Skip to main content
Glama
ESET-MCP

ESET-MCP

by maciekaz

ESET-MCP

Tests License: MIT MCP spec

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 from list_tools entirely.

  • ESET_MODE=RW → all 105 tools advertised; mutating tools carry destructiveHint: true in 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 pass Authorization: Basic <base64(user:password)> per request (plus optional X-ESET-Region for a different cloud region, or X-ESET-Server-URL to 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-id header, 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:

  • fields projection - every GET tool exposes an optional fields: [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 _capped metadata 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 typed event record with low-cardinality fields (tool, deployment, status, duration_ms, response_bytes, ...).

  • Prometheus metrics at an opt-in /metrics endpoint (ESET_MCP_METRICS_ENABLED=true, requires pip 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, Authorization headers, 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. /metrics returns 500 (not 503) if exposition ever raises - the worker stays up.

  • Quieting in production: set ESET_LOG_LEVEL=WARNING to mute the per-call INFO events but keep retries / errors visible; set ESET_LOG_LEVEL=ERROR to silence everything but hard failures. Disable metrics entirely with ESET_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.

Single-tenant: one ESET account, one deployment

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:

Multi-tenant: many clients, one MCP, many backends

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 env mode the password is read once at startup and kept in memory.

  • In basic mode 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

env

stdio or http

.env (ESET_USER / ESET_PASSWORD)

basic

http only

Authorization: Basic header per request

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:

  1. Catalog hiding - list_tools filters out every non-GET tool in RO mode. The agent never sees write tools.

  2. Defence-in-depth gate - call_tool validates the tool's declared mode against ESET_MODE before any HTTP request goes out. Hard-coded clients, prompt-injection attempts, and stale agent snapshots all hit the gate and receive a structured ModeForbiddenError text 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 Credentials instance 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/dev profiles publish only 127.0.0.1:8765 and require Basic credentials.

  • In the prod profile 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, pydantic and python-dotenv; exact versions are in requirements.lock. Plus starlette + uvicorn when 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:2.0.0

Published-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/mcp

Send 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:2.0.0

From 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-mcp

Docker Compose (builds this checkout)

docker compose --profile http up --build -d eset-mcp-http
# MCP endpoint: http://localhost:8765/mcp

The 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-stdio

Hacking 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-dev

Configuration

All settings live in .env. Required fields are marked in .env.example.

Variable

Default

Purpose

ESET_AUTH_MODE

env

env (single tenant) or basic (multi tenant)

ESET_USER

-

API user (required in env mode)

ESET_PASSWORD

-

API password (required in env mode)

ESET_MODE

RO

RO (read-only catalog) or RW

ESET_REGION

eu

eu / de / us / ca / jpn

ESET_MCP_TRANSPORT

stdio

stdio or http

ESET_MCP_HTTP_HOST

127.0.0.1

HTTP bind address

ESET_MCP_HTTP_PORT

8765

HTTP port

ESET_MCP_RESPONSE_BYTES_MAX

100000

Per-call response byte cap; 0 disables

ESET_LOG_LEVEL

INFO

DEBUG / INFO / WARNING / ERROR

ESET_MCP_LOG_FORMAT

text

text (dev, human-readable) or json (prod log shippers)

ESET_MCP_METRICS_ENABLED

false

Mount Prometheus /metrics; requires eset-mcp[metrics]

ESET_MCP_METRICS_PATH

/metrics

Where to mount the metrics endpoint

ESET_DEPLOYMENT

cloud

cloud (ESET Connect) or onprem (customer-hosted PROTECT)

ESET_ONPREM_SERVER_URL

-

https://host[:port] of the on-prem console (req. in env+onprem)

ESET_ONPREM_VERIFY_SSL

true

Set false for on-prem consoles with self-signed certs

ESET_ONPREM_AUTH_STYLE

legacy

Preserve historical JSON login; v13 explicitly enables documented camelCase grants

ESET_ONPREM_ORIGINS

{}

JSON mapping ESET usernames to allowed non-default HTTPS origins

ESET_ONPREM_NETWORKS

empty

Optional comma-separated CIDRs; default allows private networks, rejects loopback/link-local/special addresses

ESET_CA_BUNDLE

empty

Explicit PEM CA file for Cloud/On-Prem; use instead of disabling verification

ESET_MCP_ALLOWED_HOSTS

loopback hosts

Comma-separated HTTP Host values, optional :* port suffix; configure public domain behind a proxy

ESET_MCP_ALLOWED_ORIGINS

empty

Explicit browser origins; an absent Origin is accepted

ESET_MCP_ALLOW_UNAUTHENTICATED_HTTP

false

Explicit override for env-auth on non-loopback listeners behind an authenticated gateway

ESET_ONPREM_CF_ACCESS_CLIENT_ID

-

Cloudflare Access Service Token client-id (on-prem behind CF)

ESET_ONPREM_CF_ACCESS_CLIENT_SECRET

-

Cloudflare Access Service Token client-secret (paired with the above)

ESET_PUBLIC_DOMAIN

-

Domain Caddy issues a TLS cert for (prod profile only)

ESET_ACME_EMAIL

-

Email Let's Encrypt uses for renewals (prod profile only)

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 request

Every HTTP request must carry:

Header

Required

Notes

Authorization

yes

Basic <base64(user:password)>

X-ESET-Region

no

Override default region (eu/de/us/ca/jpn)

X-ESET-Server-URL

no

Route this request to an on-prem PROTECT console (e.g. https://protect.example.com:9443) - see On-prem support

X-ESET-CF-Access-Client-Id

no

Cloudflare Access Service Token client-id (on-prem behind CF Access)

X-ESET-CF-Access-Client-Secret

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 basic mode 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

ESET_AUTH_MODE

What controls the deployment per request

env

Static: ESET_DEPLOYMENT (cloud) or ESET_DEPLOYMENT=onprem + ESET_ONPREM_SERVER_URL

basic

Per request: presence of X-ESET-Server-URL switches that single request to on-prem; absence falls back to the env default (cloud or on-prem)

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_* and task_* 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 of vuln_* 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 with isError=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}:rename is :renameDevice on-prem. These are declared in eset_mcp/openapi/onprem-path-overrides.json and 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-URL accepts only https:// URLs with no path, query or fragment. Trailing slashes are stripped. Anything else → HTTP 400.

  • ESET_ONPREM_VERIFY_SSL=false disables 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/mcp

You 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 /mcp is public; metrics stay on the private container network.


Tools, resources & prompts

Composite high-level tools

Tool

Returns

eset_search(query, kinds?, limit_per_kind?)

Case-insensitive substring matches across devices / users / policies / groups

device_full_profile(deviceUuid)

Device record + recent detections + vulnerabilities + recent scans

incident_full_context(incidentUuid)

Incident + comments + related detections + affected devices

latest_detections(hours=24, limit=10, severity_min?)

Newest detections in a time window, sorted by occurTime desc; v2 → v1 fallback

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 - RO or RW.

  • eset://config/region - current region (per-request in basic-auth mode).

  • eset://config/deployment - cloud or onprem (<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 overrides

Tests

PYTHON_DOTENV_DISABLED=1 ESET_RUN_LIVE_TESTS=0 python -m pytest tests audits -q
ruff check eset_mcp tests audits

The 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"
done

tests/test_catalog_vs_openapi.py flags any new or changed operations after a refresh.


License

MIT

Available Tools

51 tools
app_executables__get_executableC
Read-onlyIdempotent

Get executable - (GET /v1/executables/{executableUuid}) - Get details of a specific executable.

Inputs: executableUuid (required), fields.

app_executables__list_executablesC
Read-onlyIdempotent

List executables - (GET /v1/executables) - List all the executables.

Inputs: fields, pageSize, pageToken.

device_device_groups__list_groupsB
Read-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_devicesB
Read-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_devicesB
Read-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_deviceC
Read-onlyIdempotent

Get device details - (GET /v1/devices/{deviceUuid}) - Get details of a [device].

Inputs: deviceUuid (required), fields.

device_devices__list_devicesC
Read-onlyIdempotent

List managed devices - (GET /v1/devices) - List all the managed [device]s.

Inputs: fields, isMuted, pageSize, pageToken, +2 more.

device_full_profileA
Read-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).

iam_identity_provider__list_rolesC
Read-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_permissionsB
Read-onlyIdempotent

List permissions - (GET /v2/permissions) - List all possible permissions.

Inputs: fields, pageSize, pageToken.

incident_detection_groups__get_detection_groupB
Read-onlyIdempotent

Get detection group - (GET /v2/detection-groups/{detectionGroupUuid}) - Get details about a detection group.

Inputs: detectionGroupUuid (required), fields.

incident_detection_groups__list_detection_groupsB
Read-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_v1C
Read-onlyIdempotent

GET /v1/detections/{detectionUuid} - (GET /v1/detections/{detectionUuid})

Inputs: detectionUuid (required), fields.

incident_detections__get_detection_v2C
Read-onlyIdempotent

Get detection - (GET /v2/detections/{detectionUuid}) - Get detection.

Inputs: detectionUuid (required), fields.

incident_detections__list_detections_v1C
Read-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_v2C
Read-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_exclusionB
Read-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_exclusionsC
Read-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_ruleC
Read-onlyIdempotent

Get EDR rule - (GET /v2/edr-rules/{ruleUuid}) - Get [EDR rule] details.

Inputs: ruleUuid (required), fields.

incident_edr_rules__list_edr_rulesC
Read-onlyIdempotent

List EDR rules - (GET /v2/edr-rules) - List [EDR rule]s matching the criteria.

Inputs: fields, pageSize, pageToken, severityLevel, +1 more.

incident_full_contextA
Read-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_commentB
Read-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_commentsA
Read-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_incidentC
Read-onlyIdempotent

Get incident - (GET /v2/incidents/{incidentUuid}) - Get details of a specific incident.

Inputs: incidentUuid (required), fields.

incident_incidents__list_incidentsC
Read-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_installerC
Read-onlyIdempotent

Get installer - (GET /v1/installers/{installerUuid}) - Get details of the requested [installer].

Inputs: installerUuid (required), fields.

installer_installers__list_installersC
Read-onlyIdempotent

List installers - (GET /v1/installers) - List all installers available to the caller.

Inputs: fields, usable, pageSize, pageToken.

latest_detectionsA
Read-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_setC
Read-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_setsB
Read-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_detailsB
Read-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_detailsA
Read-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_patchesB
Read-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_policyC
Read-onlyIdempotent

Get policy - (GET /v2/policies/{policyUuid}) - Get policy details.

Inputs: policyUuid (required), fields.

policy_policies__list_policiesB
Read-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_assignmentB
Read-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_assignmentsC
Read-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_objectC
Read-onlyIdempotent

Get quarantined object - (GET /v1/quarantined-objects/{objectUuid}) - Get a quarantined object.

Inputs: objectUuid (required), fields.

quarantine_quarantined_objects__get_quarantined_objects_countC
Read-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_objectsC
Read-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_taskB
Read-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_runsA
Read-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_tasksC
Read-onlyIdempotent

List tasks - (GET /v1/device_tasks) - List all device tasks matching criteria.

Inputs: fields, pageSize, pageToken.

user_users__get_userA
Read-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_usersC
Read-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_detailsA
Read-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_vulnerabilitiesA
Read-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_vulnerabilitiesA
Read-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_devicesB
Read-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_rulesC
Read-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

    C2.8/5.0

    Scored across 51 tools

    Disambiguation3/5

    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.

    Naming Consistency4/5

    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.

    Tool Count2/5

    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.

    Completeness3/5

    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

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A 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.
      177
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP Server for the Edgee API, enabling organization management, project operations, component management, and user administration through the Model Context Protocol.
      Apache 2.0
    • A
      license
      B
      quality
      B
      maintenance
      A 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.
      18
      153 PyPI
      3
      Apache 2.0
    • A
      license
      B
      quality
      B
      maintenance
      ssh-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.
      46
      4,967 npm
      2
      AGPL 3.0