mlab.sh MCP server
Commit Nov 5, 2026Provides threat intelligence and DFIR capabilities including IOC lookups, CVE searches, threat actor profiles, and memory forensics.
Also known as mlab-sh/mcp, mcp
- Stars
- 2
- Tools
- 48
- Downloads, 30 days
- —
- Latest version
- 1.2.0
- Last commit
- Nov 5, 2026
- License
- MIT
What is mlab.sh MCP?
mlab.sh provides threat intelligence and DFIR capabilities including IOC lookups, CVE searches, threat actor profiles, and memory forensics. It exposes 48 tools, such as detect_ioc, scan_ip, scan_url.
Summary generated from the project's README
About mlab.sh MCP server
Security operations center analysts and digital forensics investigators can perform threat intelligence and incident response tasks directly through their AI client. This remote MCP server provides access to 48 specialized tools for investigating indicators of compromise, searching for vulnerabilities, and analyzing threat actor profiles. It functions as a backend service that connects to clients like Claude.ai, Claude Desktop, Cursor, and VS Code using either OAuth or static bearer tokens.
Users can perform deep technical investigations including IP geolocation, domain scans, and static analysis of shell scripts or software bills of materials. For enterprise teams, the server supports advanced capabilities like managing security cases and interacting with remote workspaces. These workspaces allow for memory forensics on engram agents, YARA rule execution, and monitoring Kubernetes clusters or Proxmox VE environments. The system manages usage through organization-wide quotas for specific actions like IP or domain scans.
What you can do with it
- 1Investigate suspicious indicatorsAnalyze an IP address, domain, or file hash to gather geolocation, reputation, and malware family information.
- 2Analyze malicious scriptsPerform static analysis on shell scripts to identify suspicious constructs like reverse shells or base64 decoding.
- 3Research threat actorsRetrieve detailed profiles on threat actors, including their suspected sponsors and associated MITRE ATT&CK techniques.
- 4Perform memory forensicsExamine memory dumps for injected code, process trees, and registry hives within a secure workspace.
Written from the project's README. Every use case is checked against a quote from it.
How to install mlab.sh MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall mlab.sh MCP in Claude Code
$ claude mcp add --transport http mcp https://mlab.sh/mcpInstall mlab.sh MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mlab.sh/mcp"
}
}
}Install mlab.sh MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://mlab.sh/mcp"
}
}
}Install mlab.sh MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"http","url":"https://mlab.sh/mcp"}'Install mlab.sh MCP in Codex
$ codex mcp add mcp --url https://mlab.sh/mcpInstall mlab.sh MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] url = "https://mlab.sh/mcp"
Install mlab.sh MCP in Gemini CLI
$ gemini mcp add -s user --transport http mcp https://mlab.sh/mcpInstall mlab.sh MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"url": "https://mlab.sh/mcp",
"type": "http"
}
}
}mlab.sh MCP tools 48
Detected from the READMEdetect_iocscan_ipscan_urlscan_hashscan_cryptoscan_emailscan_phonescan_macstart_domain_scanget_domain_scan_resultsscan_bashscan_sbom
Show all 48 toolsShow fewer tools
cve_searchcve_detailsearch_actorsget_actorlist_casesget_casecreate_caseadd_case_indicatorsadd_case_commentworkspace_listworkspace_agentsworkspace_memory_dumpsworkspace_memory_indexworkspace_memory_overviewworkspace_memory_processworkspace_memory_readworkspace_memory_registryworkspace_memory_yaraworkspace_memory_yara_statusworkspace_cluster_listworkspace_cluster_imagesworkspace_cluster_imageworkspace_cluster_eventsworkspace_cluster_configworkspace_virt_listworkspace_virt_guestsworkspace_virt_guestworkspace_virt_eventsworkspace_virt_configworkspace_virt_auditget_account_infoget_scan_limitsget_scan_historyget_bookmarksadd_bookmarkremove_bookmark
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemlab-sh/mcp is public and reachablegithub.com/mlab-sh/mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-05github.com/mlab-sh/mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model48 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubmlab.sh MCP server
Public metadata and connection guide for the remote MCP server at https://mlab.sh/mcp, a threat intelligence server for SOC and DFIR work.
This repo is the registry listing and the documentation. It is not the server source: the server runs inside the mlab.sh backend and is closed source.
Connect
Endpoint: https://mlab.sh/mcp (Streamable HTTP via POST, SSE via GET).
Claude.ai
Settings > Connectors > Add custom connector, then paste the URL. OAuth runs in the browser, no token to copy.
https://mlab.sh/mcp
Claude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"mlab": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mlab.sh/mcp",
"--header",
"Authorization: Bearer mcp_xxx"
]
}
}
}
Drop the --header pair to use OAuth instead of a static token.
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"mlab": {
"url": "https://mlab.sh/mcp",
"headers": {
"Authorization": "Bearer mcp_xxx"
}
}
}
}
VS Code
.vscode/mcp.json:
{
"servers": {
"mlab": {
"type": "http",
"url": "https://mlab.sh/mcp",
"headers": {
"Authorization": "Bearer mcp_xxx"
}
}
}
}
curl
curl -sS -X POST https://mlab.sh/mcp \
-H "Authorization: Bearer mcp_xxx" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1.0.0"}}}'
Ready to paste versions of these four configs live in examples/.
Officially supported clients are Claude.ai and Claude Desktop. Other MCP clients (Cursor, VS Code, Windsurf and friends) work but are best effort.
Tools
48 tools. tools/list only shows a token the tools its role and plan can use, so a client never sees a tool that would refuse every call. Every tool carries MCP annotations (read only, destructive, idempotent, open world), so a host can tell what it may run unattended. No tool deletes anything.
Parameters marked ? are optional.
Who can use what
| Group | Plan | Role |
|---|---|---|
IOC lookups, domain scans, scan_bash, scan_sbom |
Any | Owner, admin, member (viewers cannot spend quota) |
| CVEs, actors, account, bookmarks, history | Any | Any, viewer included |
Cases: reading (list_cases, get_case) |
Team, Enterprise | Any, viewer included |
Cases: writing (create_case, add_case_indicators, add_case_comment) |
Team, Enterprise | Owner, admin, member |
| Workspaces | Team (1 workspace), Enterprise (up to 20) | Any; members only see the workspaces they were added to, owners and admins see all |
Quotas are counted per organization over a rolling 24 hour window. get_scan_limits reads what is left.
IOC lookups
| Tool | Parameters | What it returns |
|---|---|---|
detect_ioc |
value |
Detects the type of an indicator (IPv4, IPv6, CIDR, domain, URL, MD5/SHA1/SHA256/SHA512 hash, email, MAC) and returns the relevant intel. A domain is typed, not scanned: use start_domain_scan for that. An IP spends IP quota |
scan_ip |
ip |
For an address: geolocation, ISP, ASN, datacenter / proxy / VPN / mobile network, TOR consensus status, forward confirmed reverse DNS, RDAP record with the abuse contact. For a CIDR range: network, broadcast, host window, netmask, size, reserved blocks. Addresses spend IP quota (cached 7 days); ranges are free |
scan_url |
url, resolve? |
Static analysis without visiting: scheme, host with its Unicode and punycode forms, IP literal hosts, credentials in the URL, dangerous extensions, shorteners, embedded redirect targets, and what a past domain scan recorded about the host. resolve follows the link to its real destination, the only part that visits anything. No quota |
scan_hash |
hash |
MD5, SHA1 or SHA256 against CIRCL hashlookup (NIST NSRL): known good, known malicious or unknown, each feed's own answer, malware family, product and file name, CIRCL trust score, and mlab_sample when mlab analysed the file itself. unknown is not the same as safe. No quota |
scan_crypto |
address, chain? |
Labels, sanctions, risk score and address type across 18 chains (Bitcoin, Ethereum and 12 other EVM chains, Tron, Solana, TON, Dogecoin), with a checksum check. EVM addresses do not reveal their chain: pass chain when you know it. Spends crypto quota |
scan_email |
email |
Mailbox type (disposable, role, consumer, standard), SPF / DKIM / DMARC spoofability of its domain, MX presence, domain age when scanned, and a 0 to 100 score with its weighted reasons. No quota |
scan_phone |
number |
E.164 number: validity, country, line type, allocated operator, formatting and scam shaped findings. Offline, no quota |
scan_mac |
mac |
OUI vendor, unicast or multicast, universal or local administration, randomized or virtual interface, EUI-64 IPv6, other formats. Offline, no quota |
Domain scans and code
| Tool | Parameters | What it returns |
|---|---|---|
start_domain_scan |
domain |
Returns a recent completed scan right away, or launches a new one and returns {"status": "started"}. A new scan contacts the target and spends domain scan quota |
get_domain_scan_results |
domain |
Results of a domain scan: DNS records, subdomains, SSL certificates, security.txt, robots.txt. Call again while the status is pending or scanning |
scan_bash |
content, filename? |
Static analysis of an inline shell script: sha256, every IOC it holds, and well known suspicious constructs (download piped to a shell, base64 decoding, /dev/tcp reverse shells, persistence, anti forensics, destructive deletes). Nothing runs or is stored. No quota |
scan_sbom |
content, format? |
Known vulnerabilities in a lockfile or SBOM (npm, yarn, pnpm, Cargo, pip, Poetry, uv, PDM, Pipfile, Composer, Gem, Go, Maven, Gradle, NuGet, pub, Hex, mise, CycloneDX, SPDX), one finding per package and CVE, worst first, with the fixed version and what the scan could not cover. Matched server side on vuln.mlab.sh (OSV, NVD for CPE only components). 2 MB at most; format defaults to auto |
CVEs and threat actors
| Tool | Parameters | What it returns |
|---|---|---|
cve_search |
query, severity?, date_start?, date_end?, limit?, page? |
CVEs by keyword, product, vendor or ID, filtered by severity (CRITICAL, HIGH, MEDIUM, LOW) and publication date, with CVSS, EPSS and KEV status |
cve_detail |
cve_id |
The full record: CVSS vector breakdown, affected products, references, CWEs, EPSS, CISA KEV status |
search_actors |
query, origin?, motivation?, sector?, limit? |
Threat actors by name or alias from the MISP Galaxy cluster (CC0), narrowed by origin, incident type or targeted sector. Returns the slug for get_actor |
get_actor |
slug |
MISP Galaxy profile (origin, suspected sponsor, synonyms, targeted countries and sectors, references) with the MITRE ATT&CK tools and techniques attributed to it. Keep the sources block when quoting: it carries MITRE's notice |
Cases
Team and Enterprise. Each call goes through the same checks as the case pages.
| Tool | Parameters | What it returns |
|---|---|---|
list_cases |
none | The organization's cases, open ones first, with indicator and comment counts |
get_case |
uuid |
Title, summary, status, every indicator with a link to its analysis, and the comment thread |
create_case |
title, summary? |
Opens a case and returns the uuid the other case tools take |
add_case_indicators |
uuid, indicators |
Files a paste of indicators (one per line, or comma or space separated, mixed types), typed automatically; anything mlab cannot look up comes back in skipped with the reason |
add_case_comment |
uuid, body, indicator_uuid? |
A note on the case, or on one of its indicators |
Workspaces
Team and Enterprise, and only in a workspace whose admin turned on AI agents (MCP): a workspace keeps its data on the organization's own hosts, and an answer goes to the LLM provider of whoever asked. workspace_list says which workspaces are open. Every tool except workspace_list takes workspace (the uuid from workspace_list). Each call is written to the workspace's audit log.
The tools read, and can start an index or a YARA scan. Creating, deleting, enrolling, members, policies, pushing a cluster config and binary downloads stay in the app. Answers carry data sent by the hosts, which may contain text planted by an attacker: the server says so before every answer.
Agents and memory forensics (engram)
| Tool | Parameters | What it returns |
|---|---|---|
workspace_list |
none | The workspaces you can open, whether AI agents may read them, agents online and the tools they run |
workspace_agents |
workspace |
The workspace's agents: live state, version, the tools each one reports |
workspace_memory_dumps |
workspace |
Memory dumps on the engram agents, and which ones are indexed. Asks every agent: allow a few seconds |
workspace_memory_index |
workspace, agent, dump |
Starts indexing a dump on its host, in the background. Follow it with workspace_memory_dumps |
workspace_memory_overview |
workspace, agent, dump |
A dump's index: system, process tree, findings (injected code and other anomalies), registry hives |
workspace_memory_process |
workspace, agent, dump, pid |
One process in full: command line, environment, modules, memory regions, handles, findings |
workspace_memory_read |
workspace, agent, dump, address, len?, space?, pid? |
Up to 4 KiB read live from the dump, as hex and text. space is virtual (needs pid, the default) or physical |
workspace_memory_registry |
workspace, agent, dump, hive, path? |
One registry key: values, subkeys, last write time |
workspace_memory_yara |
workspace, agent, dump, rules, pids? |
Runs YARA rules over the dump's processes on the host. Usually returns a job, a new one each call |
workspace_memory_yara_status |
workspace, agent, job |
Progress of a YARA scan, and its matches once done |
Kubernetes clusters (k3sec)
| Tool | Parameters | What it returns |
|---|---|---|
workspace_cluster_list |
workspace |
Clusters reporting to the workspace: nodes online, images, vulnerabilities in packages really loaded, recent detections |
workspace_cluster_images |
workspace, cluster |
Running images with their vulnerabilities, loaded ones first |
workspace_cluster_image |
workspace, cluster, digest |
One image: findings and packages, with which are loaded in memory |
workspace_cluster_events |
workspace, cluster, source?, kind?, namespace?, min_severity?, q?, before?, limit? |
Runtime events, newest first: Kubernetes events, eBPF activity, YARA detections, with cached reputation of destinations and binaries. 200 at most per call; before pages back |
workspace_cluster_config |
workspace, cluster |
What k3sec collects on each node, and the ceiling the nodes' local policies allow |
Proxmox VE (virtsec)
| Tool | Parameters | What it returns |
|---|---|---|
workspace_virt_list |
workspace |
Proxmox clusters: nodes online, LXC and VM guests, guests with weakened isolation, vulnerabilities in loaded packages, critical events of the last 24 h |
workspace_virt_guests |
workspace, cluster |
Guests and nodes: status, isolation risks from their config (privileged, host bind mounts, passthrough), vulnerabilities |
workspace_virt_guest |
workspace, cluster, key, agent? |
One guest by vmid, or a node (key = node with its agent): isolation risks, findings, packages |
workspace_virt_events |
workspace, cluster, source?, kind?, min_severity?, q?, vmid?, before?, limit? |
Runtime events, newest first: executions in guests, outbound connections, sensitive writes, VM escape signals, PVE logins, auth failures, tasks, guest config changes. 200 at most per call |
workspace_virt_config |
workspace, cluster |
What virtsec collects on each node, and the ceiling the local policies allow |
workspace_virt_audit |
workspace, cluster |
Security posture per node: failed checks (PVE firewall off, users without a second factor, root SSH with a password, unreachable or test repositories, guests without backup, isolation risks, pending restarts), each with a fix |
Account, bookmarks and history
| Tool | Parameters | What it returns |
|---|---|---|
get_account_info |
none | The authenticated user, their organization and plan |
get_scan_limits |
none | Remaining IP, domain, file and crypto quotas of the organization, over a rolling 24 hours shared by all members |
get_scan_history |
type?, limit? |
Recent scans of the account, filtered by ip, domain or file |
get_bookmarks |
limit? |
Your bookmarked indicators |
add_bookmark |
value |
Bookmarks an IP, domain, URL, hash, crypto address, email, phone number or MAC address |
remove_bookmark |
value |
Removes a bookmark |
Authentication
OAuth 2.1 is the recommended path: authorization code with PKCE S256, dynamic client registration, CIMD supported. The server advertises its metadata at https://mlab.sh/.well-known/oauth-authorization-server, so a compliant client only needs the endpoint URL. A token issued this way is listed in Account > Settings as OAuth: <client name>; reconnecting the same client replaces its previous token instead of piling up new ones.
If your client does not speak OAuth, create a static token in Account > Settings > MCP Tokens and send it as Authorization: Bearer mcp_xxx. At creation you pick its lifetime: 30, 90 or 365 days, or never. A token can be renamed and revoked at any time from the same page.
MCP tokens are personal: they act as you, with your role in the organization. Organization API key permissions do not apply to them. Up to 5 active tokens, 100 on Team and Enterprise.
Full details: https://doc.mlab.sh/docs/mlab.sh/integrations/mcp
Rate limits and quotas
Limits follow your organization's plan and are counted over a rolling 24 hour window, shared by every member. A spent quota returns an error that says which one and when it frees up. Call get_scan_limits to read what is left.
Registry
Published to the official MCP Registry as sh.mlab/mcp.
https://registry.modelcontextprotocol.io/v0.1/servers?search=sh.mlab
Other public servers
https://news.mlab.sh/mcp is a separate, unauthenticated, read only MCP server exposing a cyber news index. It is not published from this repo.
Security
Report vulnerabilities to security@mlab.sh. See https://mlab.sh/security.txt and SECURITY.md.
License
MIT, see LICENSE.
mlab.sh MCP questions
How do I add mlab.sh MCP to Claude Code?
Run claude mcp add --transport http mcp https://mlab.sh/mcp in your terminal. Add --scope user to make it available in every project.
How do I add mlab.sh MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does mlab.sh MCP provide?
It exposes 48 tools, including detect_ioc, scan_ip, scan_url, scan_hash, scan_crypto.
Can the server delete any data?
No, the server is designed so that no tool performs deletions.
What kind of IOC lookups are supported?
The server supports lookups for IPv4, IPv6, CIDR, domains, URLs, various hash types (MD5, SHA1, SHA256, SHA512), emails, and MAC addresses.
Does the server run locally?
No, the server runs in the mlab.sh backend and is closed source.