scrypted-mcp-plugin (sv-tools/scrypted-mcp-plugin) is an MCP server listed on the M8ven Trust Index. It scores 62 out of 100, grade C. It declares 39 tools. No publisher has claimed this listing.

C
Caution
62/100

scrypted-mcp-plugin

Scrypted plugin that exposes a Streamable HTTP Model Context Protocol endpoint, with OAuth backed by Scrypted user accounts. Lets AI assistants inspect logs, manage plugins, and query devices on the same Scrypted server.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

sv-tools

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes39 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_plugins

List installed Scrypted plugins. Returns for each: Scrypted device `id`, npm `pluginId` (the id passed to reload_plugin / get_plugin_info / kill_plugin), name, and type.

get_plugin_info

Inspect a plugin: pid, pending RPC calls, object count, etc.

reload_plugin

Restart a plugin host process (preserves state, picks up code changes).

kill_plugin

Kill a plugin host without auto-reload — the plugin stays down until you call reload_plugin or the server restarts. Prefer reload_plugin unless you specifically need it stopped.

install_plugin

Install (or upgrade) a plugin from npm. Returns the plugin device id.

update_plugins

Check all installed plugins against npm and upgrade any that are outdated.

npm_info

Query npmjs.org via the Scrypted server. Pass a package name (e.g. "scrypted-kasa") for full metadata, or "-/v1/search?text=keywords:scrypted-plugin" to discover available Scrypted plugins. Returns the raw npm registry response.

rename_device_id

Rename a Scrypted device id. Briefly kills the owning plugin host while it rewrites references — expect a short offline window.

set_mixins

Replace the list of mixins on a device. The provided array fully replaces the device's current mixins — read get_device first if you only want to add or remove one. Mixin ids are device ids of plugins like prebuffer, snapshot, REST, etc.

get_storage

Read a plugin device's persistent KV storage (string keys, string values).

set_storage

Replace a plugin device's persistent KV storage. The provided map fully replaces existing storage — read get_storage first if you only want to change one key.

get_id_for_native_id

Reverse-lookup a Scrypted device id from a plugin's internal nativeId. Useful when reading logs that reference nativeIds. Returns { id: null } if no match.

disconnect_clients

Disconnect all websocket clients of a plugin (forces reconnection).

clear_console

Clear a plugin device's console buffer. Useful for setting up a clean repro window.

get_logs

Fetch retained server-side logs (newest first). Filter by component (substring match), level, sinceMs. Results are capped (`truncated: true` when more matched) — narrow the filters or raise `limit` to see the rest.

clear_logs

Clear the server-side log buffer. Returns { cleared: true } on success.

list_alerts

List Scrypted alerts (newest first). Alerts are persisted notices like plugin crashes or warnings. Results are capped (`truncated: true` when more matched) — raise `limit` to see the rest.

remove_alert

Remove a single alert by id (use the `id` field from list_alerts).

clear_alerts

Remove all alerts. Returns { cleared: true } on success.

list_devices

List devices on the Scrypted server. Filter by interface, type, or name substring.

get_device

Get a snapshot of every state property on a device. Returns the full state map, which can be large for cameras; the `interfaces` array tells you which methods call_device_method can invoke.

call_device_method

Invoke a method on a device (e.g. turnOn, setBrightness, getSettings). The available methods follow from the device's `interfaces` — call get_device first if unsure. May read or mutate depending on the method. Returns the JSON-serialized result.

get_server_info

Get Scrypted server version and SCRYPTED_* environment variables.

restart_server

Restart the Scrypted server. The current MCP connection will drop and need to reconnect.

update_server

Trigger a Scrypted server update. Honors SCRYPTED_WEBHOOK_UPDATE if set, otherwise writes .update and restarts. Returns immediately; the server restarts asynchronously and the MCP connection will drop, like restart_server.

get_dotenv

Read the contents of the Scrypted .env file. Returns empty content if the file does not exist.

set_dotenv

Overwrite the Scrypted .env file. The provided content is written verbatim — include all keys you want to keep.

list_users

List Scrypted user accounts (username + admin flag).

add_user

Create a new Scrypted user. Omit aclId to create an admin.

remove_user

Delete a Scrypted user by username.

get_local_addresses

Get the configured local addresses / interface names that Scrypted advertises.

set_local_addresses

Replace the configured local addresses. Pass interface names ("en0") or IPs.

get_external_addresses

Get the configured external (publicly reachable) addresses for a plugin endpoint.

set_external_addresses

Replace the configured external addresses for a plugin endpoint.

get_cors

Get the CORS origin allowlist for a plugin endpoint.

set_cors

Replace the CORS origin allowlist for a plugin endpoint.

list_cluster_workers

List registered Scrypted cluster worker nodes (id, name, labels, mode, address, fork count).

create_backup

Snapshot the Scrypted database. Returns the ZIP inline as a base64-encoded resource (plus a JSON summary with byte count + sha256) for the agent to save locally. Nothing is written to the Scrypted host filesystem.

restore_backup
// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.18.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.18.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.18.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configSCRYPTED_INSECURE_PORT
// quality suggestions

All four hints declared on every tool

17/39 tools missing one or more hints — list_plugins (missing: destructiveHint); get_plugin_info (missing: destructiveHint); npm_info (missing: destructiveHint), +14 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

2 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.18.0 (high), @modelcontextprotocol/sdk@1.18.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sv-tools/scrypted-mcp-plugin?variant=verified)](https://m8ven.ai/mcp/sv-tools/scrypted-mcp-plugin)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 99b6a0e3875ca3086562dfdcfac9a9d9053e6219
code hash: 70655877348cf554dc952b3a263a49ad6892caec9e8a137ac38812362e20432d
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client