Double AIgents DSAR service MCP server
com.doubleaigents.www/dsarwww.doubleaigents.comstreamable-httpv1.2.0Scanned
GDPR DSAR deadlines, breach triage, AI tool checks, HR retention and letters (UK/EU/CH)
10 tools: 1 do something that can't be undone, 8 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 Double AIgents DSAR service MCP server can do
The Double AIgents DSAR service MCP server is published by www.doubleaigents.com, a domain the MCP Registry verified. It has 10 tools. It can do things that cannot be undone, such as sending, paying or publishing (breach_triage) and create or change data (8 tools: dsar_deadline, dsar_quote, dsar_service_info, dsar_request_scoping and 4 more), but cannot delete data. 1 tool only reads.
1 tool reads private data (dsar_search_checklist); 1 tool brings in text other people can write (dsar_search_checklist); 1 tool can send data out of your system (breach_triage). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.2.0.
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.
10 tools
Can't be undone 1Claude Code: ask
breach_triageA likely-reportability view on a personal data breach (UK, EU/EEA, Switzerland), following the ICO guide "Personal data breaches: a guide" and EDPB Guidelines 9/2022: whether notif…Can send data out1 finding
Why it is in this group
- The input addresses people (input.recipient): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.recipient): what the tool writes goes there.
Findings
- Warn
The server marks "breach_triage" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.recipient): what it sends cannot be taken back.
Description, as the server wrote it A likely-reportability view on a personal data breach (UK, EU/EEA, Switzerland), following the ICO guide "Personal data breaches: a guide" and EDPB Guidelines 9/2022: whether notifying the regulator and telling the people affected is likely or unlikely to be required, the factors behind that view, and the notification deadline. The controller decides. General information, not legal advice. Do not pass names or other personal data.
Annotations the server declares
- title: Personal data breach triage
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 8Claude Code: ask
ai_tool_checkScreens a planned use of an AI tool: whether a DPIA is likely to be required (Art.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 Screens a planned use of an AI tool: whether a DPIA is likely to be required (Art. 35(3), the ICO high-risk list, the WP248 criteria; FADP Art. 22 for Switzerland), EU AI Act risk flags (Annex III high-risk areas, especially employment; Art. 5 prohibited practices such as emotion recognition at work; current application dates after the Digital Omnibus), and automated decision rules (GDPR Art. 22, UK GDPR Arts 22A to 22D). Findings with sources. The use_case text is not stored or returned. General information, not legal advice.
Annotations the server declares
- title: AI tool check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
breach_clockWhen a personal data breach must be notified to the regulator: 72 hours from awareness in the UK and EU/EEA (Art.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 When a personal data breach must be notified to the regulator: 72 hours from awareness in the UK and EU/EEA (Art. 33), "as soon as possible" in Switzerland (revised FADP Art. 24). Gives the deadline, the rule, the processor and individual-notification position, and the facts the regulator will ask for. The controller decides whether to notify. General information, not legal advice.
Annotations the server declares
- title: Personal data breach notification clock
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dsar_deadlineCalculate the statutory deadline for answering a data subject access request in the UK, the EU/EEA or Switzerland, with the rule that applies and the extension position.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 Calculate the statutory deadline for answering a data subject access request in the UK, the EU/EEA or Switzerland, with the rule that applies and the extension position. General information, not legal advice.
Annotations the server declares
- title: DSAR response deadline
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dsar_letter_templatePlain-text letter template, in British English with [placeholders], for an acknowledgement, an extension of time or a request for clarification of a data subject access request, un…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 Plain-text letter template, in British English with [placeholders], for an acknowledgement, an extension of time or a request for clarification of a data subject access request, under UK, EU/EEA or Swiss law. Fills in the dates if received_date is given. General information, not legal advice.
Annotations the server declares
- title: DSAR letter template
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dsar_quoteFixed price from Double AIgents for preparing a DSAR response, by pack size in pages after de-duplication.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 Fixed price from Double AIgents for preparing a DSAR response, by pack size in pages after de-duplication. Also gives the retainer price (15% off). Excludes VAT.
Annotations the server declares
- title: DSAR fixed-price quote
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dsar_request_scopingExplains how to start free scoping and returns a prefilled email (mailto URL) to james@doubleaigents.com.1 finding
Why it is in this group
- The name "dsar_request_scoping" says "request": 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 "dsar_request_scoping" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "dsar_request_scoping" says "request": a word for a change.
Description, as the server wrote it Explains how to start free scoping and returns a prefilled email (mailto URL) to james@doubleaigents.com. Sends nothing and stores nothing. Do not pass the requester's personal data or the request letter.
Annotations the server declares
- title: Start DSAR scoping
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dsar_service_infoWhat the Double AIgents DSAR service covers: scoping, collection guidance, de-duplication, redaction, exemption recommendations, two independent reviews, secure delivery, data hand…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 What the Double AIgents DSAR service covers: scoping, collection guidance, de-duplication, redaction, exemption recommendations, two independent reviews, secure delivery, data handling, jurisdictions and partner arrangements.
Annotations the server declares
- title: DSAR service information
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
hr_retentionRecommended retention period for a common UK HR record, whether it is statutory or only recommended, and the source (HMRC, Home Office, RIDDOR 2013, Working Time Regulations, Limit…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 Recommended retention period for a common UK HR record, whether it is statutory or only recommended, and the source (HMRC, Home Office, RIDDOR 2013, Working Time Regulations, Limitation Act 1980, ICO, DBS). UK only for now. General information, not legal advice.
Annotations the server declares
- title: HR record retention periods (UK)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 1Show 1 read-only tool
dsar_search_checklistWhere to search when answering a subject access request, especially from an employee: Microsoft 365 (Exchange and archives, shared mailboxes, Teams, OneDrive, SharePoint), other co…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "dsar_search_checklist" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "mailbox": it reads mail.
- untrusted-inputThe description's first sentence says "mailbox": it reads inbound email, which other people can write.
Description, as the server wrote it Where to search when answering a subject access request, especially from an employee: Microsoft 365 (Exchange and archives, shared mailboxes, Teams, OneDrive, SharePoint), other collaboration tools, HR, payroll, recruitment, CCTV, access logs, devices, line manager notes, paper files, occupational health and backups; search-term tips; and the search standard (UK GDPR Art. 15(1A) reasonable and proportionate searches). General information, not legal advice.
Annotations the server declares
- title: DSAR search checklist
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.
1 path in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__dsar__breach_triage"
]
}
}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, 18:37 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
- 9
- 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 9 tools that change things (1 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.doubleaigents.com/api/mcp: tools/list returned 10 tools to an anonymous client, including breach_triage (irreversible), dsar_deadline (write), dsar_quote (write), dsar_service_info (write), dsar_request_scoping (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "dsar_request_scoping" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "dsar_request_scoping" says "request": a word for a change.
- Warnbreach_triage
The server marks "breach_triage" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.recipient): what it sends cannot be taken back.
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 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http dsar https://www.doubleaigents.com/api/mcpclaude mcp add --transport http dsar https://www.doubleaigents.com/api/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__dsar__dsar_search_checklist"
],
"ask": [
"mcp__dsar__dsar_deadline",
"mcp__dsar__dsar_quote",
"mcp__dsar__dsar_service_info",
"mcp__dsar__dsar_request_scoping",
"mcp__dsar__breach_clock",
"mcp__dsar__dsar_letter_template",
"mcp__dsar__breach_triage",
"mcp__dsar__ai_tool_check",
"mcp__dsar__hr_retention"
],
"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 dsar. Review it before you use it.
Capability tags behind 2 rules
- mcp__dsar__breach_triage outbound
- mcp__dsar__dsar_search_checklist private-data, 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.doubleaigents.www/dsar/verify?hash=7850f71ed30594f75ce50ccc445138bf8928f2e557109f3d825f324d77e69d52" | jq -e '.changed == false'Pinned hash 7850f71ed305, from Nov 10, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.doubleaigents.www/dsar/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.doubleaigents.www/dsar)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:54 UTC.
Double AIgents DSAR service MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Double AIgents DSAR service MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 9 of which can change, send or delete something, and 2 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 Double AIgents DSAR service MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Double AIgents DSAR service MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: breach_triage.
What tools does the Double AIgents DSAR service MCP server have?
- 10 tools: 1 irreversible, 8 write, 1 read. breach_triage, dsar_deadline, dsar_quote, dsar_service_info, dsar_request_scoping, breach_clock, dsar_letter_template, ai_tool_check and 2 more.
Does the Double AIgents DSAR service MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Double AIgents DSAR service MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): breach_triage.
Has the Double AIgents DSAR service MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.