Qdrant (mhalder) MCP Server
@mhalder/qdrant-mcp-server
npm
v3.3.5
Source verified
Published by mhalder — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server for semantic search using local Qdrant and Ollama (default) with support for OpenAI, Cohere, and Voyage AI
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 8
high Shell/command execution in server code (build/code/indexer.js)MTC-SRC-002
In the server's implementation (`build/code/indexer.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { createHash } from "node:crypto"; import { promises as fs } from "node:f
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server build/code/indexer.js
high Shell/command execution in server code (build/git/extractor.js)MTC-SRC-002
In the server's implementation (`build/git/extractor.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { GIT_LOG_COMMIT_DELIMITER, GIT_LO
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server build/git/extractor.js
high Shell/command execution in server code (src/code/indexer.ts)MTC-SRC-002
In the server's implementation (`src/code/indexer.ts:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { createHash } from "node:crypto"; import { promises as fs } from "node:f
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/code/indexer.ts
high Shell/command execution in server code (src/git/extractor.ts)MTC-SRC-002
In the server's implementation (`src/git/extractor.ts:6`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { GIT_LOG_COMMIT_DELIMITER, GIT_LO
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/git/extractor.ts
low Shell/command execution in packaging/dev tooling (build/git/extractor.integration.test.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`build/git/extractor.integration.test.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { beforeAll, describe, expect, it
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server build/git/extractor.integration.test.js
low Shell/command execution in packaging/dev tooling (build/git/extractor.test.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`build/git/extractor.test.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: execFile vi.mock("node:child_process", () => ({ execFile: vi.fn(), })); vi.mock("node:util", () => ({ promisify
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server build/git/extractor.test.js
low Shell/command execution in packaging/dev tooling (src/git/extractor.integration.test.ts)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/git/extractor.integration.test.ts:6`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { beforeAll, describe, expect, it
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/git/extractor.integration.test.ts
low Shell/command execution in packaging/dev tooling (src/git/extractor.test.ts)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/git/extractor.test.ts:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: execFile vi.mock("node:child_process", () => ({ execFile: vi.fn(), })); vi.mock("node:util", () => ({ promisify: (
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/git/extractor.test.ts
Tools 20
Each tool and what it can reach — statically extracted from the published source.
add_documentsno sensitive capabilityclear_git_indexno sensitive capabilityclear_indexno sensitive capabilitycontextual_searchno sensitive capabilitycreate_collectionno sensitive capabilitydelete_collectionno sensitive capabilitydelete_documentsno sensitive capabilityfederated_searchno sensitive capabilityget_collection_infono sensitive capabilityget_git_index_statusno sensitive capability
Show 10 more tools ↓
get_index_statusno sensitive capabilityhybrid_searchno sensitive capabilityindex_codebaseno sensitive capabilityindex_git_historyno sensitive capabilityindex_new_commitsno sensitive capabilitylist_collectionsno sensitive capabilityreindex_changesno sensitive capabilitysearch_codeno sensitive capabilitysearch_git_historyno sensitive capabilitysemantic_searchno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (20 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v3.3.5 latest |
A 94/100 | 8 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @mhalder/qdrant-mcp-server --onlineOther implementations of Qdrant 5
Independent packages implementing the same tool, scanned with the same engine. Compare all 6 side by side →
MCP server for qdrant integration
Qdrant MCP server with configurable embedding providers
A Model Context Protocol (MCP) server for Qdrant vector database with semantic search capabilities
Een MCP server voor interactie met Qdrant vectordatabase
MCP server for retrieving context from a Qdrant vector database
More in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology