VRChatSAFE
This project is a Model Context Protocol (MCP) server for interacting with the VRChat API.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://badge.fury.io/js/vrchat-mcp) [](https://opensource.org/licenses/MIT)
日本語 | 한국어
This project is a Model Context Protocol (MCP) server for interacting with the VRChat API. It allows you to retrieve various information from VRChat using a standardized protocol.
Overview
The VRChat MCP server provides a way to access VRChat's API endpoints in a structured manner. It supports a wide range of functionalities, including user authentication, retrieving user and friend information, accessing avatar and world data, and more.
Usage
To start the server, ensure you have the necessary environment variables set:
export VRCHAT_USERNAME=your_username export VRCHAT_AUTH_TOKEN=your_auth_token
[!NOTE] #### How to obtain AUTH TOKEN You can use the following command to login and obtain an auth token: `` $ npx vrchat-auth-token-checker VRChat Username: your-username Password: ******** # If 2FA is enabled 2FA Code: 123456 # Success output Auth Token: authcookie-xxxxx `` Command source code Please handle the obtained token with care as it has a very long lifetimeThen, run the following command:
npx vrchat-mcp
This will launch the MCP server, allowing you to interact with the VRChat API through the defined tools.
Usage with Claude Desktop
To use this MCP server with Claude Desktop, you do not need to run npx vrchat-mcp manually. Instead, add
12dfe2be7f09OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add vrchat-mcp --env VRCHAT_AUTH_TOKEN=${VRCHAT_AUTH_TOKEN} --env VRCHAT_PASSWORD=${VRCHAT_PASSWORD} --env VRCHAT_TOTP_SECRET=${VRCHAT_TOTP_SECRET} -- npx -y [email protected]{
"mcpServers": {
"vrchat-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"VRCHAT_AUTH_TOKEN": "${VRCHAT_AUTH_TOKEN}",
"VRCHAT_PASSWORD": "${VRCHAT_PASSWORD}",
"VRCHAT_TOTP_SECRET": "${VRCHAT_TOTP_SECRET}"
}
}
}
}Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
vrchat_add_favorite | write | Add a new favorite. |
vrchat_get_current_user | read | Retrieve your own VRChat user information |
vrchat_join_group | read | Join a VRChat group by ID |
vrchat_list_favorite_groups | read | Returns a list of favorite groups owned by a user. |
vrchat_search_groups | read | Search VRChat groups by name or shortCode |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
.clinerules
@modelcontextprotocol/sdk, dotenv, otplib, vrchat, zod, @eslint/js, @types/node, eslint
Gates applied: no_behavioural_pass.
12dfe2be7f09full audit observations/trust-audit/mcp-server/sawa-zen__vrchat.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 12dfe2be7f09 | SAFE | B | 89 | first audit |
Questions
What is the VRChat MCP server?
This project is a Model Context Protocol (MCP) server for interacting with the VRChat API.
What tools does VRChat expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is VRChat safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does VRChat need?
It reads VRCHAT_AUTH_TOKEN, VRCHAT_PASSWORD and VRCHAT_TOTP_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does VRChat run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as vrchat-mcp at 0.15.0.
How current is this page?
The grade is for one exact copy of the source (12dfe2be7f09), read on 2026-10-07. The repository is watched and re-audited when it changes.