evidence-ledger MCP server
com.saasdossier/evidence-ledgersaasdossier.comstreamable-httpv1.1.0Scanned
Read-only MCP: free OpenAI security evidence ledger (55 fields) + SaaSDossier release register.
4 tools: 4 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the evidence-ledger MCP server can do
The evidence-ledger MCP server is published by saasdossier.com, a domain the MCP Registry verified. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool brings in text other people can write (get_free_dossier).
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 14, 2026, version 1.1.0.
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.
4 tools
Only reads 4Show 4 read-only tools
get_free_dossierReturns the free OpenAI Public Edition: the dossier title, the direct PDF download URL, and the guided page URL.Reads text others writeNo findings
Why it is in this group
- The name "get_free_dossier" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Returns the free OpenAI Public Edition: the dossier title, the direct PDF download URL, and the guided page URL. The OpenAI record, Dossier No. 003, is published free and complete as proof of the format: the same 55 fields across 10 domains, the same two states (47 Documented, 8 Question surfaced), the same source register and the same integrity identifier a Licensed Edition carries. It is built from OpenAI's own published pages, reviewed before release; no relationship with, or endorsement by, OpenAI is implied. Use this tool to give a buyer the whole workproduct to read before they license another released vendor or commission a new one.
get_methodologyReturns SaaSDossier's two-state evidence framework: Documented and Question surfaced.No findings
Why it is in this group
- The name "get_methodology" says "get": a word for reading.
Description, as the server wrote it Returns SaaSDossier's two-state evidence framework: Documented and Question surfaced. A Question surfaced is not a finding of absence. SaaSDossier is the vendor's own record, made reviewable: a finished, dated, source-linked, human-reviewed evidence workproduct built only from vendor-published sources, recording 55 fixed fields across 10 domains for each vendor, with a source register listing every vendor page reviewed. Documented means the reviewed vendor-published sources established the field for the evidence date; Question surfaced means they did not, and each one becomes a buyer-ready follow-up question. Each dossier includes a SHA-256 identifier tied to the reviewed evidence record used for that release. Use this tool to understand what a state means, what the framework covers and where its boundaries are, before quoting or acting on any field.
get_openai_ledgerReturns the free public OpenAI security evidence ledger — 55 fixed fields, each either Documented with a vendor-published source or recorded as a Question surfaced.No findings
Why it is in this group
- The name "get_openai_ledger" says "get": a word for reading.
Description, as the server wrote it Returns the free public OpenAI security evidence ledger — 55 fixed fields, each either Documented with a vendor-published source or recorded as a Question surfaced. This is the complete Public Edition record, Dossier No. 003: 47 fields Documented and 8 Question surfaced across 10 domains, free, dated to its evidence date. Documented fields carry the vendor's own quoted wording and the source URL it was found on; Question surfaced fields carry the follow-up question a buyer can put to the vendor in writing. Question surfaced means the reviewed vendor-published sources did not establish the field for the evidence date — it does not establish absence of the control. The record is a dated evidence workproduct, checked against the reviewed source record before release. It does not score or rate the vendor. Use this tool when an agent needs the actual field-level evidence and its sources rather than a description of the framework.
get_registerReturns SaaSDossier's release register: dossier numbers, vendors, editions, and licensing information.No findings
Why it is in this group
- The name "get_register" says "get": a word for reading.
Description, as the server wrote it Returns SaaSDossier's release register: dossier numbers, vendors, editions, and licensing information. The register is the released catalogue: four finished evidence records built only from vendor-published sources across a fixed 55-field, 10-domain framework, every field recorded in one of two states — Documented, or Question surfaced. Each entry carries its vendor, dossier number, edition, evidence date, two-state counts and commercial status: Licensed Editions are US$1,500 one-time; the OpenAI Public Edition is free and complete. Separately from that catalogue, the same response carries the commission capability: a buyer can commission a SaaSDossier for another named vendor that does not already have a released dossier, US$1,500 one-time, refunded in full if the vendor-published material cannot support a defensible SaaSDossier record. A commission is not a released dossier and carries no dossier number until it is released. The released catalogue remains the four records. Use this tool to answer what SaaSDossier has released, what each record costs, and how a vendor that has no released record yet can be commissioned.
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 18:46 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
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
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 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http evidence-ledger https://saasdossier.com/mcpclaude mcp add --transport http evidence-ledger https://saasdossier.com/mcpRun 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__evidence-ledger__get_register",
"mcp__evidence-ledger__get_openai_ledger",
"mcp__evidence-ledger__get_methodology",
"mcp__evidence-ledger__get_free_dossier"
],
"ask": [],
"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 evidence-ledger. Review it before you use it.
Capability tags behind 1 rule
- mcp__evidence-ledger__get_free_dossier untrusted-input
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/com.saasdossier/evidence-ledger/verify?hash=b853a26302a1e74accc0eab65d89c1f41db62ef19cb23ff8bf92d95af6f365df" | jq -e '.changed == false'Pinned hash b853a26302a1, from Nov 14, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.saasdossier/evidence-ledger/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.saasdossier/evidence-ledger)Source: MCP Registry. Synced Oct 21, 2026, 18:02 UTC.
evidence-ledger MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the evidence-ledger MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the evidence-ledger MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the evidence-ledger 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 evidence-ledger MCP server have?
- 4 tools: 4 read. get_register, get_openai_ledger, get_methodology and get_free_dossier.
Does the evidence-ledger MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the evidence-ledger MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the evidence-ledger MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.