_documentGet the extraction result for a document by id: doc_type, extracted fields, user corrections (when present), and deterministic verification warnings (ISO 6346 container check digit…Reads private dataNo findings
Why it is in this group
- The name "get_document" says "get": a word for reading.
What it can reach
- private-dataThe name "get_document" says "get" and "document": it reads documents.
- private-dataThe description's first sentence says "get" and "document": it reads documents.
Description, as the server wrote it Get the extraction result for a document by id: doc_type, extracted fields, user corrections (when present), and deterministic verification warnings (ISO 6346 container check digits, plausibility flags). `fields` is the best available data (corrections win); `original_fields` and `corrected_fields` show both sides.
Annotations the server declares
- readOnlyHint: true
get_usageCheck this account's remaining prepaid credits and subscription status.No findings
Why it is in this group
- The name "get_usage" says "get": a word for reading.
Description, as the server wrote it Check this account's remaining prepaid credits and subscription status. Call this before large batches to avoid running out of credits mid-workflow. When the account cannot bill more documents, a human can top up at the returned buy_credits_url.
Annotations the server declares
- readOnlyHint: true
list_documentsList the 100 most recent documents for this account with id, filename, status (pending/done/failed), doc_type and primary reference number.Reads private dataNo findings
Why it is in this group
- The name "list_documents" says "list": a word for reading.
What it can reach
- private-dataThe name "list_documents" says "list" and "document": it reads documents.
- private-dataThe description's first sentence says "list" and "document": it reads documents.
Description, as the server wrote it List the 100 most recent documents for this account with id, filename, status (pending/done/failed), doc_type and primary reference number.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
12 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__bol-ai__extract_batch",
"mcp__bol-ai__extract_bol"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:09 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://bol.ai/.well-known/oauth-protected-resource/api/mcp
- Authorization servers
- https://bol.ai
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://bol.ai/api/mcp: tools/list returned 8 tools to an anonymous client, including extract_bol (write), extract_batch (write), save_corrections (write), export_documents (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http bol-ai https://bol.ai/api/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http bol-ai https://bol.ai/api/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__bol-ai__list_documents",
"mcp__bol-ai__get_document",
"mcp__bol-ai__get_related_documents",
"mcp__bol-ai__get_usage"
],
"ask": [
"mcp__bol-ai__extract_bol",
"mcp__bol-ai__extract_batch",
"mcp__bol-ai__save_corrections",
"mcp__bol-ai__export_documents"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as bol-ai. Review it before you use it.
Capability tags behind 5 rules
- mcp__bol-ai__extract_bol untrusted-input, outbound
- mcp__bol-ai__extract_batch untrusted-input, outbound
- mcp__bol-ai__list_documents private-data
- mcp__bol-ai__get_document private-data
- mcp__bol-ai__get_related_documents private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.peter-schout/bol-ai/verify?hash=a6e447925f857f6829d6ac1511e15ae18e3bcdcae745a9515f06b664155f7cf1" | jq -e '.changed == false'Pinned hash a6e447925f85, from Nov 21, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.peter-schout/bol-ai/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.peter-schout/bol-ai)Source: MCP Registry. Synced Oct 21, 2026, 18:43 UTC.
bol-ai MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the bol-ai MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the bol-ai MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the bol-ai MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the bol-ai MCP server have?
- 8 tools: 4 write, 4 read. extract_bol, extract_batch, save_corrections, export_documents, list_documents, get_document, get_related_documents and get_usage.
Does the bol-ai MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the bol-ai MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract_bol and extract_batch.
Has the bol-ai MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.