Skip to content

Thales MCP server

report.thales/thalesthales.reportstreamable-httpv1.0.0Scanned

Read-only record of a transparent, AI-agent-operated simulated trading experiment.

7 tools: 1 can delete or cancel things, 5 change things and 1 only read.

Tools: 1 delete, 0 irreversible, 5 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Thales MCP server can do

The Thales MCP server is published by thales.report, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (1 tool: kill_list) and create or change data (5 tools: fleet_overview, sleeve_record, research_journal, research_note and 1 more). 1 tool only reads.

None of its tools reads private data, brings in text other people write, or sends data out.

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 19, 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.

7 tools

Deletes or cancels 1Claude Code: deny
  • kill_listEvery strategy idea this platform built, tested, and rejected — with dates, verdicts, and honest reasons.No findings

    Why it is in this group

    • The name "kill_list" says "kill": a word for removing or ending something.
    Description, as the server wrote it
    Every strategy idea this platform built, tested, and rejected — with dates, verdicts, and honest reasons. Publishing failures is the credibility mechanism.
Changes things 5Claude Code: ask
  • fleet_overviewSummary of every strategy sleeve: total and evaluation-window returns, the stocks-only return beside SPY (`invested`: the return on the money actually in stocks — account returns i…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.
    Description, as the server wrote it
    Summary of every strategy sleeve: total and evaluation-window returns, the stocks-only return beside SPY (`invested`: the return on the money actually in stocks — account returns include cash the sizer holds back), drawdown, live days, and the 20 most recent submitted orders. All series are indexed to 100 at inception (paper capital is arbitrary; only performance is published). All figures are SIMULATED paper trading.
  • research_journalThe live research journal: every internal research document (experiment pre-registrations, incident write-ups, verdicts including nulls), auto-published verbatim by the daily expor…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.
    Description, as the server wrote it
    The live research journal: every internal research document (experiment pre-registrations, incident write-ups, verdicts including nulls), auto-published verbatim by the daily export. Returns the manifest; fetch a document with research_note.
  • research_noteFull markdown text of one published research document, by slug (see research_journal for the list).1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...r the list). Verbatim internal writing; credential identifiers redacted."

      What this check looks for
    Description, as the server wrote it
    Full markdown text of one published research document, by slug (see research_journal for the list). Verbatim internal writing; credential identifiers redacted.
  • site_guideWhat Thales is, every machine-readable endpoint, and the verification standard the project holds itself to.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.
    Description, as the server wrote it
    What Thales is, every machine-readable endpoint, and the verification standard the project holds itself to.
  • sleeve_recordFull public record for one sleeve: stats, the stocks-only return vs SPY (`invested`), indexed performance curve (100 = inception), drawdown series, and the complete submitted-order…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.
    Description, as the server wrote it
    Full public record for one sleeve: stats, the stocks-only return vs SPY (`invested`), indexed performance curve (100 = inception), drawdown series, and the complete submitted-order log. All figures are SIMULATED paper trading.
Only reads 1Show 1 read-only tool
  • gate_statusThe pre-registered go-live gate: criteria frozen on 2026-07-05, current progress, and the binding interpretation (this gate tests operational competence, not alpha).No findings

    Why it is in this group

    • The name "gate_status" says "status": a word for reading.
    Description, as the server wrote it
    The pre-registered go-live gate: criteria frozen on 2026-07-05, current progress, and the binding interpretation (this gate tests operational competence, not alpha).

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 untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:18 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
6
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://thales.report/api/mcp: tools/list returned 7 tools to an anonymous client, including kill_list (destructive), fleet_overview (write), sleeve_record (write), research_journal (write), research_note (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http thales https://thales.report/api/mcp
claude mcp add --transport http thales https://thales.report/api/mcp

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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__thales__gate_status"
    ],
    "ask": [
      "mcp__thales__fleet_overview",
      "mcp__thales__sleeve_record",
      "mcp__thales__research_journal",
      "mcp__thales__research_note",
      "mcp__thales__site_guide"
    ],
    "deny": [
      "mcp__thales__kill_list"
    ]
  }
}

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 thales. Review it before you use it.

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/report.thales/thales/verify?hash=5dddaab17160c7f331444f0cbdfcfc0618b26e70413f120876a081f6c6e140c3" | jq -e '.changed == false'

Pinned hash 5dddaab17160, from Nov 19, 2026, 02:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/report.thales/thales/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for report.thales/thales
[![Anlyon Radar](https://radar.anlyon.com/badge/report.thales/thales.svg)](https://radar.anlyon.com/servers/report.thales/thales)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

Thales MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Thales MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Thales MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: kill_list.

Can the Thales 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 Thales MCP server have?

7 tools: 1 destructive, 5 write, 1 read. kill_list, fleet_overview, sleeve_record, research_journal, research_note, site_guide and gate_status.

Does the Thales MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Thales MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Thales MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.