vrchat-mcp (sawa-zen/vrchat-mcp) is an MCP server listed on the M8ven Trust Index. It scores 72 out of 100, grade C. It declares 18 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
72/100

vrchat-mcp

A Model Context Protocol server that allows AI assistants to interact with the VRChat API, enabling retrieval of user information, friends lists, and other VRChat data through a standardized interface.

→ sawa-zen/vrchat-mcp· listed on mcp_so

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

⚡ 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

sawa-zen

Source: mcp.so · also listed on ModelScope

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 →

⚡ Connect GitHub for Live Monitored

Install from

mcp.sonot scored hereModelScopenot scored here

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.

⏳ This MCP is queued for scoring. Check back in a few minutes.
// key findings
⚠️
Known vulnerabilities in dependencies: 2 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 3 credentials: VRCHAT_AUTH_TOKEN, VRCHAT_PASSWORD, VRCHAT_TOTP_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes18 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.

vrchat_select_avatar

Select and switch to a specific avatar by its ID.

vrchat_search_avatars

Search and list avatars by query filters. You can only search your own or featured avatars. It is not possible as a normal user to search other people's avatars.

vrchat_list_favorite_groups

Returns a list of favorite groups owned by a user.

vrchat_list_favorites

Returns a list of favorites.

vrchat_add_favorite

Add a new favorite.

vrchat_send_friend_request

Send a friend request to another user.

vrchat_get_friends_list

Retrieve a list of VRChat friend information. The following information can be retrieved: - "bio" - "bioLinks" - "currentAvatarImageUrl" - "currentAvatarThumbnailImageUrl" - "currentAvatarTags" - "developerType" - "displayName" - "fallbackAvatar" - "id" - "isF…

vrchat_join_group

Join a VRChat group by ID

vrchat_search_groups

Search VRChat groups by name or shortCode

vrchat_get_instance

Get information about a specific instance. Note: Detailed information about instance members is only available if you are the instance owner.

vrchat_create_instance

Create a new instance of a world.

vrchat_list_invite_messages

Returns a list of all the users Invite Messages. Admin Credentials are required to view messages of other users!

vrchat_request_invite

Request an invite from a user. IMPORTANT: Always obtain explicit permission from the user before sending an invite request. Note that invite requests cannot be sent to users in private instances. Returns the Notification of type requestInvite that was sent.

vrchat_get_invite_message

Returns a specific invite message. Admin Credentials are required to view messages of other users! Message type refers to a different collection of messages: - message = Message during a normal invite - response = Message when replying to a message - request = Message when requestin…

vrchat_get_notifications

Retrieve a list of VRChat notifications.

vrchat_get_current_user

Retrieve your own VRChat user information

vrchat_list_favorited_worlds

List favorited worlds by query filters.

vrchat_search_worlds

Search and list worlds by query filters.

// known CVEs in dependencies2 high

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

high@modelcontextprotocol/sdk@1.7.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.7.0GHSA-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.
🔐 secretVRCHAT_AUTH_TOKENexport =your_auth_token
🔐 secretVRCHAT_PASSWORD
🔐 secretVRCHAT_TOTP_SECRET
configVRCHAT_USERNAMEexport =your_username
// 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

18/18 tools missing one or more hints — vrchat_select_avatar (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vrchat_search_avatars (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vrchat_list_favorite_groups (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +15 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.

Tool inputs are validated

17/18 tool handlers declare input schemas (94%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.7.0 (high), @modelcontextprotocol/sdk@1.7.0 (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 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/sawa-zen/vrchat-mcp?variant=verified)](https://m8ven.ai/mcp/sawa-zen/vrchat-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 410c26b271f3fec3ae140357b0a03346ebce1ba4
code hash: de89669454d0d8a2fda21f9b5b068b3ed6a8155b0dc2d7a677423c4ca0d3e283
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