Skip to content

Rösti Threat Intel MCP server

dev.rosti/rostirosti.devstreamable-httpv0.2.1Scanned

Look up IOCs and search threat-intel reports, YARA rules, MITRE ATT&CK ids and CVEs from rosti.dev

11 tools: 11 only read.

Tools: 0 delete, 0 irreversible, 0 write, 11 read.
  • Reads private data · 0
  • Reads text others write · 0
  • 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.
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 Rösti Threat Intel MCP server can do

The Rösti Threat Intel MCP server is published by rosti.dev, a domain the MCP Registry verified. It has 11 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

None of its tools reads private data, brings in text other people write, or sends data 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, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 19, 2026, version 0.2.1.

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.

11 tools

Only reads 11Show 11 read-only tools
  • describe_taxonomyList the values Rösti uses for IOC types, IOC tags (with descriptions), IOC categories and export formats, and explain the false-positive risk scale.No findings

    Why it is in this group

    • The name "describe_taxonomy" says "describe": a word for reading.
    Description, as the server wrote it
    List the values Rösti uses for IOC types, IOC tags (with descriptions), IOC categories and export formats, and explain the false-positive risk scale. Use these values for the filters of the search and list tools.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Describe the taxonomy
  • get_reportGet one Rösti report: metadata, MITRE ATT&CK ids, CVEs, available export formats, and how many of its IOCs there are per type and per tag.No findings

    Why it is in this group

    • The name "get_report" says "get": a word for reading.
    Description, as the server wrote it
    Get one Rösti report: metadata, MITRE ATT&CK ids, CVEs, available export formats, and how many of its IOCs there are per type and per tag. Use list_report_iocs for the IOCs themselves and get_yara_rules for its YARA rules.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Get a report
  • get_yara_rulesGet the YARA rules published with one Rösti report, with their full source.No findings

    Why it is in this group

    • The name "get_yara_rules" says "get": a word for reading.
    Description, as the server wrote it
    Get the YARA rules published with one Rösti report, with their full source.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Get YARA rules
  • list_report_iocsList the IOCs of one Rösti report, optionally filtered by type, tag, category or text.No findings

    Why it is in this group

    • The name "list_report_iocs" says "list": a word for reading.
    Description, as the server wrote it
    List the IOCs of one Rösti report, optionally filtered by type, tag, category or text. IOCs with the same entity_ref belong together, e.g. the MD5, SHA-1 and SHA-256 of one file. Each IOC carries its IDS flag and false-positive risk.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List a report's IOCs
  • list_sourcesList the publishers whose reports Rösti collects (vendor blogs, CERTs, researchers), with report counts, the newest report date and whether the source is still active.No findings

    Why it is in this group

    • The name "list_sources" says "list": a word for reading.
    Description, as the server wrote it
    List the publishers whose reports Rösti collects (vendor blogs, CERTs, researchers), with report counts, the newest report date and whether the source is still active. Source ids work as the sources filter of search_reports.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List sources
  • lookup_iocCheck whether one IOC (indicator of compromise) appears in Rösti's threat-intelligence reports.No findings

    Why it is in this group

    • The name "lookup_ioc" says "lookup": a word for reading.
    Description, as the server wrote it
    Check whether one IOC (indicator of compromise) appears in Rösti's threat-intelligence reports. A defanged value (hxxps://evil[.]com, 1.2.3[.]4) is refanged before the lookup; `input` then shows the value as given. Matching is exact, with a case-insensitive fallback. Returns every report the value appears in (newest first, up to max_matches) with the IOC's type, category, tags, IDS flag, comment and false-positive risk. Also checks the value against the Rösti False Positive Warninglist (popular domains, public DNS resolvers, ...) and returns its verdict in `false_positive_verdict`, also when Rösti does not know the value; null when the warninglist has no verdict.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Look up an IOC
  • lookup_iocsCheck many IOCs (indicators of compromise) at once against Rösti's threat-intelligence reports.No findings

    Why it is in this group

    • The name "lookup_iocs" says "lookup": a word for reading.
    Description, as the server wrote it
    Check many IOCs (indicators of compromise) at once against Rösti's threat-intelligence reports. Defanged values (hxxps://evil[.]com, 1.2.3[.]4, user[at]evil[.]com) are refanged before the lookup; `refanged` shows which. Matching is exact, with a case-insensitive fallback. For each value that is found, returns the reports it appears in (newest first) with the IOC's type, category, tags, IDS flag, comment and false-positive risk. Values that are not found are listed in `not_found`. Every value is also checked against the Rösti False Positive Warninglist (popular domains, public DNS resolvers, ...): found values carry `false_positive_verdict`, not-found values appear in `false_positive_verdicts`; values without a verdict are left out. Use lookup_ioc for all matches of a single value.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Look up IOCs
  • search_iocsSearch IOCs across all Rösti reports by text, type, tag, category and creation time.No findings

    Why it is in this group

    • The name "search_iocs" says "search": a word for reading.
    Description, as the server wrote it
    Search IOCs across all Rösti reports by text, type, tag, category and creation time. Without filters, lists IOCs from all reports. Each IOC carries its report id (use get_report for the report), type, category, tags, IDS flag, comment and false-positive risk. Use lookup_ioc or lookup_iocs to check whether specific values are known.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Search IOCs
  • search_reportsSearch Rösti's threat-intelligence reports by text, source, CVE, MITRE ATT&CK id and publication date.No findings

    Why it is in this group

    • The name "search_reports" says "search": a word for reading.
    Description, as the server wrote it
    Search Rösti's threat-intelligence reports by text, source, CVE, MITRE ATT&CK id and publication date. Returns report summaries: title, date, source, authors, tags, counts of IOCs, YARA rules and MITRE ids, and links to the original report and rosti.dev. Use get_report for the details of one report.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Search reports

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 19, 2026, 17:23 UTC, unchanged since Nov 5, 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
https://mcp.rosti.dev/.well-known/oauth-protected-resource/mcp
Authorization servers
https://rosti.dev/api/auth
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no

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.

  1. Tools2 changed.~2 changedView diff
  2. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http rosti https://mcp.rosti.dev/mcp
claude mcp add --transport http rosti https://mcp.rosti.dev/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__rosti__lookup_iocs",
      "mcp__rosti__lookup_ioc",
      "mcp__rosti__search_iocs",
      "mcp__rosti__search_reports",
      "mcp__rosti__get_report",
      "mcp__rosti__list_report_iocs",
      "mcp__rosti__get_yara_rules",
      "mcp__rosti__find_related_reports",
      "mcp__rosti__get_export_link",
      "mcp__rosti__list_sources",
      "mcp__rosti__describe_taxonomy"
    ],
    "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 rosti. 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/dev.rosti/rosti/verify?hash=8adaba40366b3d13fe3a43c10d47c9d02526584c8b6aecb78d8905fd00c473a8" | jq -e '.changed == false'

Pinned hash 8adaba40366b, from Nov 19, 2026, 11:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.rosti/rosti/changes.xml

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

Badge

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

Source: MCP Registry. Synced Nov 5, 2026, 15:17 UTC.

Rösti Threat Intel MCP server: questions and answers

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

Is the Rösti Threat Intel MCP server safe?

No scan can promise that. What its definitions show: 11 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 Rösti Threat Intel MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Rösti Threat Intel 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 Rösti Threat Intel MCP server have?

11 tools: 11 read. lookup_iocs, lookup_ioc, search_iocs, search_reports, get_report, list_report_iocs, get_yara_rules, find_related_reports and 3 more.

Does the Rösti Threat Intel MCP server need sign-in or OAuth?

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

Does the Rösti Threat Intel MCP server send data to outside services?

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

Has the Rösti Threat Intel MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.