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.
npx agentmods add instructions/adhikasp/mcp-client-cli/agents-mdgit clone --depth 1 https://github.com/adhikasp/mcp-client-cliWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01472 | $0.01472 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
mcp-client-cli 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
mcp-client-cli is a CLI tool that acts as a Model Context Protocol (MCP) client. It allows users to run LLM prompts from the terminal with access to MCP-compatible servers/tools. The CLI supports multiple LLM providers (OpenAI, Anthropic, Google) and can be extended with any MCP-compatible server.
Key Features:
- MCP client implementation for tool usage
- Multi-provider LLM support (OpenAI, Anthropic, Google, local models)
- Conversation persistence and continuation
- Prompt templates
- Image input support (via stdin or clipboard)
- Memory storage for context across sessions
Architecture
The project uses:
- LangChain/LangGraph: For LLM orchestration and agent execution
- MCP SDK: For communicating with MCP servers
- SQLite: For conversation checkpointing and memory storage
- Rich: For terminal output formatting
Core Flow
- User provides a query via CLI
cli.pyparses arguments and loads configuration- MCP servers are initialized and tools are loaded
- A LangGraph ReAct agent processes the query with available tools
- Results are streamed back to the user with Rich formatting
Directory Structure
mcp-client-cli/
├── src/mcp_client_cli/
│ ├── cli.py # Main entry point, argument parsing, agent orchestration
│ ├── config.py # Configuration loading and dataclasses
│ ├── const.py # Constants (paths, defaults)
│ ├── input.py # Input handling (clipboard support)
│ ├── memory.py # SQLite-based memory/store implementation
│ ├── output.py # Output formatting with Rich
│ ├── prompt.py # Prompt templates
│ ├── storage.py # Tool caching and conversation management
│ └── tool.py # MCP to LangChain tool conversion
├── .github/workflows/
│ ├── test.yml # Installation tests on Linux/Windows/macOS
│ └── release.yml # PyPI publishing workflow
├── pyproject.toml # Project metadata and dependencies
├── CONFIG.md # Configuration documentation
└── README.md # User-facing documentation
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.
- 2d ago First seen · 196 lines · 1,472 tokens per session scan A 215ab5a95e1b
mcp-client-cli AGENTS.md is an instructions file published in the GitHub repository adhikasp/mcp-client-cli (677 stars, last pushed 9mo ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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 2026-08-30.
Other instructions, from other repositories
trainer CLAUDE.md
Instructions for Joe-Heffer/trainer, covering claude.md, project overview, technology stack, commands and development setup.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.