Skip to main content
Glama
ransomware-live-mcp

ransomware-live-mcp

by abdulbrown

ransomware-live-mcp

An MCP server exposing the ransomware.live PRO threat-intelligence API to any MCP client: ransomware groups and their TTPs, victims, IOCs, YARA rules, ransom notes, leaked negotiation chats, press coverage, SEC 8-K cyber disclosures, and national CSIRT contacts.

25 tools, all read-only. Every tool maps to a documented GET endpoint on https://api-pro.ransomware.live.

Built for defensive use: threat hunting, detection engineering, incident response, third-party risk and tabletop exercises.

Works on macOS, Linux and Windows.


Quick start

git clone https://github.com/abdulbrown/ransomware-live-mcp.git
cd ransomware-live-mcp
uv venv
uv pip install -e ".[dev]"
cp .env.example .env          # then paste your key into .env

Then register it with your MCP client.

Full detail below.


Related MCP server: eSentire Atlas MCP Server

1. Requirements

  • Python 3.10+

  • An MCP client — Claude Code, Claude Desktop, or any other

  • A free ransomware.live PRO API key

Get and enable your API key

The key is free. Every user needs their own — keys are personal and should never be shared or committed.

  1. Go to my.ransomware.live.

  2. Register with an email address and confirm it. The confirmation link activates the account; the key will not authenticate until you do this.

  3. Sign in to the dashboard and generate / copy your API key. It looks like a UUID (36 characters, in the form xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).

  4. Paste it into .env — see step 3 below.

  5. Verify it is enabled before wiring it into a client:

    <PYTHON> scripts/selftest.py

    A working key prints [ok] API key valid: followed by the account identifier tied to it. You can also check it directly:

    curl https://api-pro.ransomware.live/validate -H "X-API-KEY: your-key-here"
    # {"status": "valid", "client": "you@example.com"}

Once registered, the key is authenticated by sending it as an X-API-KEY header on every request — this server handles that for you.

Which API tier this uses

ransomware.live offers several tiers. This server targets API PRO:

Tier

Auth

Limit

Used here

API v1

none

deprecated

no

API v2

none

1 req/min per endpoint

no

API PRO

X-API-KEY

500,000 calls/month

yes

API PRO+

key

in development

no

PRO is free but key-gated, and is the only tier exposing group intelligence (TTPs, CVEs), negotiations, YARA rules and ransom notes. A fair use policy applies; exceeding the quota returns HTTP 429, which this server retries with backoff.

What the key unlocks

23 of the 25 tools call the API and require the key. Only build_victim_id and decode_victim_identifier work offline. If the key is missing or invalid, every API tool returns one clear error message and the server stays running — it does not crash the session.

2. Install

git clone https://github.com/abdulbrown/ransomware-live-mcp.git
cd ransomware-live-mcp

# with uv (recommended):
uv venv
uv pip install -e ".[dev]"

# or with plain venv + pip:
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

Your Python interpreter is at .venv/bin/python.

git clone https://github.com/abdulbrown/ransomware-live-mcp.git
cd ransomware-live-mcp

# with uv (recommended):
uv venv
uv pip install -e ".[dev]"

# or with plain venv + pip:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -e ".[dev]"

Your Python interpreter is at .venv\Scripts\python.exe.

Throughout this README, <PYTHON> means the interpreter path for your platform: .venv/bin/python on macOS/Linux, .venv\Scripts\python.exe on Windows.

Verify the install before going further — this works without an API key:

<PYTHON> -m pytest -q

Expect 32 passed.

3. Add your API key

Copy the example file and paste your key into it:

# macOS / Linux
cp .env.example .env
# Windows
Copy-Item .env.example .env

Edit .env:

RANSOMWARE_LIVE_API_KEY=your-key-here

.env is gitignored and will never be committed. The server resolves it relative to its own install location, not the working directory, so it works no matter where your MCP client launches it from.

Confirm the key works:

<PYTHON> scripts/selftest.py

Expected output ends with [ok] full self-test passed. If you have not added a key yet it exits cleanly and tells you so, rather than failing cryptically.

4. Register with your MCP client

Every MCP client spawns the interpreter directly, so you must use an absolute path to the venv Python. Get it with:

# macOS / Linux
echo "$(pwd)/.venv/bin/python"
# Windows
(Resolve-Path .\.venv\Scripts\python.exe).Path

Claude Code

# macOS / Linux
claude mcp add ransomware-live --scope user -- /ABSOLUTE/PATH/TO/ransomware-live-mcp/.venv/bin/python -m ransomware_live_mcp.server
# Windows
claude mcp add ransomware-live --scope user -- C:\ABSOLUTE\PATH\TO\ransomware-live-mcp\.venv\Scripts\python.exe -m ransomware_live_mcp.server

--scope user makes it available in every project; drop the flag to scope it to the current project only.

Confirm it connected:

claude mcp list

You should see ransomware-live: ... - ✓ Connected. The tools become available in new sessions, so restart any session you already have open.

To remove it later: claude mcp remove ransomware-live --scope user

Claude Desktop

Edit your claude_desktop_config.json:

Platform

Location

macOS

~/Library/Application Support/Claude/claude_desktop_config.json

Windows

%APPDATA%\Claude\claude_desktop_config.json

You can also reach it from the app: Settings → Developer → Edit Config.

{
  "mcpServers": {
    "ransomware-live": {
      "command": "/Users/you/code/ransomware-live-mcp/.venv/bin/python",
      "args": ["-m", "ransomware_live_mcp.server"]
    }
  }
}

Backslashes must be escaped in JSON:

{
  "mcpServers": {
    "ransomware-live": {
      "command": "C:\\Users\\you\\code\\ransomware-live-mcp\\.venv\\Scripts\\python.exe",
      "args": ["-m", "ransomware_live_mcp.server"]
    }
  }
}

Restart Claude Desktop completely after editing — quit the app, don't just close the window. The tools appear under the tools icon in the chat input.

Any other MCP client

The server speaks MCP over stdio. Point your client at:

  • command: the absolute path to <PYTHON>

  • args: ["-m", "ransomware_live_mcp.server"]

Passing the key inline instead of using .env

Any client that supports an env block can supply the key directly:

{
  "mcpServers": {
    "ransomware-live": {
      "command": "/absolute/path/to/.venv/bin/python",
      "args": ["-m", "ransomware_live_mcp.server"],
      "env": { "RANSOMWARE_LIVE_API_KEY": "your-key-here" }
    }
  }
}

.env is usually preferable — it keeps your key out of client config files, which are easy to sync, screenshot or share by accident.

Running it directly

<PYTHON> -m ransomware_live_mcp.server

It will sit and wait for a client on stdin. That is correct behaviour, not a hang.

5. Troubleshooting

Symptom

Cause and fix

✗ Failed to connect in claude mcp list

Wrong interpreter path. It must be the absolute path to the venv Python, not python or a system install.

Every tool returns "No API key configured"

.env missing or key not filled in. Run <PYTHON> scripts/selftest.py to confirm.

API key rejected (403)

Key is wrong or inactive. Verify at my.ransomware.live.

ModuleNotFoundError: ransomware_live_mcp

The client is using a different interpreter than the one you installed into. Re-check the absolute path.

Tools don't appear in Claude Code

They only load in new sessions. Restart the session.

Tools don't appear in Claude Desktop

Quit and relaunch the app entirely; closing the window is not enough.

Windows: running scripts is disabled

PowerShell execution policy. Use .\.venv\Scripts\python.exe directly instead of activating.


Tools

Tool

Endpoint

Purpose

validate_api_key

/validate

Confirm the key is active

get_stats

/stats

Victim/group/press totals and last update

list_groups

/groups

All tracked groups with victim counts

get_group

/groups/{name}

Full profile: TTPs, CVEs, tools, leak sites

list_sectors

/listsectors

Valid sector filter values

get_recent_victims

/victims/recent

100 newest victims

search_victims

/victims/search

Free-text search on name/website

filter_victims

/victims/

Exact filter by group/sector/country/date

get_victim

/victim/{id}

One enriched victim record

build_victim_id

—

Offline: names → Base64 victim ID

decode_victim_identifier

—

Offline: Base64 victim ID → names

list_ioc_groups

/iocs

Groups holding IOCs, by type

get_group_iocs

/iocs/{group}

IOC values for a group

list_yara_groups

/yara

Groups with YARA rules

get_yara_rules

/yara/{group}

Full YARA rule text

list_ransomnote_groups

/ransomnotes

Groups with ransom notes

list_group_ransomnotes

/ransomnotes/{group}

Note identifiers

get_ransomnote

/ransomnotes/{group}/{note}

Note content

list_negotiation_groups

/negotiations

Groups with leaked chats

list_group_negotiations

/negotiations/{group}

Chats + ransom amounts/outcome

get_negotiation

/negotiations/{group}/{id}

Full message thread

get_recent_press

/press/recent

100 newest cyberattack press entries

search_press

/press/all

Press by year/month/country

get_sec_8k_filings

/8k

SEC 8-K Item 1.05 / 8.01 cyber disclosures

get_csirt_contacts

/csirt/{country}

National CERT/CSIRT contacts

All 25 are annotated readOnlyHint, so clients can auto-approve them without prompting on every call.

Use cases

Once registered, ask your client in plain language. The examples below are grouped by what the API key actually unlocks, with real figures observed against the live API.

1. Threat landscape monitoring

"What's the current ransomware landscape summary?" "Which groups have been most active this month?"

Tools: get_stats, list_groups, get_recent_victims

A single get_stats call is the cheapest freshness check — it returns total victims, tracked groups, press entries and the timestamp of the most recent leak-site listing. list_groups returns every tracked group with a victim count, which is also how you resolve the exact group name other tools expect.

2. Adversary profiling and vulnerability prioritisation

"Profile the Akira ransomware group — TTPs, exploited CVEs, and tooling." "Which ransomware groups exploit vulnerabilities in my edge devices?"

Tools: get_group

The richest endpoint. For one group you get a full MITRE ATT&CK mapping (Initial Access → Impact), the CVEs that group is known to exploit with CVSS scores, categorised tooling (RMM abuse, exfiltration, credential theft), and known leak-site URLs.

This turns a patch backlog into a threat-informed queue: Akira's list includes SonicWall CVE-2024-40766, Veeam CVE-2024-40711 and Fortinet CVE-2022-40684 — all CVSS 9.8, all internet-facing. Cross-reference against your own edge inventory and the patch order writes itself.

3. Detection engineering

"Pull YARA rules and hash IOCs for Qilin and write them to ./rules/." "Get Akira's IP indicators for my blocklist."

Tools: list_yara_groups, get_yara_rules, list_ioc_groups, get_group_iocs

get_yara_rules returns complete .yar rule text ready for a scanner. get_group_iocs returns indicators grouped by type — use the ioc_type filter (md5, sha256, ip, domain, email, btc, tox, session) to keep responses small, since some groups hold hundreds of hashes.

Check coverage before you pull: list_ioc_groups shows the per-type breakdown, so you can see that a group is hash-heavy and network-light before assuming an IP blocklist gives you meaningful coverage.

4. Third-party and supply chain risk

"Have any of these vendors appeared on a leak site? [domain list]" "Show UK healthcare ransomware victims from the last year."

Tools: search_victims, filter_victims, list_sectors, get_victim

search_victims substring-matches both the organisation name and the website domain, so you can paste a vendor domain list straight in. filter_victims does exact-match slicing by group, sector, country and date — filtering to UK healthcare returns 65 victims, paginated.

Use list_sectors first to get valid sector values; it also returns victim counts per sector, which is a quick relative-risk picture on its own.

5. Incident response

"I found a ransom note called README0apt on a host — which group is this?" "Who do I notify for a ransomware incident in Germany?"

Tools: list_ransomnote_groups, list_group_ransomnotes, get_ransomnote, get_csirt_contacts, get_group

Ransom notes give you attribution from an artefact you'd actually recover from a compromised machine. Once attributed, get_group tells you that actor's typical initial access and exfiltration tooling — i.e. where else to look.

get_csirt_contacts returns national CERT/CSIRT contacts from ENISA and FIRST. Worth resolving before you need it, not during an incident.

6. Ransom negotiation preparation and tabletop exercises

"Analyze Akira's negotiation history — what do victims actually pay?"

Tools: list_negotiation_groups, list_group_negotiations, get_negotiation

The most unusual dataset here: leaked negotiation transcripts with ransom amounts and outcomes. Aggregating Akira's 76 chats:

Metric

Value

Confirmed paid

27 / 76 (36%)

Median discount off initial demand

57%

Median initial demand

$400,000

Median settled amount

$140,000

Largest demand observed

$10,000,000

Longest negotiation

170 messages ($1.7M → $225k)

list_group_negotiations gives amounts and outcomes without pulling every message, so prefer it for aggregate analysis; use get_negotiation when you want the actual transcript for a tabletop.

Interpret with care: this is only the subset of negotiations that leaked, which skews toward cases that went badly or public. Treat the payment rate as a property of that sample, not a market-wide figure.

7. Executive reporting and regulatory tracking

"Which public companies filed SEC 8-K Item 1.05 cyber disclosures in 2025?" "What ransomware activity hit our sector this quarter?"

Tools: get_sec_8k_filings, get_recent_press, search_press, list_sectors

get_sec_8k_filings covers SEC Form 8-K cyber disclosures — Item 1.05 (Material Cybersecurity Incidents, mandatory since December 2023) and Item 8.01. Set include_item_801=false for mandatory material incidents only. Each result carries company, ticker, CIK, filing date and a direct EDGAR link.

Press endpoints add journalistic coverage cross-linked to leak-site victims where the domain matches, which is useful for the "has this become public yet?" question.


Notes on responses

The live API departs from its own documentation in two ways this server smooths over, both confirmed against api-pro.ransomware.live:

  • Envelopes. Every response is a wrapper dict ({client, count, victims}, {client, count, groups}, {client, filters, count, forms}, ...), not the bare list the docs imply. Tools unwrap it, and drop the client field that echoes your account identity back on every single response.

  • Two spellings for victim fields. /victims/recent returns victim / group / attackdate, while /victims/search and /victim/{id} still return the legacy post_title / group_name / published. Everything is normalised to the modern names, so all tools report one schema.

Victim and press listings can run to thousands of records, so those tools paginate and slim by default:

  • limit defaults to 50, max 200. Page onward with the next_offset value the response hands back.

  • Pass full=true for the enrichment fields (screenshot URL, infostealer data, press link, permalink). When omitted, the response still flags has_infostealer_data / has_press_coverage / has_screenshot.

GET responses are cached in memory for 5 minutes, and HTTP 429 / 5xx are retried with exponential backoff honouring Retry-After.

Known limitations

  • get_group and unfiltered get_group_iocs return large payloads and are not paginated. A single group profile can run to several thousand tokens; some groups hold hundreds of hashes. Use the ioc_type filter to narrow.

  • Upstream data quality is uneven and passed through faithfully: some group entries are artefacts (e.g. .git), ransom amounts appear as "N/A", "" or null in the same field, and country is sometimes blank.

  • There is no monthly quota tracking. The cache reduces repeat calls but is per-process and does not survive a restart.

Configuration

Variable

Default

Meaning

RANSOMWARE_LIVE_API_KEY

—

Required. PRO API key

RANSOMWARE_LIVE_BASE_URL

https://api-pro.ransomware.live

API base

RANSOMWARE_LIVE_CACHE_TTL

300

Cache lifetime, seconds (0 disables)

RANSOMWARE_LIVE_TIMEOUT

30

Per-request timeout, seconds

Precedence: real environment variables > .env in the working directory > .env beside the package.

Tests

<PYTHON> -m pytest -q             # 32 offline tests, no key needed
<PYTHON> scripts/launch_check.py  # stdio JSON-RPC handshake
<PYTHON> scripts/selftest.py      # key validation + a few live calls
<PYTHON> scripts/live_check.py    # all 25 tools against the live API

launch_check.py spawns the server as a real subprocess from an unrelated working directory and speaks raw MCP JSON-RPC to it, proving both the transport and the .env resolution work independently of any client library. live_check.py goes through MCPServer.call_tool, covering argument schemas and validation as well as the HTTP layer.

Only pytest runs without an API key; the other three make live calls.

Gotchas if you extend this

  • The API's WAF returns 403 {"message": "Invalid API key"} — not a 429 or a block page — for requests carrying the default python-httpx/* User-Agent, even with a valid key. The client always sends its own User-Agent.

  • The server exits on stdin EOF, which is correct MCP behaviour. Test harnesses using subprocess.communicate() will close stdin and abort any in-flight tool call; hold stdin open instead.

  • Raise ToolError, never a bare exception. The SDK wraps an unrecognised exception as UnexpectedToolError, which tears down the stdio session — one failing call costs the client all 25 tools. The readonly_tool decorator converts ApiError to ToolError centrally, so a missing key or a 404 returns one actionable message and the session stays up. Any new failure mode should go through ApiError.

  • This targets MCP SDK 2.x, where FastMCP was renamed MCPServer. Most tutorials still show the 1.x import.

Security

  • .env is gitignored and no key is committed to this repository.

  • The server is strictly read-only — it issues GET requests and exposes no tool that writes, deletes, or sends data anywhere.

  • Responses may contain ransom note text, leaked negotiation transcripts and victim organisation names. Handle accordingly.

License

MIT — see LICENSE.

Data is supplied by ransomware.live under its own terms; observe its fair use policy. This project is not affiliated with or endorsed by ransomware.live.

Available Tools

25 tools
build_victim_idA
Read-only

Construct the Base64 victim ID for get_victim from the two names.

Offline helper; makes no API call. The names must match the API's values exactly, so prefer reusing an id from a listing when you have one.

Args: victim_name: Victim organisation name as listed (the victim field). group_name: Ransomware group name (the group field).

Inputs: group_name (required), victim_name (required). Returns: object

decode_victim_identifierA
Read-only

Decode a Base64 victim ID back into its victim and group names.

Offline helper; makes no API call.

Args: victim_id: Base64-encoded victim ID.

Inputs: victim_id (required). Returns: object

filter_victimsA
Read-only

Filter the full victim database by group, sector, country and date.

At least one filter is required, and all filters combine with AND logic. year cannot be used alone: the API rejects it unless month is also set. Use this rather than search_victims when you want an exact-match slice (e.g. every LockBit victim, or all US healthcare victims in June 2024).

Args: group: Exact group name, case-insensitive (see list_groups). sector: Exact sector name (see list_sectors). country: ISO 3166-1 alpha-2 country code, e.g. "US". year: 4-digit year, e.g. "2024". Must be paired with month. month: 2-digit month, e.g. "06". Requires year. date: Which date field to filter on, "discovered" or "attacked". limit: Max records to return (1-200). offset: Skip this many records; use next_offset from a prior call. full: Include all enrichment fields.

Inputs: date, full, year, group, +5 more. Returns: object

get_csirt_contactsA
Read-only

Get national CSIRT/CERT incident-response contacts for a country.

Sourced from ENISA (EU) and FIRST (global). Use this to find who to notify when triaging a confirmed incident.

Args: country: ISO 3166-1 country code, alpha-2 ("FR") or alpha-3 ("FRA").

Inputs: country (required). Returns: object

get_groupA
Read-only

Get a full intelligence profile for one ransomware group.

Includes background description, first/last seen dates, victim count, known leak-site URLs (Tor and clearweb), MITRE ATT&CK TTPs, exploited CVEs with CVSS scores, tools and malware used, and flags for whether negotiation chats and ransom notes are on file.

Args: group_name: Group name, case-insensitive (e.g. "lockbit3", "blackcat", "clop").

Inputs: group_name (required). Returns: object

get_group_iocsA
Read-only

Get indicators of compromise for one ransomware group, grouped by type.

Args: group: Group name, e.g. "lockbit3". ioc_type: Return only this type (md5, sha256, ip, domain, email, btc, url) to keep the response small.

Inputs: group (required), ioc_type. Returns: object

get_negotiationA
Read-only

Get the full message thread and ransom metadata for one negotiation chat.

These threads can be long. Prefer list_group_negotiations first to read ransom amounts and outcomes without pulling every message.

Args: group: Group name, e.g. "lockbit3". chat_id: Chat ID from list_group_negotiations, e.g. "20240517".

Inputs: group (required), chat_id (required). Returns: object

get_ransomnoteA
Read-only

Get the full text of one ransom note.

Args: group: Group name, e.g. "lockbit3". note_name: Note identifier from list_group_ransomnotes, without file extension.

Inputs: group (required), note_name (required). Returns: object

get_recent_pressA
Read-only

Get the 100 most recent tracked cyberattack press entries.

Entries are enriched with infostealer data and linked to a ransomware victim record where the domain matches.

Args: country: ISO 3166-1 alpha-2 country code to narrow before taking the top 100. limit: Max records to return (1-200). offset: Skip this many records; use next_offset from a prior call. full: Include all enrichment fields.

Inputs: full, limit, offset, country. Returns: object

get_recent_victimsA
Read-only

Get the 100 most recent active ransomware victims.

Args: order: "discovered" (when ransomware.live first saw the leak-site listing) or "attacked" (estimated attack date). limit: Max records to return (1-200). offset: Skip this many records; use next_offset from a prior call. full: Return every enrichment field (screenshot URL, infostealer data, press link, permalink) instead of the slimmed core fields.

Inputs: full, limit, order, offset. Returns: object

get_sec_8k_filingsA
Read-only

Get SEC Form 8-K filings disclosing cybersecurity incidents.

Covers Item 1.05 (Material Cybersecurity Incidents, mandatory since Dec 2023) and Item 8.01 (Other Events, used for such disclosures before that).

Args: ticker: Stock ticker, uppercase, e.g. "MSFT". cik: SEC CIK code, e.g. "0001234567". year: 4-digit filing year, e.g. "2025". month: 2-digit filing month, e.g. "06". Requires year. include_item_105: Include Item 1.05 filings. include_item_801: Include Item 8.01 filings. limit: Max records to return (1-200). offset: Skip this many records; use next_offset from a prior call.

Inputs: cik, year, limit, month, +4 more. Returns: object

get_statsA
Read-only

Get platform-wide totals: victim count, tracked group count, press entry count, and the timestamp of the most recently discovered victim.

Useful as a cheap freshness check before running larger queries.

Inputs: no named parameters. Returns: object

get_victimA
Read-only

Get the full enriched record for one victim by its Base64 ID.

The ID is Base64 of "victim_name@group_name" and appears as the id field in every victim listing. If you only have the names, use build_victim_id first. Returns 404 if the listing was taken down.

Args: victim_id: Base64-encoded victim ID from a listing's id field.

Inputs: victim_id (required). Returns: object

get_yara_rulesA
Read-only

Get every YARA rule for a group, each with filename and full rule text.

The returned content is ready to feed to a YARA scanner.

Args: group: Group name, e.g. "lockbit3", "blackcat".

Inputs: group (required). Returns: object

list_group_negotiationsA
Read-only

List negotiation chats for a group with ransom and outcome metadata.

Each entry carries id (pass to get_negotiation), message_count, initialransom, negotiatedransom, and paid.

Args: group: Group name, e.g. "lockbit3".

Inputs: group (required). Returns: object

list_group_ransomnotesA
Read-only

List the ransom note identifiers available for one group.

Pass a returned name to get_ransomnote to read its content.

Args: group: Group name, e.g. "lockbit3", "clop".

Inputs: group (required). Returns: object

list_groupsA
Read-only

List all tracked ransomware groups alphabetically with victim counts.

Each entry has group (the lowercase name used by every other tool), altname, and victims. Call this to resolve a group name before using get_group, get_group_iocs, get_yara_rules and similar.

Inputs: limit, offset. Returns: object

list_ioc_groupsA
Read-only

List ransomware groups that have IOCs on file, with per-type counts.

Common IOC types: md5, sha256, ip, domain, email, btc, url.

Args: ioc_type: Only return groups holding this IOC type, e.g. "ip".

Inputs: ioc_type. Returns: object

list_negotiation_groupsA
Read-only

List ransomware groups with leaked negotiation chat logs, and chat counts.

Inputs: no named parameters. Returns: object

list_ransomnote_groupsA
Read-only

List ransomware groups that have ransom notes on file, with note counts.

Inputs: no named parameters. Returns: object

list_sectorsA
Read-only

List every victim sector/industry value with a victim count per sector.

The sector values returned here are the valid inputs for the sector filter on search_victims and filter_victims.

Inputs: no named parameters. Returns: object

list_yara_groupsA
Read-only

List ransomware groups that have YARA detection rules, with rule counts.

Inputs: no named parameters. Returns: object

search_pressA
Read-only

Search all tracked cyberattack press entries by year, month and country.

Results are sorted newest first.

Args: year: 4-digit year, e.g. "2024". month: 2-digit month, e.g. "03". Requires year. country: ISO 3166-1 alpha-2 country code, e.g. "FR". limit: Max records to return (1-200). offset: Skip this many records; use next_offset from a prior call. full: Include all enrichment fields.

Inputs: full, year, limit, month, +2 more. Returns: object

search_victimsA
Read-only

Free-text search across victim organisation names and website domains.

q is matched case-insensitively as a substring of both the victim name and the website. The other filters narrow further with AND logic.

Args: q: Keyword, e.g. "hospital", "university", "acme". group: Exact group name, case-insensitive (see list_groups). sector: Exact sector name (see list_sectors). country: ISO 3166-1 alpha-2 country code, e.g. "US", "FR", "DE". order: Sort by "discovered" or "attacked". limit: Max records to return (1-200). offset: Skip this many records; use next_offset from a prior call. full: Include all enrichment fields.

Inputs: q, full, group, limit, +4 more. Returns: object

validate_api_keyA
Read-only

Check that the configured RANSOMWARE_LIVE_API_KEY is valid and active.

Returns the client identifier tied to the key. Run this first when any other tool reports an authentication failure.

Inputs: no named parameters. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 25 tools

    Disambiguation4/5

    Each tool targets a distinct resource and action, with clear list/get navigation pairs for victims, IOCs, YARA rules, ransom notes, and negotiations. A couple of names are near-permutations (list_ransomnote_groups vs list_group_ransomnotes; list_negotiation_groups vs list_group_negotiations), so an agent could misselect without reading the descriptions.

    Naming Consistency4/5

    All tool names are verb-first snake_case (validate, get, list, search, filter, build, decode), giving a predictable overall style. Minor deviations include 'id' vs 'identifier' between build_victim_id and decode_victim_identifier, and the swapped noun order in the list_<type>_groups / list_group_<type> pairs.

    Tool Count4/5

    25 tools is at the heavy end, but the server spans many distinct intelligence domains (victims, groups, IOCs, YARA, ransom notes, negotiations, press, SEC filings, CSIRT contacts), so the count is justified. It feels slightly over-packed rather than redundant.

    Completeness5/5

    The tool surface gives complete read-only coverage of the exposed domain: every artifact type has listing plus retrieval, with navigation helpers (build/decode victim ID, sector/group enumerations) that avoid dead ends. Since this is an intelligence/retrieval API, write operations are not an expected part of the lifecycle.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables comprehensive ransomware threat analysis through 25+ tools that interact with ransomware.live API. Provides real-time data on ransomware groups, victims, negotiations, IOCs, and attack trends for cybersecurity investigation and monitoring.
      -
    • F
      license
      A
      quality
      B
      maintenance
      Exposes eSentire Atlas API (Findings, Ticketing, MVS) and Threat Intelligence feeds (IP Watch, Advanced/STIX) as MCP tools, enabling security operations and threat intelligence queries through natural language.
      29
      -
    • A
      license
      B
      quality
      D
      maintenance
      Unified dark web and threat intelligence MCP server providing 66 tools across 16 data sources, including breach databases, ransomware tracking, Tor .onion access, blockchain intel, and malware analysis for AI agents.
      66
      3
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Live threat intelligence for agents: incident clusters, threat actor and malware profiles, CVEs with KEV/EPSS/exploit status, and ransomware leak-site victims, as ten read-only tools over the ThreatCluster API with a free key. Every result carries citation URLs and the credits it cost.
      3
      GPL 3.0