ESET-MCP
Supports Cloudflare Access service-token authentication so requests can traverse a Cloudflare Access tunnel to reach an on-prem ESET PROTECT console; tokens can be set via env defaults or per-request headers (X-ESET-CF-Access-Client-Id / -Client-Secret).
Exposes an opt-in /metrics endpoint for Prometheus scraping, with counters for tool calls, token refreshes, HTTP retries and response-cap hits, histograms for tool duration and response sizes, and a gauge for client pool size.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ESET-MCP show me latest detections from ESET"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ESET-MCP
A Model Context Protocol server for the entire ESET management surface: ESET Connect (cloud, all regions), ESET PROTECT On-Prem, ESET Inspect, and ESET Cloud Office. Drive any of them from any MCP host (Claude Desktop, Claude Code, or a custom agent) through tools, resources, and prompts.
Built as a single hub for any number of ESET deployments. One process fronts cloud and on-prem consoles at the same time; clients pick the target per request via headers; non-default on-prem origins require an operator allowlist. MCP receives credentials (Basic auth, plus an optional URL override and optional Cloudflare Access service token), routes the call to the right backend, mints its own tokens, and keeps tenants isolated in the pool.
⚠️ Just to be clear, fellas
This is an independent, community-driven open-source project and is not affiliated with, officially supported by, or endorsed by ESET, spol. s r.o. ESET and its product names are registered trademarks of their respective owners.While every effort has been made to ensure this software is safe and robust (including the strict Read-Only mode gate), this code is provided "AS IS", without any warranty of any kind. You are solely responsible for how you use this tool and any changes made to your ESET environment.
2.0.0 — breaking security update: See the v1 → v2 migration guide. Authentication endpoints are private to the adapter and never exposed as tools. The 101 business tools, their input schemas and four composites retain their existing contracts. Read the required upgrade settings before updating an HTTP or On-Prem deployment. MCP 2026 base protocol and transports are supported; the existing custom Basic profile is retained, not advertised as MCP OAuth 2.1 authorization.
Table of contents
Related MCP server: Edgee MCP Server
Features
Complete API coverage
101 business tools auto-generated from 16 official ESET Connect OpenAPI 3.0.1 specs, covering application-management, asset-management, automation, device-management, identity, incident-management, installer-management, mobile-device-management, network-access-protection, patch-management, policy-management, quarantine-management, user-management, vulnerability-management, and web-access-protection.
4 high-level composites that fold 3-6 raw calls into one:
eset_search,device_full_profile,incident_full_context,latest_detections.
Read-only / read-write modes
ESET_MODE=RO→ catalog exposes only read-only tools (51 total). Write tools are hidden fromlist_toolsentirely.ESET_MODE=RW→ all 105 tools advertised; mutating tools carrydestructiveHint: truein their MCP annotations.Independent of the ESET account's underlying permissions.
A defence-in-depth in-memory gate rejects RW tool names in RO mode before any HTTP request is sent.
Authentication
ESET_AUTH_MODE=env- single tenant, credentials from.env.ESET_AUTH_MODE=basic- multi tenant, clients passAuthorization: Basic <base64(user:password)>per request (plus optionalX-ESET-Regionfor a different cloud region, orX-ESET-Server-URLto route the request to an on-prem PROTECT console). One server fronts many ESET accounts and can mix cloud + on-prem in the same process.Per-tenant OAuth tokens, pooled and isolated by
(user, password_hash, deployment, region-or-server-url, cf_secret_hash). Rotating a password or Cloudflare Access service token mints a fresh client; cloud and on-prem clients for the same user never share a pool entry.
Transports
stdio - JSON-RPC over stdin/stdout for local hosts.
Streamable HTTP - MCP 2026-07-28, with legacy 2025-11-25 compatibility.
Multi-region
eu / de / us / ca / jpn. Fixed via ESET_REGION in env mode;
per-request via X-ESET-Region in basic mode.
Cloud + on-prem in one process
In addition to the cloud regions, a single MCP server can front
customer-hosted ESET PROTECT On-Prem consoles. The on-prem auth wire
format (POST /GetTokens with a camelCase response) and per-host URL
structure are handled transparently; clients pick the target per request
via the X-ESET-Server-URL header. See
On-prem ESET PROTECT support.
Cloudflare Access (optional)
When the on-prem console sits behind a Cloudflare Access tunnel, MCP
authenticates as a service token
(env-default or per-request X-ESET-CF-Access-Client-Id /
X-ESET-CF-Access-Client-Secret) and rides through to the origin. The
CF token is an extra ingress layer in front of - not a replacement for -
the ESET account credentials. Cloud requests never carry these headers.
Resilience
OAuth2 with proactive refresh ~5 min before token expiry and a forced refresh + retry on 401.
429 retries with exponential backoff (up to 3 attempts, honours
Retry-After).Pagination (
nextPageToken) walked transparently.202 long-polling with the
response-idheader, up to 10 minutes.
Response shaping (context-window protection)
A single uncapped list_* call can return hundreds of KB - enough to
overflow a model's context. Two transformations are applied to every
tool response:
fieldsprojection - every GET tool exposes an optionalfields: [string]parameter that filters each list-item down to the requested keys (e.g.["uuid", "displayName"]). Applied server-side after fetch.Byte cap (
ESET_MCP_RESPONSE_BYTES_MAX, default 100 KB) - if a payload still exceeds the budget, the longest list is trimmed while every top-level field (nextPageToken,totalSize, …) is preserved, and a_cappedmetadata block is attached with an actionable hint on how to continue. Agents retain full access to the data through pagination.
Agent-friendly errors
HTTP errors are mapped to readable hints: 403 → check Permission Sets in ESET PROTECT Hub; 401 → server refreshes the token automatically; 429 → back off; 5xx → retry shortly.
Observability (logs + Prometheus)
Structured logs to stderr. Text (default) for dev, JSON Lines for prod log shippers via
ESET_MCP_LOG_FORMAT=json. Every tool call, token refresh, HTTP retry and pool eviction emits a typedeventrecord with low-cardinality fields (tool, deployment, status, duration_ms, response_bytes, ...).Prometheus metrics at an opt-in
/metricsendpoint (ESET_MCP_METRICS_ENABLED=true, requirespip install eset-mcp[metrics]). Counters for tool calls, token refreshes, HTTP retries, cap hits; histograms for tool duration and response sizes; gauge for client pool size.What never enters logs or metrics: passwords,
Authorizationheaders, CF Access secrets, request/response bodies, query strings, substituted path parameters (which can leak UUIDs). A defensive deny-list in the logger strips known-sensitive keys before any formatter sees them.Failure isolation: telemetry emission is wrapped in a try/except so a broken metrics registry or formatter can never turn a successful tool call into an error to the agent.
/metricsreturns 500 (not 503) if exposition ever raises - the worker stays up.Quieting in production: set
ESET_LOG_LEVEL=WARNINGto mute the per-call INFO events but keep retries / errors visible; setESET_LOG_LEVEL=ERRORto silence everything but hard failures. Disable metrics entirely withESET_MCP_METRICS_ENABLED=false(default). The three knobs are independent.
Architecture at a glance
The simplest setup: credentials in .env, one MCP host, one ESET cloud
region. Good for personal use, a single team, or a desktop AI client like
Claude Desktop or Claude Code.
For real multi-tenant or enterprise deployments, put a credentials manager in front of ESET-MCP. The diagram below shows one such pattern using IBM mcp-context-forge as the "creds management" layer - any equivalent MCP gateway (or your own auth proxy) works the same way:
The forge holds per-tenant secrets and injects Authorization: Basic,
X-ESET-Region, X-ESET-Server-URL, and X-ESET-CF-Access-* headers per
request. ESET-MCP routes each request to the right backend (cloud region,
on-prem PROTECT console, or on-prem behind Cloudflare Access) and the
per-tenant LRU client pool keeps OAuth tokens fully isolated between
tenants. This is a working pattern, not aspirational - the headers, pool
keys, and routing rules described here are all in the test suite under
tests/test_concurrency.py and tests/test_onprem.py.
Security
Credentials
In
envmode the password is read once at startup and kept in memory.In
basicmode the password is on the wire only for the duration of the request, and in memory only while the per-tenant client is hot in the LRU pool. It is never logged.The pool key uses a SHA-256 hash of the password rather than the password itself.
OAuth access/refresh tokens are held per-tenant; tokens never cross tenant boundaries within a single session.
Authentication modes & transport
Mode | Transport allowed | Credentials source |
| stdio or http |
|
| http only |
|
basic mode over plain HTTP would leak passwords. The server enforces
HTTP transport for basic mode at startup but does not enforce TLS -
that is the deployment's job. The prod docker-compose profile fronts
the server with Caddy + Let's Encrypt.
Missing / malformed Authorization in basic mode → HTTP 401 with a
WWW-Authenticate: Basic challenge. Unknown region in X-ESET-Region
→ HTTP 400. An unapproved on-prem origin is rejected with HTTP 403.
RO / RW isolation
Two independent layers:
Catalog hiding -
list_toolsfilters out every non-GET tool in RO mode. The agent never sees write tools.Defence-in-depth gate -
call_toolvalidates the tool's declared mode againstESET_MODEbefore any HTTP request goes out. Hard-coded clients, prompt-injection attempts, and stale agent snapshots all hit the gate and receive a structuredModeForbiddenErrortext response (no exception, no network call).
In RW mode, mutating tools carry destructiveHint: true so MCP hosts
that respect annotations can require a per-call confirmation.
Per-tenant isolation (basic-auth mode)
Auth headers are parsed in dedicated ASGI middleware and stashed in a request scope. Handlers use the SDK's explicit HTTP request, so legacy session tasks cannot retain another request's identity. Legacy sessions are bound to credentials, region/origin, CF pair and TLS/network policy.
Each request resolves to a
Credentialsinstance keyed by the complete connection identity. Passwords and CF values are hashed in the index; hashes must not be logged.An LRU bound on the client pool prevents unbounded memory growth from random-credential spraying.
Network surface
The explicit
http/devprofiles publish only127.0.0.1:8765and require Basic credentials.In the
prodprofile the MCP container has no published port - Caddy joins the same docker bridge network and proxies HTTPS in. The only host ports are 80 (HTTP-01 ACME) and 443 (HTTPS).Cloud traffic goes to fixed ESET regional domains. On-prem traffic goes to the configured default or an explicitly allowed origin. DNS is checked at connection time; redirects and implicit environment proxies are disabled.
Dependency & code audit
Ruff: clean (
select = E F W I B UP RUF).Runtime dependencies include
mcp,httpx,httpcore,jsonschema,pydanticandpython-dotenv; exact versions are inrequirements.lock. Plusstarlette+uvicornwhen running HTTP.
Out of scope (by design)
No webhook receivers.
No persistent token storage; application logs go to stderr. Caddy error logs remove request headers and URI.
No on-disk caching of OAuth tokens.
No write-back of
basic-mode credentials to disk.
Responsible disclosure
Please open a private security advisory rather than a public issue: https://github.com/maciekaz/ESET-MCP/security/advisories/new.
Quick start
Use the signed 2.0.0 image. Upgrading from v1 requires the
configuration changes below; the :1 tag stays on the v1 line.
cp .env.example .env # fill in ESET_USER / ESET_PASSWORD / ESET_REGION
docker run --rm -i --env-file .env ghcr.io/maciekaz/eset-mcp:2.0.0Published-image pin policy:
:2- latest 2.x.x (updates within the major):2.0- latest 2.0.x (updates within the minor):2.0.0- exact version:latest- most recent stable release; may cross major versions:main/:sha-<short>- edge builds from main (not for production)
Wire up to Claude Desktop / Claude Code (stdio)
// claude_desktop_config.json
{
"mcpServers": {
"eset": {
"command": "docker",
"args": ["run", "--rm", "-i", "--env-file", "/absolute/path/to/.env",
"ghcr.io/maciekaz/eset-mcp:2.0.0"]
}
}
}HTTP transport (local Basic authentication)
docker run -d --name eset-mcp \
--env-file .env -p 127.0.0.1:8765:8765 \
-e ESET_MCP_TRANSPORT=http -e ESET_MCP_HTTP_HOST=0.0.0.0 \
-e ESET_AUTH_MODE=basic \
ghcr.io/maciekaz/eset-mcp:2.0.0
# MCP endpoint: http://localhost:8765/mcpSend the ESET credentials in the Basic header as shown below. For remote access, use the production HTTPS profile and configure its public host.
Verify the image (cosign keyless)
Verify the release workflow identity and pin the resolved image digest for deployments:
cosign verify \
--certificate-identity 'https://github.com/maciekaz/ESET-MCP/.github/workflows/publish-image.yml@refs/tags/v2.0.0' \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
ghcr.io/maciekaz/eset-mcp:2.0.0From source (contributors / local hacking)
git clone https://github.com/maciekaz/ESET-MCP.git
cd ESET-MCP
cp .env.example .env
python -m venv .venv && source .venv/bin/activate
pip install --require-hashes -r requirements-dev.lock
pip install --no-deps --no-build-isolation -e .
eset-mcpDocker Compose (builds this checkout)
docker compose --profile http up --build -d eset-mcp-http
# MCP endpoint: http://localhost:8765/mcpThe compose file builds this checkout as eset-mcp:2.0.0-local. HTTP
profiles use Basic authentication. Published images described above are
release artifacts; this working tree does not publish or update them.
One-off stdio via compose:
docker compose --profile stdio run --build --rm eset-mcp-stdioHacking on the source? Use the dev profile to build from your local checkout instead of pulling:
docker compose --profile dev up --build eset-mcp-http-devConfiguration
All settings live in .env. Required fields are marked in
.env.example.
Variable | Default | Purpose |
|
|
|
| - | API user (required in |
| - | API password (required in |
|
|
|
|
|
|
|
|
|
|
| HTTP bind address |
|
| HTTP port |
|
| Per-call response byte cap; |
|
|
|
|
|
|
|
| Mount Prometheus |
|
| Where to mount the metrics endpoint |
|
|
|
| - |
|
|
| Set |
|
| Preserve historical JSON login; |
|
| JSON mapping ESET usernames to allowed non-default HTTPS origins |
| empty | Optional comma-separated CIDRs; default allows private networks, rejects loopback/link-local/special addresses |
| empty | Explicit PEM CA file for Cloud/On-Prem; use instead of disabling verification |
| loopback hosts | Comma-separated HTTP Host values, optional |
| empty | Explicit browser origins; an absent Origin is accepted |
|
| Explicit override for env-auth on non-loopback listeners behind an authenticated gateway |
| - | Cloudflare Access Service Token client-id (on-prem behind CF) |
| - | Cloudflare Access Service Token client-secret (paired with the above) |
| - | Domain Caddy issues a TLS cert for ( |
| - | Email Let's Encrypt uses for renewals ( |
Use a dedicated API user - not your console login. Create one in ESET PROTECT Hub / ESET Business Account → API users.
Multi-tenant deployment (basic-auth mode)
# .env
ESET_AUTH_MODE=basic
ESET_MCP_TRANSPORT=http
ESET_REGION=eu # default region; clients can override per requestEvery HTTP request must carry:
Header | Required | Notes |
| yes |
|
| no | Override default region ( |
| no | Route this request to an on-prem PROTECT console (e.g. |
| no | Cloudflare Access Service Token client-id (on-prem behind CF Access) |
| no | Paired with the above - both must be sent together |
Example Python client:
import base64
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
token = base64.b64encode(b"api-user@tenant.tld:secret").decode()
headers = {"Authorization": f"Basic {token}", "X-ESET-Region": "us"}
async with streamablehttp_client(
"https://eset-mcp.example.com/mcp/", headers=headers
) as (r, w, _):
async with ClientSession(r, w) as session:
await session.initialize()
tools = await session.list_tools()⚠️ Basic auth without TLS leaks credentials. Always run
basicmode behind HTTPS.
On-prem ESET PROTECT support
ESET ships PROTECT as both a cloud service (the ESET Connect API at
*.eset.systems) and an on-prem console customers self-host. The on-prem
REST API lives on a single host (default port 9443) and uses a different
authentication endpoint - POST /GetTokens with a JSON body and a
camelCase response - but otherwise shares the URL structure of the cloud
API. ESET-MCP supports both, in the same process.
How the server decides cloud vs on-prem
| What controls the deployment per request |
| Static: |
| Per request: presence of |
So a single MCP server can front the cloud for most clients and route
specific requests to one or more on-prem consoles - keyed entirely by which
URL each client sends in X-ESET-Server-URL.
Single-tenant on-prem (env mode)
# .env
ESET_AUTH_MODE=env
ESET_DEPLOYMENT=onprem
ESET_ONPREM_SERVER_URL=https://protect.company.local:9443
ESET_ONPREM_VERIFY_SSL=true # set to false only for self-signed certs you trust
ESET_USER=api-user@company.local
ESET_PASSWORD=...Multi-tenant on-prem (basic auth, per-request URL)
# .env
ESET_AUTH_MODE=basic
ESET_MCP_TRANSPORT=http
ESET_DEPLOYMENT=cloud # default; clients opt into on-prem per-request
# ESET_ONPREM_SERVER_URL is optional - if set it becomes the on-prem default
ESET_ONPREM_ORIGINS='{"api-user@example.com":["https://protect.client-a.local:9443"]}'Client targeting on-prem:
headers = {
"Authorization": f"Basic {token}",
"X-ESET-Server-URL": "https://protect.client-a.local:9443",
}Same MCP server, different request - same headers minus X-ESET-Server-URL
stays on cloud.
What works on on-prem vs cloud
The tool catalog is identical for both deployments (all 101 OpenAPI-derived tools plus the 4 composites). At call time the server uses cloud paths for cloud credentials and on-prem paths for on-prem credentials.
Historical mappings retained:
device_*,asset_groups_*,policy_*andtask_*retain their existing paths and overrides. Endpoint availability depends on the PROTECT version and installed modules.Cloud-only modules:
incident_*,mobile_*,wap_*,nap_*,quarantine_*and most ofvuln_*correspond to separate ESET products (ESET Inspect, Cloud Office Security, MDM) that are not part of the on-prem PROTECT installation. Calling them against an on-prem console may return an ESET error; failures are sanitized and returned withisError=true. The historical catalog is preserved for compatibility.Path overrides: a few endpoints have a different URL on-prem - e.g.
POST /v1/devices/{uuid}:renameis:renameDeviceon-prem. These are declared ineset_mcp/openapi/onprem-path-overrides.jsonand applied automatically when the request targets on-prem.
Cloudflare Access in front of the on-prem console
When the on-prem PROTECT console is exposed via a Cloudflare tunnel and gated by Cloudflare Access, MCP can authenticate as a service token. The chain becomes MCP → Cloudflare Access → ESET on-prem.
Two values per token pair, supplied either via .env:
ESET_ONPREM_CF_ACCESS_CLIENT_ID=abc1234567890.access
ESET_ONPREM_CF_ACCESS_CLIENT_SECRET=<long-secret>…or per-request in basic-auth mode (overrides the env defaults - handy when each tenant has its own tunnel and its own service token):
headers = {
"Authorization": f"Basic {token}",
"X-ESET-Server-URL": "https://protect.client-a.local:9443",
"X-ESET-CF-Access-Client-Id": "abc1234567890.access",
"X-ESET-CF-Access-Client-Secret": "<long-secret>",
}MCP translates the X-ESET-CF-* input headers into the actual
CF-Access-Client-Id / CF-Access-Client-Secret headers that Cloudflare
Access expects, and attaches them to every outbound call - both the
POST /GetTokens auth handshake and every subsequent ESET API request.
The CF secret is treated like the password: never logged, only its SHA-256 hash enters the client pool key. Rotating the secret mints a fresh client
fresh ESET token. Cloud requests never carry CF Access headers regardless of env defaults - ESET Connect is a public SaaS.
Security notes for on-prem
X-ESET-Server-URLaccepts onlyhttps://URLs with no path, query or fragment. Trailing slashes are stripped. Anything else → HTTP 400.ESET_ONPREM_VERIFY_SSL=falsedisables TLS certificate verification and exposes the connection to MITM. The server logs a single WARNING per client construction when it's disabled. Use only on trusted intranets with self-signed certs you cannot replace.On-prem tokens are held in memory per
(user, password_hash, server_url, cf_secret_hash)- same isolation rules as cloud tokens. The pool keys them separately so cloud and on-prem clients never collide, and two clients hitting the same on-prem URL with different CF service tokens get separate pool entries.Sending only one of the two
X-ESET-CF-*headers returns HTTP 400 rather than silently falling back to the env default (almost certain operator typo).
Production deployment (HTTPS via Caddy)
The prod docker-compose profile launches Caddy in front of the MCP
server. Caddy fetches a Let's Encrypt cert on first start (HTTP-01
challenge - ports 80 / 443 must be reachable from the public internet)
and proxies HTTPS to the internal MCP container.
# .env
ESET_AUTH_MODE=basic
ESET_PUBLIC_DOMAIN=eset-mcp.example.com
ESET_ACME_EMAIL=ops@example.com
docker compose --profile prod up --build -d
# MCP endpoint: https://eset-mcp.example.com/mcpYou get:
HTTPS on 443 with auto-renewing Let's Encrypt cert.
HTTP-01 challenge on 80.
MCP container bound only to the docker bridge network - no published port.
gzip / zstd compression; raw access logs disabled and error-log headers removed.
Only
/mcpis public; metrics stay on the private container network.
Tools, resources & prompts
Composite high-level tools
Tool | Returns |
| Case-insensitive substring matches across devices / users / policies / groups |
| Device record + recent detections + vulnerabilities + recent scans |
| Incident + comments + related detections + affected devices |
| Newest detections in a time window, sorted by |
Each composite degrades gracefully when a sub-call returns 403/404
(e.g. on tenants missing a module). The shape carries skipped /
truncated flags where applicable.
Resources
eset://config/mode-ROorRW.eset://config/region- current region (per-request in basic-auth mode).eset://config/deployment-cloudoronprem (<server-url>)for this request.eset://config/tools-catalog- JSON catalog of mode-allowed raw business tools (name, mode, method, path, service, description).eset://docs/rate-limits- quick reminder about the 10 req/s ceiling.
Prompts
audit_inactive_devices(days=30)- offboarding candidates.vulnerability_report- per-device CVE report.incident_triage- open incidents + related detections.
Architecture
eset_mcp/
├── __main__.py # entrypoint - stdio or HTTP, wires resolver + pool
├── server.py # MCP server (tools / resources / prompts) + telemetry
├── credentials.py # Credentials + explicit per-request resolution
├── middleware.py # ASGI Basic-auth middleware (basic mode only)
├── client_pool.py # LRU pool of EsetHttpClient keyed by (user, region, ...)
├── http_client.py # async httpx + 202 polling + 429 retry + 401 refresh
├── auth.py # CloudTokenManager (OAuth2) + OnPremTokenManager (/GetTokens)
├── regions.py # cloud region → per-service domains + on-prem URL resolver
├── modes.py # RO/RW gate
├── errors.py # HTTP error → agent-friendly text
├── config.py # .env loading
├── response_shaping.py # fields projection + byte cap
├── composite_tools.py # hand-written high-level tools
├── tools_loader.py # generator: tools from OpenAPI specs + on-prem path overrides
├── observability/ # JSON/text structured logging + Prometheus metrics
└── openapi/ # 16 ESET Connect OpenAPI 3.0.1 specs + onprem path overridesTests
PYTHON_DOTENV_DISABLED=1 ESET_RUN_LIVE_TESTS=0 python -m pytest tests audits -q
ruff check eset_mcp tests auditsThe default suite covers API contracts, synthetic failures, MCP HTTP and stdio,
and loopback TLS. It blocks external connections and does not load .env.
To run integration tests with configured ESET credentials, explicitly set
ESET_RUN_LIVE_TESTS=1. See the test instructions for baseline
fixture maintenance and container probes.
Refreshing the OpenAPI specs
cd eset_mcp/openapi
for name in business-account application-management asset-management automation \
device-management iam incident-management installer-management \
mobile-device-management network-access-protection patch-management \
policy-management quarantine-management user-management \
vulnerability-management web-access-protection; do
curl -sO "https://eu.esetconnect.eset.systems/swagger/api/${name}.json"
donetests/test_catalog_vs_openapi.py flags any new or changed operations
after a refresh.
License
MIT
Available Tools
51 toolsapp_executables__get_executableCRead-onlyIdempotent
Get executable - (GET /v1/executables/{executableUuid}) - Get details of a specific executable.
Inputs: executableUuid (required), fields.
app_executables__list_executablesCRead-onlyIdempotent
List executables - (GET /v1/executables) - List all the executables.
Inputs: fields, pageSize, pageToken.
device_device_groups__list_groupsBRead-onlyIdempotent
List all device groups - (GET /v1/device_groups) - Hierarchy can be reconstructed from the returned device_groups.
Inputs: fields, pageSize, pageToken.
device_device_groups__list_member_devicesBRead-onlyIdempotent
List devices in device group - (GET /v1/device_groups/{groupUuid}/devices) - Return the list of devices within a [device group].
Info: The lifecycle of membership and devices are uncorrelated: a device can be a member of many arbitrary groups without a device entity knowing that. This is also supported by the fact that some systems responsible for the device-group membership are autonomous and do not need to update the device state to remember membership.
As a
Inputs: groupUuid (required), fields, pageSize, pageToken, +1 more.
device_devices__batch_get_devicesBRead-onlyIdempotent
Get batch of devices - (GET /v1/devices:batchGet) - Retrieves a specific set of devices at a consistent time point.
Info: Modeled after Batch methods: Get
Inputs: fields, devicesUuids.
device_devices__get_deviceCRead-onlyIdempotent
Get device details - (GET /v1/devices/{deviceUuid}) - Get details of a [device].
Inputs: deviceUuid (required), fields.
device_devices__list_devicesCRead-onlyIdempotent
List managed devices - (GET /v1/devices) - List all the managed [device]s.
Inputs: fields, isMuted, pageSize, pageToken, +2 more.
device_full_profileARead-onlyIdempotent
One call → device record + recent detections + vulnerabilities + recent scans. Use when answering 'what do you know about this machine'. Each sub-section degrades gracefully if the tenant lacks a module.
Inputs: deviceUuid (required).
eset_searchARead-onlyIdempotent
Case-insensitive substring search across devices, users, policies and groups. Returns matching items with their UUIDs and which field matched. Use this instead of list_* + manual filtering when you have a name fragment (e.g. 'jeff', 'laptop-23', 'finance').
Inputs: query (required), kinds, limit_per_kind.
iam_identity_provider__list_rolesCRead-onlyIdempotent
List roles - (GET /v2/role-assignments) - List [role]s of [subject]s.
Info: Not only Users are [subject]s, but anything that can have roles attached. For example, Devices.
Info: Modeled after List role assignments.
Might be filtered by the specified [subject] or [scope]s.
If the filters are left empty, all the roles availa
Inputs: fields, orderBy, pageSize, pageToken, +3 more.
iam_permissions__list_permissionsBRead-onlyIdempotent
List permissions - (GET /v2/permissions) - List all possible permissions.
Inputs: fields, pageSize, pageToken.
incident_detection_groups__get_detection_groupBRead-onlyIdempotent
Get detection group - (GET /v2/detection-groups/{detectionGroupUuid}) - Get details about a detection group.
Inputs: detectionGroupUuid (required), fields.
incident_detection_groups__list_detection_groupsBRead-onlyIdempotent
List detection groups - (GET /v2/detection-groups) - Return a list of all the [detection group]s matching criteria.
Inputs: fields, endTime, pageSize, pageToken, +3 more.
incident_detections__get_detection_v1CRead-onlyIdempotent
GET /v1/detections/{detectionUuid} - (GET /v1/detections/{detectionUuid})
Inputs: detectionUuid (required), fields.
incident_detections__get_detection_v2CRead-onlyIdempotent
Get detection - (GET /v2/detections/{detectionUuid}) - Get detection.
Inputs: detectionUuid (required), fields.
incident_detections__list_detections_v1CRead-onlyIdempotent
List detections - (GET /v1/detections) - Return a list of all the [detection]s matching criteria.
Inputs: fields, endTime, pageSize, pageToken, +2 more.
incident_detections__list_detections_v2CRead-onlyIdempotent
List detections - (GET /v2/detections) - Return a list of all the [detection]s matching criteria.
Inputs: fields, endTime, pageSize, pageToken, +2 more.
incident_edr_rule_exclusions__get_edr_rule_exclusionBRead-onlyIdempotent
Get EDR rule exclusion - (GET /v2/edr-rule-exclusions/{exclusionUuid}) - Get details of an [EDR rule exclusion].
Inputs: exclusionUuid (required), fields.
incident_edr_rule_exclusions__list_edr_rule_exclusionsCRead-onlyIdempotent
List EDR rule exclusions - (GET /v2/edr-rule-exclusions) - List [EDR rule exclusion]s matching criteria.
Inputs: fields, pageSize, pageToken, includeTotalSize.
incident_edr_rules__get_edr_ruleCRead-onlyIdempotent
Get EDR rule - (GET /v2/edr-rules/{ruleUuid}) - Get [EDR rule] details.
Inputs: ruleUuid (required), fields.
incident_edr_rules__list_edr_rulesCRead-onlyIdempotent
List EDR rules - (GET /v2/edr-rules) - List [EDR rule]s matching the criteria.
Inputs: fields, pageSize, pageToken, severityLevel, +1 more.
incident_full_contextARead-onlyIdempotent
One call → incident + comments + related detections + affected devices. Detections and devices are capped at 10 each to stay within rate limits; the response carries a 'truncated' flag if more exist.
Inputs: incidentUuid (required).
incident_incident_comments__get_incident_commentBRead-onlyIdempotent
Get incident comment - (GET /v2/incidents/{incidentUuid}/comments/{commentUuid}) - Get an Incident Comment.
Preconditions:
incident_uuid must point to an existing incident.
Inputs: commentUuid (required), incidentUuid (required), fields.
incident_incident_comments__list_incident_commentsARead-onlyIdempotent
List incident comments - (GET /v2/incidents/{incidentUuid}/comments) - List Comments that are accessible to the caller. The user must always specify the uuid of an Incident in arguments; therefore, the list is always provided only for one Incident.
Comments are ordered by create_time.
Inputs: incidentUuid (required), fields.
incident_incidents__get_incidentCRead-onlyIdempotent
Get incident - (GET /v2/incidents/{incidentUuid}) - Get details of a specific incident.
Inputs: incidentUuid (required), fields.
incident_incidents__list_incidentsCRead-onlyIdempotent
List incidents - (GET /v2/incidents) - Returns a list of incidents matching the filter.
The list is ordered according to order_by.
Inputs: fields, filter, orderBy, pageSize, +1 more.
installer_installers__get_installerCRead-onlyIdempotent
Get installer - (GET /v1/installers/{installerUuid}) - Get details of the requested [installer].
Inputs: installerUuid (required), fields.
installer_installers__list_installersCRead-onlyIdempotent
List installers - (GET /v1/installers) - List all installers available to the caller.
Inputs: fields, usable, pageSize, pageToken.
latest_detectionsARead-onlyIdempotent
Newest detections in a time window, sorted by occurTime descending. Use this - NOT raw incident_detections__list_detections_* - when answering 'what's the latest detection / what happened recently'. The raw list endpoints do NOT sort by date, so a first-page sort silently returns stale rows. This composite does v2→v1 fallback, paginates the time window, and sorts locally.
Inputs: hours, limit, severity_min.
nap_network_access_configurator__get_ip_setCRead-onlyIdempotent
Get IP set - (GET /v1/policies/{policyUuid}/ip-sets/{ipSetUuid}) - Get details about an IP set.
Inputs: ipSetUuid (required), policyUuid (required), fields.
nap_network_access_configurator__list_ip_setsBRead-onlyIdempotent
List IP sets - (GET /v1/policies/{policyUuid}/ip-sets) - List all IP sets.
Inputs: policyUuid (required), fields, pageSize, pageToken.
patch_patch_management__list_device_patching_detailsBRead-onlyIdempotent
List patching details - (GET /v1/patching-process-details) - History is pruned repeatedly to prevent database flooding. Entries from at least the previous 30 days should be available at any time.
Inputs: fields, pageSize, pageToken, deviceUuid, +3 more.
patch_patch_management__list_recent_application_patching_detailsARead-onlyIdempotent
List recent application patching details - (GET /v1/application-patching-processes/recent/details) - List the patching details of all application patching attempts performed recently (within the last few days).
The list might be empty if no application patching has been performed recently. Stale data (that is, not recent) is removed from the list over the course of several days.
Inputs: fields.
patch_unpatched_devices__list_device_patchesBRead-onlyIdempotent
List device patches - (GET /v1/device-patches) - If the same application, package or operating system is unpatched on multiple devices, the collection would contain entities for each device and patch individually.
The list may be empty if no patches for any device are found.
Inputs: fields, pageSize, pageToken, patchType, +2 more.
policy_policies__get_policyCRead-onlyIdempotent
Get policy - (GET /v2/policies/{policyUuid}) - Get policy details.
Inputs: policyUuid (required), fields.
policy_policies__list_policiesBRead-onlyIdempotent
List policies - (GET /v2/policies) - List all the policies accessible to the caller (based on the token).
Inputs: fields, pageSize, pageToken.
policy_policy_assignments__get_policy_assignmentBRead-onlyIdempotent
Get policy assignment - (GET /v2/policy-assignments/{assignmentUuid}) - Get details of the given policy assignment.
Inputs: assignmentUuid (required), fields.
policy_policy_assignments__list_policy_assignmentsCRead-onlyIdempotent
List policy assignments - (GET /v2/policy-assignments) - List all the policy assignments available to the caller.
Inputs: fields, pageSize, pageToken, policyUuid, +4 more.
quarantine_quarantined_objects__get_quarantined_objectCRead-onlyIdempotent
Get quarantined object - (GET /v1/quarantined-objects/{objectUuid}) - Get a quarantined object.
Inputs: objectUuid (required), fields.
quarantine_quarantined_objects__get_quarantined_objects_countCRead-onlyIdempotent
Get quarantined objects count - (GET /v1/quarantined-objects/count) - Get the count of quarantined objects matching the criteria.
Inputs: fields, filter.fileName, filter.userUuid, filter.objectType, +11 more.
quarantine_quarantined_objects__list_quarantined_objectsCRead-onlyIdempotent
List quarantined objects - (GET /v1/quarantined-objects) - List all quarantined objects matching the criteria in the filter.
Inputs: fields, orderBy, pageSize, pageToken, +14 more.
task_device_tasks__get_taskBRead-onlyIdempotent
Get task - (GET /v1/device_tasks/{taskUuid}) - Get the task entity.
For a complete history, call ListTaskRuns().
Inputs: taskUuid (required), fields.
task_device_tasks__list_task_runsARead-onlyIdempotent
List task runs - (GET /v1/device_tasks/{taskUuid}/runs) - List task history - all the runs of the task.
For the sake of forensics, the [task run]s are listed collectively, not as children of their parent task. Information about task runs might easily survive their parent task.
Info: Modeled based on Jobs: Executions and results with ESET specific vocabulary.
Inputs: taskUuid (required), fields, pageSize, pageToken, +2 more.
task_device_tasks__list_tasksCRead-onlyIdempotent
List tasks - (GET /v1/device_tasks) - List all device tasks matching criteria.
Inputs: fields, pageSize, pageToken.
user_users__get_userARead-onlyIdempotent
Get user - (GET /v1/users/{userUuid}) - Retrieves the details of a specific user based on their unique identifier.
Inputs: userUuid (required), fields.
user_users__list_usersCRead-onlyIdempotent
List users - (GET /v1/users) - Retrieves a list of users, optionally filtered by certain criteria defined in the user filter.
Inputs: email, fields, pageSize, pageToken, +12 more.
vuln_vulnerability_management__list_recent_scan_detailsARead-onlyIdempotent
List recent scan details - (GET /v1/scans/recent) - List the scan details of all vulnerability scan attempts performed recently (within the last few days).
The list might be empty if no vulnerability scans have been performed recently. Stale data (that is, not recent) is removed from the list over the course of several days.
Inputs: fields, pageSize, pageToken, deviceUuid, +1 more.
vuln_vulnerable_devices__list_device_os_vulnerabilitiesARead-onlyIdempotent
List device operating system vulnerabilities - (GET /v1/device-os-vulnerabilities) - List vulnerabilities of the operating system of the given device.
Note: Besides vulnerabilities of the Linux kernel, there are also some "core packages" whose vulnerabilities are treated as operating system vulnerabilities. For example: glibc, systemd, etc.
Such vulnerabilities are reported twice, once as an operating system vulnerability and once as a package vulnerability.
Inputs: fields, pageSize, pageToken, deviceUuid, +1 more.
vuln_vulnerable_devices__list_device_vulnerabilitiesARead-onlyIdempotent
List device vulnerabilities - (GET /v1/device-vulnerabilities) - List device vulnerabilities where the vulnerabilities fit the criteria from the request.
Each vulnerability is treated individually; that is, if the device has multiple vulnerabilities, it will be listed multiple times.
Inputs: fields, pageSize, pageToken, deviceUuid, +2 more.
vuln_vulnerable_devices__list_vulnerable_devicesBRead-onlyIdempotent
List vulnerable devices - (GET /v1/vulnerable-devices) - List vulnerable devices matching the criteria from the request.
Even if a device has multiple vulnerabilities, it will be listed only once.
Inputs: fields, pageSize, pageToken, deviceGroupUuid.
wap_web_address_rules_configurator__list_web_address_rulesCRead-onlyIdempotent
GET /v2/policies/{policyUuid}/web-address-rules - (GET /v2/policies/{policyUuid}/web-address-rules)
Inputs: policyUuid (required), fields, includeDomain.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 51 tools
Most resources have a clean list/get split, but there are near-duplicate pairs: incident_detections__list_detections_v1 and _v2, plus a third composite latest_detections that explicitly tells the agent not to use the raw list endpoints. Similar overlap exists between device_devices__list_devices, eset_search, and device_full_profile. The descriptions do steer the agent, but the versioned twins and raw-vs-composite overlap create real misselection risk.
The bulk of the surface follows a predictable `<domain>_<resource>__<verb>_<noun>` snake_case pattern (list_incidents, get_device, list_quarantined_objects). Four composite convenience tools (eset_search, device_full_profile, incident_full_context, latest_detections) break the verb_noun convention with bare noun phrases, but they are few and clearly purposeful. Minor deviation, not chaotic.
51 tools is heavy for a single MCP surface, and the bulk is read-only list/get boilerplate spanning ~12 sub-domains (incidents, devices, policies, patches, vulns, quarantine, IAM, NAP, WAP). Several slots are spent on redundant v1/v2 detection endpoints and overlapping composite wrappers. Trimming the versioned duplicates and folding some list/get pairs would make this far more usable.
Read coverage is genuinely broad — incidents, detections, devices, groups, policies, tasks, patches, vulnerabilities, quarantine, users, installers — with sensible count and history endpoints. However, the surface is entirely GET-only: no incident resolution/update, no comment creation (list/get only), no policy assignment writes, no task creation, and no quarantine release/remediation actions. For an EDR/incident response domain, those missing mutations are notable gaps that would dead-end many agent workflows.
Maintenance
Related MCP Connectors
MCP gateway and cloud hosting for MCP servers, agents and apps like RAG, managed from your agent.
MCP server for Product Management
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA powerful executable server for running Model Context Protocol services that supports tool chain execution, multiple MCP services management, and a pluggable tool system for complex automation workflows.177MIT
- AlicenseNot gradedqualityDmaintenanceMCP Server for the Edgee API, enabling organization management, project operations, component management, and user administration through the Model Context Protocol.Apache 2.0
- AlicenseBqualityBmaintenanceA Model Context Protocol server for complete shell and SSH mastery, enabling command execution, interactive sessions, file transfer, and port forwarding with auditing and policy controls.18153 PyPI3Apache 2.0
- AlicenseBqualityBmaintenancessh-mcp-pro is a secure Model Context Protocol (MCP) server for SSH automation, enabling clients to open SSH sessions, run commands, manage files, transfer artifacts, create tunnels, and perform package/service operations under policy control.464,967 npm2AGPL 3.0