Интерфейс чата командной строки, который подключается к серверу MCP с использованием API Anthropic. Создан во время прохождения курса Anthropic Введение в протокол контекста модели (Introduction to Model Context Protocol), дополнен пользовательскими инструментами, ресурсами и подсказками.
MCP (Model Context Protocol) — это открытый стандарт для подключения моделей ИИ к внешним инструментам и источникам данных. Этот проект реализует обе стороны этого соединения — сервер FastMCP, который предоставляет документы в качестве ресурсов и определяет инструменты для их чтения и редактирования, и клиент, который подключается к серверу и делает эти возможности доступными внутри интерфейса чата.
Сервер определяет:
Инструменты — чтение и редактирование документов
Ресурсы — список всех документов или получение конкретного документа по URI
Подсказки — переформатирование документа в markdown или суммаризация его содержимого
Клиент реализует полную сессию клиента MCP, включая вызовы инструментов, чтение ресурсов, получение подсказок и автодополнение команд.
Related MCP server: MCP Chat
Начиная с начального пакета курса, я реализовал недостающие части с обеих сторон:
read_resource, list_prompts и get_prompt на стороне клиента
Конечные точки ресурсов (docs://documents и docs://documents/{doc_id}) на стороне сервера
Две подсказки (format и summarize), которые инструктируют модель использовать доступные инструменты
Главное, что этот проект прояснил для меня, — это разделение между сервером (который определяет, что доступно) и клиентом (который знает, как это вызвать), а также то, что подсказки — это просто структурированные сообщения, которые дают модели начальный контекст, а не магия.
Python 3.9+
API-ключ Anthropic
Клонируйте репозиторий и перейдите в папку проекта.
Создайте виртуальное окружение и активируйте его:
uv venv
.venv\Scripts\activate # Windows
source .venv/bin/activate # Mac/LinuxУстановите зависимости:
uv pip install -e .Создайте файл .env в корне проекта:
ANTHROPIC_API_KEY="your-key-here"Запустите приложение:
uv run main.pyВведите сообщение для чата. Используйте @doc_id, чтобы включить документ в ваш запрос, и /command, чтобы вызвать подсказку. Клавиша Tab дополняет доступные команды.
> Tell me about @deposition.md
> /summarize report.pdf
> /format plan.mdЧтобы добавить свои собственные документы, отредактируйте словарь docs в mcp_server.py.
mcp dev mcp_server.pyЭто откроет инспектор MCP в вашем браузере, где вы сможете протестировать инструменты, ресурсы и подсказки без интерфейса чата.
mcp_chat_cli/
├── main.py # entrypoint
├── mcp_server.py # FastMCP server — tools, resources, prompts
├── mcp_client.py # MCP client session wrapper
├── core/
│ ├── chat.py # chat loop logic
│ ├── claude.py # Anthropic API integration
│ ├── cli.py # CLI setup and input handling
│ ├── cli_chat.py # connects CLI and chat
│ └── tools.py # tool call handling
├── .env # API key (not committed)
└── pyproject.toml # dependenciesEdit a document by replacing a string in the documents content with a new string.
| Name | Required | Description | Default |
|---|---|---|---|
| doc_id | Yes | Id of the document that will be edited | |
| old_str | Yes | The text to replace. Must match exactly, including whitespace. | |
| new_str | Yes | The new text to insert in place of the old text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must disclose behavioral traits. It only states 'replacing a string' without indicating whether it replaces all occurrences, behavior on missing string, or side effects like auto-save. Missing important mutation details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded with the essential action and resource. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple edit tool with fully documented parameters, the description is adequate but lacks details on error handling (e.g., what if old_str not found) and whether it replaces all occurrences or just the first.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds value by clarifying that old_str must match exactly including whitespace. This goes beyond the schema's basic descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (edit), resource (document), and method (string replacement). It effectively distinguishes from the sibling tool 'read_doc_contents' which is read-only.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool vs alternatives. While the sibling tool name implies a read vs. edit distinction, no further guidance is provided on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the contents of a document and return it as a string.
| Name | Required | Description | Default |
|---|---|---|---|
| doc_id | Yes | Id of the document to read |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only states basic read operation; no mention of error handling, read-only guarantee, or behavior on invalid inputs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no redundant information. Could be improved with additional context without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description mentions return value as string, which is helpful. Lacks details on error conditions or edge cases, but adequate for a simple read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter; description does not add additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (read), resource (document), and output format (string). Distinguishes from sibling tool 'edit_document' which implies modification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the sibling 'edit_document'. Does not specify any prerequisites or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0edit_documentread_doc_contentsThe two tools have completely distinct purposes: one reads document contents, the other edits by replacing text. There is no functional overlap.
Both tool names follow the verb_noun pattern (edit_document, read_doc_contents), with consistent snake_case and clear action-object structure.
With only two tools, the server feels thin for a document utility, though it could be a minimal implementation. It falls into the borderline category (1-2 tools).
The server lacks basic CRUD operations like create and delete documents. While read and edit are provided, agents cannot create new documents or remove them, which are significant gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cslylla/mcp_chat_cli'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
