mcp-knowledge-service AGENTS.md

mcp-knowledge-service AGENTS.md is an instructions file for Codex, OpenCode from hyh0620/mcp-knowledge-service. It costs 266 tokens per session, scanned A, original, MIT.

Project instructions for a reusable MCP knowledge-retrieval service, which lets clients search stored documents and receive citations. They define setup, ingestion, querying, configuration, and protocol rules.

In plain words
What is it for?
Use them when setting up the Python service, ingesting and querying collections, maintaining MCP tools, checking citations, and keeping runtime data out of commits.
Why use it?
They prevent common service errors such as hardcoded collection names, secrets committed to version control, or logs mixed into MCP messages.

Instructions file for CodexOpenCode

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

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/hyh0620/mcp-knowledge-service/agents-md
Clone the repo
git clone --depth 1 https://github.com/hyh0620/mcp-knowledge-service

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 mcp-knowledge-service AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hyh0620/mcp-knowledge-service/agents-md.svg)](https://agentmods.dev/instructions/hyh0620/mcp-knowledge-service/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hyh0620/mcp-knowledge-service/agents-md"><img src="https://agentmods.dev/badge/instructions/hyh0620/mcp-knowledge-service/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 266 This file is loaded in full into every session.
When invoked 266 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00266 $0.00266
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00027 $0.00027

Measured 5d ago against content hash 8ff8dc418d5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-knowledge-service 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 5d 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 · 14 lines

What it actually says

AGENTS.md

  • Python version: 3.11.
  • Install: python3.11 -m venv .venv && source .venv/bin/activate && pip install -e '.[dev]'.
  • Local config: copy config/settings.example.yaml to ignored config/settings.yaml.
  • MCP server command: python -m src.mcp_server.server.
  • MCP stdio rule: stdout is reserved for JSON-RPC protocol messages; logs must go to stderr.
  • Collection names must come from tool arguments, CLI arguments, environment variables, or config. Do not hardcode salon_knowledge in service code.
  • Default public collection is knowledge_hub; salon data is only an example under examples/salon.
  • Ingest: python scripts/ingest.py --path <SOURCE_PATH> --collection <COLLECTION> --force.
  • Query: python scripts/query.py --query "<QUESTION>" --collection <COLLECTION>.
  • Do not commit .env, API keys, config/settings.yaml, ChromaDB data, BM25 indexes, SQLite runtime data, logs, traces, or cache files.
  • After changing MCP tools or response format, verify initialize, tools/list, query_knowledge_hub, citations, and collection isolation.
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. 5d ago First seen · 14 lines · 266 tokens per session scan A 8ff8dc418d5e

Subscribe to this mod's changes

mcp-knowledge-service AGENTS.md is an instructions file published in the GitHub repository hyh0620/mcp-knowledge-service (0 stars, last pushed 1mo ago), licensed MIT. It adds 266 tokens to every session, about $0.0013 per session on Opus 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 2026-09-01.