qdrant-mcp-server: Instructions file for Codex

AGENTS.md

qdrant-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from deveyus/qdrant-mcp-server. It costs 945 tokens per session, scanned A, original, MIT.

A repository guide named AGENTS.md for developers and coding agents working on a Qdrant MCP server fork. Qdrant is a database for searching documents by meaning, and MCP is a standard way for an AI agent to use external tools.

In plain words
What is it for?
Use it when building, running, or modifying this Node.js and TypeScript server, especially its Qdrant search and document-recency behaviour.
Why use it?
It explains the repository’s purpose, technology stack, build process, runtime command, and important configuration so changes follow the project’s requirements.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions OpenCode.

This is deveyus/qdrant-mcp-server's own configuration. It tells Codex and OpenCode how to work on qdrant-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qdrant-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to deveyus/qdrant-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/deveyus/qdrant-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/deveyus/qdrant-mcp-server

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qdrant-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/deveyus/qdrant-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/deveyus/qdrant-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/deveyus/qdrant-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/deveyus/qdrant-mcp-server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qdrant-mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/deveyus/qdrant-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/deveyus/qdrant-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 945 This file is loaded in full into every session.
When invoked 945 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00945 $0.00945
Opus 5.5 $0.00378 $0.00378
Sonnet 5.5 $0.00189 $0.00189
Haiku 4.5 $0.00094 $0.00094

Measured 2mo ago against content hash 992f5472174d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qdrant-mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file guides AI agents (Claude Code, OpenCode, Cursor) working in this repository.

What this repository is

A fork of mhalder/qdrant-mcp-server, upstream MIT (c) 2025 Martin Halder and contributors. All upstream code belongs to upstream. This fork adds exactly one change on top of upstream main:

  • recency scoring for semantic_search and hybrid_search. Fresh documents surface ahead of older near-duplicates via Qdrant's exp_decay formula.

See README.md -> "Fork Changes" for the full description.

Stack

  • Node.js 22.x or 24.x, TypeScript, compiled with tsc to build/.
  • Native module tree-sitter builds against system C++ headers.
  • Backend: Qdrant (vector DB), embedding via OpenCode-compatible provider (Ollama/OpenAI/etc.).

Build

npm install

# Node 22.x
npm run build

# Node 24.x: native module needs C++20
CXXFLAGS='-std=c++20' npm install
npm run build

Output goes to build/index.js. build/ and node_modules/ are gitignored.

Run

stdio transport is the default:

node build/index.js

Environment variables are documented in README.md -> Advanced Configuration. The two most important: QDRANT_URL (your Qdrant server) and EMBEDDING_PROVIDER (default ollama).

Registering the MCP server with OpenCode

Add this to opencode.json (project-scope or ~/.config/opencode/opencode.json):

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "qdrant": {
      "type": "local",
      "command": ["node", "/path/to/qdrant-mcp-server/build/index.js"],
      "enabled": true,
      "environment": {
        "QDRANT_URL": "http://localhost:6333",
        "EMBEDDING_PROVIDER": "ollama"
      }
    }
  }
}
  • command is an array of strings, never a single string.
  • type is required.
  • Point QDRANT_URL at your Qdrant server; set EMBEDDING_PROVIDER and, if needed, EMBEDDING_BASE_URL / EMBEDDING_MODEL to match your embedding setup.
  • Save + restart OpenCode after any config change; config is loaded at startup.
  • See README.md -> OpenCode Setup for the full example, including a permission block that auto-approves the search tools.

Read the full file on GitHub · 112 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 112 lines · 945 tokens per session scan A 992f5472174d

Subscribe to this mod's changes

qdrant-mcp-server AGENTS.md is an instructions file published in the GitHub repository deveyus/qdrant-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 945 tokens to every session, about $0.0038 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

qdrant-mcp-server AGENTS.md compared with instructions from other repositories

qdrant-mcp-server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
qdrant-mcp-server AGENTS.mddeveyus/qdrant-mcp-serverInstructions file02mo agoMITA945Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode