Skip to content

Backtester MCP server

io.github.morshedgit/backtestermorshedgitstreamable-httpv1.0.0Scanned

Test a plain-words trading rule on historical prices and compare the trades with SPY. Not advice.

9 tools: 1 can delete or cancel things, 5 change things and 3 only read.

Tools: 1 delete, 0 irreversible, 5 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 3
  • 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 Backtester MCP server can do

The Backtester MCP server is published by the GitHub account morshedgit. It has 9 tools. It can delete or cancel things (1 tool: save_strategy) and create or change data (5 tools: build_series, build_signal, simulate, report and 1 more). 3 tools only read.

3 tools bring in text other people can write (share_report, list_strategies and save_strategy).

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

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 8, 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.

9 tools

Deletes or cancels 1Claude Code: deny
  • save_strategyPublish a completed report to the public website after the user asks to save it.Reads text others writeNo findings

    Why it is in this group

    • The name "save_strategy" says "save": a word for a change.
    • The description's first verb is "publish": a word for a change that another call does not undo.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Publish a completed report to the public website after the user asks to save it. Use the reportId returned by report, a public slug, and client-authored page and presentation choices. Never submit or invent result numbers. Adds it to the strategy directory without rerunning the strategy. Existing slugs require expectedKey to replace a different result. setAsHome changes the home page only when explicitly requested.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
Changes things 5Claude Code: ask
  • build_seriesBuild named time series from a run form.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
    Build named time series from a run form. Needs version, data, and series.

    Annotations the server declares

    • readOnlyHint: true
  • build_signalBuild named trading signals from a run form.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
    Build named trading signals from a run form. Needs version, data, series, and signals.

    Annotations the server declares

    • readOnlyHint: true
  • reportRun a backtest and show its results.1 finding

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "report" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The description's first verb is "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Run a backtest and show its results. Supply strategyExplanation in plain terms for the widget. In your reply, explain the rule, always show Return vs. SPY (summary.returnVsSpyPct in percentage points, or Unavailable), and give one takeaway or limit supported by the report. Choose any additional cards using stats. Use scoreSeries for a separate score panel. Use chartSeries to select named report series and set their legend labels, line or bar types, colors, and line patterns. Keep the interpretation about this historical test. To publish this exact result later, pass its reportId to save_strategy after the user asks to save it to the website.

    Annotations the server declares

    • readOnlyHint: true
  • share_reportMake a report public so it can be shared, and return its page URL.Reads text others writeNo 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.
    Description, as the server wrote it
    Make a report public so it can be shared, and return its page URL. Needs only the reportId returned by report. The page text comes from the report itself. Sharing the same report again returns the same URL. The report widget calls this when the visitor presses its share icon.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • simulateSimulate historical fills and account balances.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
    Simulate historical fills and account balances. Needs the full run form.

    Annotations the server declares

    • readOnlyHint: true
Only reads 3Show 3 read-only tools
  • get_pricesRead historical prices for a run form.No findings

    Why it is in this group

    • The name "get_prices" says "get": a word for reading.
    Description, as the server wrote it
    Read historical prices for a run form. Needs only version and data.

    Annotations the server declares

    • readOnlyHint: true
  • list_dataList available price data, fields, dates, limits, and whether reports can be retained for publishing.No findings

    Why it is in this group

    • The name "list_data" says "list": a word for reading.
    Description, as the server wrote it
    List available price data, fields, dates, limits, and whether reports can be retained for publishing.

    Annotations the server declares

    • readOnlyHint: true
  • list_strategiesList published website strategies, their URLs, and their current keys.Reads text others writeNo findings

    Why it is in this group

    • The name "list_strategies" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List published website strategies, their URLs, and their current keys. Use a current key as expectedKey only when the user asks to replace that saved strategy.

    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.

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 write3
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 16, 2026, 14:21 UTC, unchanged since Nov 9, 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://backtester.daenadigital.com/mcp: tools/list returned 9 tools to an anonymous client, including save_strategy (destructive), build_series (write), build_signal (write), simulate (write), report (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warnreport

    The server marks "report" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The description's first verb is "run": a word for a change.

    What this check looks for

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 backtester https://backtester.daenadigital.com/mcp
claude mcp add --transport http backtester https://backtester.daenadigital.com/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__backtester__list_data",
      "mcp__backtester__get_prices",
      "mcp__backtester__list_strategies"
    ],
    "ask": [
      "mcp__backtester__build_series",
      "mcp__backtester__build_signal",
      "mcp__backtester__simulate",
      "mcp__backtester__report",
      "mcp__backtester__share_report"
    ],
    "deny": [
      "mcp__backtester__save_strategy"
    ]
  }
}

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 backtester. Review it before you use it.

Capability tags behind 3 rules
  • mcp__backtester__share_report untrusted-input
  • mcp__backtester__list_strategies untrusted-input
  • mcp__backtester__save_strategy 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/io.github.morshedgit/backtester/verify?hash=24377636b5223cacae82686a0fa4dc405c721a146d5f389d13bb212b5e8af4cf" | jq -e '.changed == false'

Pinned hash 24377636b522, from Nov 8, 2026, 20:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.morshedgit/backtester/changes.xml

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

Badge

Anlyon Radar badge for io.github.morshedgit/backtester
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.morshedgit/backtester.svg)](https://radar.anlyon.com/servers/io.github.morshedgit/backtester)

Source: MCP Registry. Synced Nov 8, 2026, 20:18 UTC.

Backtester MCP server: questions and answers

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

Is the Backtester MCP server safe?

No scan can promise that. What its definitions show: 9 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 Backtester MCP server delete data?

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

Can the Backtester 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 Backtester MCP server have?

9 tools: 1 destructive, 5 write, 3 read. save_strategy, build_series, build_signal, simulate, report, share_report, list_data, get_prices and 1 more.

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

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

Does the Backtester MCP server send data to outside services?

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

Has the Backtester MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.