OnyxSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/lupuletic-onyx-mcp-server)
[](https://opensource.org/licenses/MIT) [](https://www.npmjs.com/package/onyx-mcp-server) [](https://www.npmjs.com/package/onyx-mcp-server) [](https://smithery.ai/server/@lupuletic/onyx-mcp-server) [](https://github.com/lupuletic/onyx-mcp-server/blob/main/CONTRIBUTING.md)
A Model Context Protocol (MCP) server for seamless integration with Onyx AI knowledge bases.
This MCP server connects any MCP-compatible client to your Onyx knowledge base, allowing you to search and retrieve relevant context from your documents. It provides a bridge between MCP clients and the Onyx API, enabling powerful semantic search and chat capabilities.
Features
- Enhanced Search: Semantic search across your Onyx document sets with LLM relevance filtering
- Context Window Retrieval: Retrieve chunks above and below the matching chunk for better context
- Full Document Retrieval: Option to retrieve entire documents instead of just chunks
- Chat Integration: Use Onyx's powerful chat API with LLM + RAG for comprehensive answers
- Configurable Document Set Filtering: Target specific document sets for more relevant results
Installation
Installing via Smithery
To install Onyx MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @lupuletic/onyx-m
41dccb2532f7OBSERVED · 2026-10-08Connect
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 onyx-mcp-server --env ONYX_API_TOKEN=${ONYX_API_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"onyx-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ONYX_API_TOKEN": "${ONYX_API_TOKEN}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
chat_with_onyx | read | Chat with Onyx to get comprehensive answers |
search_onyx | read | Search the Onyx backend for relevant documents |
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 (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
.clinerules
.eslintrc.cjs
import { loadConfig, SERVER_CONFIG, DEBUG } from '../../config/index.js';import { OnyxMcpServer } from '../../server.js';import { OnyxApiService } from '../../services/onyxApi.js';import { OnyxConfig } from '../../types/index.js';import { handleChatWithOnyx } from '../../tools/chatTool.js';@modelcontextprotocol/sdk, axios, @types/jest, @types/node, @commitlint/cli, @commitlint/config-conventional, @typescript-eslint/eslint-plugin, @typescript-eslint/parser
Gates applied: no_behavioural_pass.
41dccb2532f7full audit observations/trust-audit/mcp-server/lupuletic__onyx.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 |
|---|---|---|---|---|---|
| 2026-10-08 | 41dccb2532f7 | SAFE | B | 89 | first audit |
Questions
What tools does Onyx expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Onyx 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 Onyx need?
It reads ONYX_API_TOKEN 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 Onyx run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as onyx-mcp-server at 1.2.2.
How current is this page?
The grade is for one exact copy of the source (41dccb2532f7), read on 2026-10-08. The repository is watched and re-audited when it changes.