Click on "Install 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 summarize @deposition.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 Control Protocol) architecture.
Python 3.9+
Anthropic API Key
Related MCP server: MCP Chat
Create or edit the .env file in the project root and verify that the following variables are set correctly:
ANTHROPIC_API_KEY="" # Enter your Anthropic API secret keyuv 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 commands defined in the MCP server:
> /summarize deposition.mdCommands will auto-complete when you press Tab.
Edit the mcp_server.py file to add new documents to the docs dictionary.
To fully implement the MCP features:
Complete the TODOs in mcp_server.py
Implement the missing functionality in mcp_client.py
There are no lint or type checks implemented.
To see the tool available to MCP client (in MCP server), run the below command:
python mcp_client.pyEdit the contents of a document by replacing the old content with new content.
| Name | Required | Description | Default |
|---|---|---|---|
| doc_id | Yes | The ID of the document to edit. | |
| new_string | Yes | The new content for the document. | |
| old_string | Yes | The old string of the document, must match including whitespace and punctuation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description must carry the behavioral burden. It does disclose that the operation replaces old content with new content, which is the core destructive behavior. However, it does not mention side effects, irreversibility, or failure behavior when the old string is not found.
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?
One clear sentence with no filler; the purpose and mechanism are front-loaded in a compact phrase.
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 operation with fully described parameters, the core is coverednovo. However, there is no mention of error behavior, idempotency, or response, and no usage guidance relative to read_doc, so it is adequate but not complete.
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 coverage is 100%: doc_id, old_string, and new_string each have descriptions, with old_string adding the 'match including whitespace and punctuation' constraint. The tool description itself adds little param detail, so the baseline 3 is appropriate.
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 states a specific action ('Edit the contents of a document') with a defined mechanism ('replacing the old content with new content'). It clearly targets this tool as a modification operation rather than the sibling read_doc, though it never names the sibling.
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 is given about when to choose this tool over the sibling read_doc, nor any conditions, prerequisites, or exclusions. The intent is implied by the verb 'Edit,' but alternatives are not addressed.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| doc_id | Yes | The ID of the document to read. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations to cover safety or side-effect information, and the description only restates the core operation without addressing permissions, errors, output format, or whether the operation is side-effect-free. The agent is left to infer most behavioral properties from the word 'read'.
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 clear sentence with no filler or redundancy. It is appropriately concise for the simplicity of the tool.
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 the tool's simplicity)Skip—one parameter and a single straightforward action—the description provides minimal viable context. However, with no annotations or output schema, a bit more detail about return format or typical usage would make it complete.
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%, so the baseline is adequate. The description adds no extra meaning beyond the schema's doc_id parameter, but it does not need to compensate for missing parameter documentation.
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 is a clear, specific verb+object statement ('Read the contents of a document'), and the sibling tool name edit_doc reinforces the distinction between reading and editing. An agent can tell exactly what operation this tool performs.
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?
There is no guidance about when to prefer this tool over alternatives, prerequisites, or typical use cases. The intended usage is only implied by the tool's name and minimal description, so an agent gets no explicit context about selection or invocation.
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_docread_docScored across 2 tools
read_doc and edit_doc have clearly distinct purposes: one retrieves contentaren't and the other modifies it. There is no overlap or ambiguity between the two tools.
Both tools follow the same verb_noun snake_case pattern: read_doc and edit_doc. The naming convention is perfectly consistent across the set.
With only two tools, the server feels minimal and borderline thin for most use cases. However, for a narrowly scoped document read/edit utility, the count is not unreasonable.
The tool surface covers reading and editing but lacks create, delete, list, or search operations, preventing any real document lifecycle management. Agents cannot discover or create documents, which creates significant workflow gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Shared memory and actions for Claude, Kiro, OpenAI, Cursor, and other MCP-compatible AI clients.
