sinoutX-user (iezhik87/sinoutX-user) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 57 tools. No publisher has claimed this listing.

D
Caution
54/100

sinoutX-user

SinoutX (personal edition) — self-hosted, single-user AI workspace with a built-in assistant that captures, remembers and acts across web, Telegram and Viber. Your data, your server, your AI keys (BYOK). Ships with SINOUT_EDITION=solo.

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

iezhik87

Source: github_repo_search

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: 14 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.
🔐
You'll be asked for 2 credentials: BACKEND_API_KEY, MCP_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes57 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.

sinout_setup_memory

Ensure this agent has its own memory workspace with the Memory («Память») module installed. Creates a workspace if none exists and installs the module (idempotent). Call once at the start of a session. Returns workspaceId and the memory collections (core/facts/entities/episodes) with their field sch

sinout_init_agent

START HERE. Bootstrap EVERYTHING in one call: ensures you have a memory workspace (creates one + installs the Memory module if you have none — works from scratch), then returns your workspace, all module projects with their collections (by NAME + field schema, so no hardcoded IDs), your memory Core

sinout_ask_assistant

Delegate a question or task to the built-in SinoutX assistant. It knows the workspace deeply and has 60+ tools (pages, tasks, search, modules/records, export to PDF/DOCX, Telegram, deep research). Use it for things it does better than you, or to act inside a workspace you share.

sinout_remember

Persist a memory immediately and reliably (one call — no need to look up collections). Use this THE MOMENT something worth remembering appears; do not wait. kind: fact (default) | core (compact pinned context, UPSERTED by key — no duplicates) | entity | episode.

sinout_recall

Reliable recall: scans ALL your memory collections (core/facts/entities/episodes) and ranks by relevance — so anything you stored is found, not forgotten. Call BEFORE answering anything that may depend on past context. scope=all also scans other modules (Finance/Medical Record/…).

sinout_read_page_with_children

Read a page together with ALL its nested child pages (full subtree) in one call — for deep context recall on a topic.

sinout_consolidate_memory

Consolidate memory NOW: distil fresh `episodes` into durable `facts`/`entities` (normally runs nightly at 04:00). Returns how many episodes were processed and facts/entities created — or a `skipped` reason (e.g. "AI provider error" = no chat model / no balance on this workspace). Use to flush episod

sinout_get_budget_summary

Get budget summary (income, expenses, balance) for a project

sinout_list_budget_entries

List budget entries (transactions) for a project

sinout_add_budget_entry

Add an income/expense entry to the legacy project budget. Pass projectId OR workspaceId (a project is resolved from it). NOTE: if you use the Finance MODULE, prefer sinout_create_record into its transactions/budget collection (sinout_list_collections) — that is the module data store.

sinout_list_events

List calendar events for a project or workspace

sinout_get_upcoming_events

Get upcoming calendar events for a workspace

sinout_create_event

Create a new calendar event

sinout_update_event

Update a calendar event

sinout_list_collections

List collections (реестры — typed datasets) of installed modules, e.g. Medical Record measurements/medications or Finance transactions. Pass projectId for one module project, or workspaceId to list across all module projects. Each collection returns its field schema (use those field keys when creati

sinout_query_records

Read records of a collection (реестр) — e.g. blood-pressure measurements, lab results, finance transactions. Get collectionId from sinout_list_collections.

sinout_create_record

Add a record to a collection (реестр) — e.g. log a blood-pressure measurement into Medical Record, or a transaction into Finance. The `data` keys must match the collection field keys from sinout_list_collections (the `fields` schema). Numbers as numbers, dates as ISO (YYYY-MM-DD).

sinout_create_records

Bulk-add MANY records to a collection in ONE call (much faster than calling sinout_create_record repeatedly, and easier on the session). Each item is a record whose keys match the collection field keys. Up to 200 items.

sinout_delete_records

Bulk-delete MANY records by their IDs in ONE call (use for de-duplication or cleanup instead of calling sinout_delete_record N times). Up to 500 IDs. Returns the count deleted.

sinout_update_record

Replace the data of an existing collection record. Get recordId from sinout_query_records. Pass the FULL new data object (it replaces the old one).

sinout_delete_record

Delete a record from a collection (реестр) by its ID.

sinout_upload_file

Upload a binary file (PNG, XLSX, PDF, image, etc.) into SinoutX from base64. Stores it as an attachment in the workspace (optionally linked to a project). Use to migrate local files off disk into SinoutX. Returns the attachment id and url.

sinout_list_files

List files (attachments) in a workspace or project. Pass workspaceId or projectId.

sinout_get_file

Download a file by attachment ID — returns its content as base64 (decode to use/parse, e.g. an XLSX or PNG) plus mimeType and size.

sinout_delete_file

Delete a file (attachment) by ID.

sinout_create_habit

Create a habit to track in a workspace

sinout_check_habit

Mark a habit as done on a date (default today)

sinout_create_objective

Create an objective (OKR) in a workspace

sinout_add_key_result

Add a key result (KR) to an objective

sinout_create_journal_entry

Create or update a personal journal entry for a date

sinout_list_notes

List notes in a workspace

sinout_get_note

Get full note content by ID

sinout_create_note

Create a new note in a workspace

sinout_update_note

Update note content or metadata

sinout_delete_note

Delete a note

sinout_list_pages

List all pages in a project (flat list)

sinout_get_page_tree

Get hierarchical page tree for a project (for navigation)

sinout_get_page

Get full content of a page by ID

sinout_create_page

Create a new page in a project. IMPORTANT: always pass the full content when you have information to write — never create a page with only a title if you have relevant data. The content field accepts plain text with newlines; it will be converted to rich text automatically.

sinout_update_page

Update page title and/or content

sinout_delete_page

Soft-delete a page and all its child pages

sinout_create_spec

Create a structured specification page for a feature or component. Generates a page with standard sections: Goal, Requirements, Technical Decisions, Implementation Plan, and Status. Optimized for coding agents to read and update as they implement.

sinout_search

Full-text search across pages, tasks, and notes

sinout_get_context

Aggregate all relevant knowledge for a topic from a project. Returns matching pages (with content), tasks, and notes in one call. Use this as the first step when a coding agent needs context before implementing a feature or making decisions.

sinout_ask

Ask Sinout's AI a question and get a synthesized answer using the knowledge base. Use this when sinout_get_context returns insufficient or unclear data, when you need to understand business logic, or when you need a decision recommendation based on project knowledge. The AI has access to all Sinout

sinout_get_graph

Get knowledge graph nodes and edges for a workspace or project

sinout_create_link

Create a link between two entities — pages, tasks, notes, and module records/collections (use type "record" to connect a memory record to a Finance/Medical-Record record, "collection" for a whole реестр).

sinout_list_tasks

List tasks in a project with optional filters

sinout_get_task

Get full task details by ID

sinout_create_task

Create a task. Pass projectId, OR workspaceId (the task goes to a general project, created if none exists). Status accepts common words (pending, todo, in progress, done, completed…) and is normalised automatically.

sinout_update_task

Update task status, priority, title, due date, or implementation notes. Use implementationNotes to document what was built, decisions made, or code locations — this creates a permanent record in the task description visible in the Sinout UI.

sinout_get_task_analytics

Get task analytics for a project (count by status, priority, overdue)

sinout_list_workspaces

List all workspaces in Sinout

sinout_create_workspace

Create a new workspace

sinout_list_projects

List projects in a workspace

sinout_create_project

Create a new project inside a workspace

sinout_get_workspace

Get workspace details by ID

// known CVEs in dependencies14 high5 medium11 low

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

high@modelcontextprotocol/sdk@1.0.0GHSA-w48q-cv73-mx4w

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

highaxios@1.7.7GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.7.7GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.7.7GHSA-43fc-jf86-j433

Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig

highaxios@1.7.7GHSA-4hjh-wcwx-xvwj

Axios is vulnerable to DoS attack through lack of data size check

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.
🔐 secretBACKEND_API_KEY
configBACKEND_URL
🔐 secretMCP_API_KEY
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

57/57 tools missing one or more hints — sinout_setup_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); sinout_init_agent (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); sinout_ask_assistant (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +54 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.

Production dependencies are patched

0 critical, 14 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high), axios@1.7.7 (high)

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

Domain consistency

npm scope @sinout doesn't match GitHub owner iezhik87

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

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 5 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/iezhik87/sinoutx-user?variant=verified)](https://m8ven.ai/mcp/iezhik87/sinoutx-user)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 853c15cd2dcbfa1f9654aaacf367274b4e423702
code hash: b0741c4e097b4e82a8613f33bd5e82032a9ab12a9fb2b3d22625b65b7ef468d3
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