Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Chat chat with Claude about @architecture.md"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Chat is a command-line interface application that enables interactive chat capabilities with AI models through the Anthropic API. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Context Protocol) architecture.
See ARCHITECTURE.md for diagrams of how main.py, mcp_client.py, mcp_server.py, and the core/ modules fit together.
Python 3.10+
Anthropic API Key
Related MCP server: MCP Chat
Copy .env.example to .env in the project root and fill in the values:
cp .env.example .envANTHROPIC_API_KEY="" # Your Anthropic API secret key
CLAUDE_MODEL="claude-sonnet-4-5" # Model id to chat with
USE_UV=1 # 1 to launch the MCP server via uv, 0 for plain pythonANTHROPIC_API_KEY and CLAUDE_MODEL are both required — the app exits at startup if either is empty.
uv is a fast Python package installer and resolver.
Install uv, if not already installed:
pip install uvCreate and activate a virtual environment:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateInstall dependencies:
uv pip install -e .Run the project
uv run main.pyCreate and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateInstall dependencies:
pip install anthropic python-dotenv prompt-toolkit "mcp[cli]==1.8.0"Run the project
python main.pySimply type your message and press Enter to chat with the model.
Use the @ symbol followed by a document ID to include document content in your query:
> Tell me about @deposition.mdUse the / prefix to execute prompts defined in the MCP server. Each command takes a document id:
> /format deposition.mdCommands will auto-complete when you press Tab. mcp_server.py currently defines one prompt, format.
Edit the mcp_server.py file to add new documents to the docs dictionary.
Pass additional server scripts as arguments; each is launched as its own MCP client and its tools are merged into the tool set offered to the model:
uv run main.py path/to/other_server.pyThere are no lint or type checks wired into CI. To lint locally:
uvx ruff check .Edit 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 | |
| new_str | Yes | The new text to insert in place of the old text | |
| old_str | Yes | The text to replace. Must match exactly, including whitespace |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It states that a string is replaced, but does not clarify whether all occurrences are replaced or only the first, nor does it mention that the edit is permanent/mutating, any side effects, or error conditions. This ambiguity is a significant gap for a mutation tool.
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, compact sentence with no filler or redundant restatement of the tool name. It is front-loaded with the action and resource, and every word contributes meaning.
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 3-parameter tool, the description plus full schema coverage is mostly sufficient for an agent to make a call. However, the missing occurrence behavior (all vs. first match) and the absence of an output schema leave some uncertainty about the tool's actual effect and return value, making it minimally complete rather than fully contextualized.
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?
The input schema covers 100% of the parameters with clear descriptions. The tool description essentially paraphrases the schema (old_str replaced by new_str) without adding new semantic meaning, such as constraints or examples. Baseline 3 is appropriate because the schema carries the burden.
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 uses a specific verb ('Edit'), names the exact resource ('a document'), and specifies the mechanism ('replacing a string ... with a new string'). This clearly distinguishes it from the sibling read_doc_contents, which is a read operation.
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 implies usage: when a document's content must be modified via string replacement. However, it provides no explicit guidance about when NOT to use it or when to prefer the sibling read_doc_contents instead. The alternative is only inferable from the tool name, not the description.
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?
With no annotations, the description carries the burden of behavioral disclosure. It does state the output behavior ('return it as a string'), but does not mention error handling, permissions, or what happens when the document does not exist. For a simple read operation, this is adequate but not rich.
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, front-loaded sentence with no wasted words. It efficiently conveys both the operation and the return format.
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?
This is a simple tool with one parameter, full schema coverage, and no output schema. The description is largely complete for a read operation, especially since it explicitly states the return type. It could be slightly stronger with error or permission context, but nothing essential is missing for basic invocation.
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?
The schema already fully documents the only parameter, doc_id, as 'Id of the document to read', so schema coverage is 100%. The description adds no additional parameter meaning beyond the schema, matching the baseline score.
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 states a specific verb and resource: 'Read the contents of a document' and explicitly notes the return type as a string. This clearly distinguishes it from the sibling 'edit_document', which implies modification rather than reading.
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 verb 'Read' establishes a clear context for when this tool is appropriate, and its contrast with 'edit_document' implies read-only usage. However, it does not explicitly state when not to use it or name the alternative.
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.
v0.1.0edit_documentread_doc_contentsScored across 2 tools
The two tools have completely distinct purposes: one reads document content, the other edits by replacing text. There is zero overlap or ambiguity between them.
Both tools follow a verb_noun pattern (read_doc_contents, edit_document), but the noun forms differ slightly ('doc_contents' vs 'document'). This minor inconsistency doesn't hinder readability.
With only two tools, the server feels thin for a document manipulation domain. While the narrow focus is defensible, the count is below the typical 3-15 range and borders on insufficient.
The server provides read and edit (replace) operations, but lacks create, delete, list, or other common document lifecycle operations. These gaps could be worked around but represent notable missing functionality.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
