Claude Chat

io.github.codeChapPublished by GitHub account codeChapv0.1.0Updated Oct 24, 2026

Anthropic Claude Messages API MCP server — chat, vision, web search, extended thinking

The publisher's own server: Claude Platform Docs

VerifiedSTDIODesktop onlyWeb Search & ScrapingAI & ML

Overview

AI-generated overview

Local MCP server that lets an assistant call Anthropic's Claude Messages API for chat, image analysis, live web search and model listing.

What you can do
  • Send prompts to Claude with multi-turn history, a system prompt, model choice and optional extended thinking
  • Analyse an image from an http or https URL together with a text prompt
  • Run a chat that uses Claude's server-side web search and returns cited sources, with a cap on searches per request
  • List available Claude model IDs, cached for five minutes
When to use it
Useful when you want a second model, or Claude specifically, available as a tool inside another MCP client such as Claude Desktop or Claude Code — for extra reasoning, image analysis, or answers grounded in live web search.
Requirements
Runs as a local stdio process built with Rust (cargo build --release). Needs an Anthropic API key set in a config file at ~/.config/mcp-server-claude-chat/config.toml; the server exits at startup if the key is missing or empty. An optional base_url can point at a compatible gateway. Network access to the Anthropic API is required.
Before you install
The API key is stored in plain text in the config file and must be an API-credit key; a Claude Pro/Max subscription is not usable and routing it through this server would breach Anthropic's terms. Usage is billed per token, and web search adds $10 per 1,000 searches, which an org admin must enable in the Claude Console. Prompts, conversation history and image URLs are sent to Anthropic.

Installation

In SourceWeft

  1. Open Claude Chat in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcp-server-claude-chat

An MCP (Model Context Protocol) server for the Anthropic Claude Messages API. Built in Rust, it exposes chat, vision, live web search, and model listing as MCP tools — so any MCP client (Claude Desktop, Claude Code, etc.) can consult Claude as a tool.

Communicates via stdio using JSON-RPC 2.0, like all the other MCP servers in this collection. Structurally it mirrors mcp-server-grok-chat / mcp-server-gpt-chat, adapted to Anthropic's API shape.

Subscription vs. API credits

This server uses the Anthropic API with an API key (API credits). That is the only supported, terms-compliant way to drive Claude from a third-party tool.

A Claude Pro/Max subscription (the kind that powers Claude Code and the Claude apps) is not usable here: that authentication is licensed for Anthropic's own first-party clients, and routing it through a custom server would violate Anthropic's Consumer Terms — the "$200 of Claude usage from another service" concern you raised. So: API key it is. (If you run an Anthropic-compatible gateway, point base_url at it — see Configuration.)

Tools

ToolDescription
chatSend a message to Claude. Supports multi-turn history, a system prompt, model selection, and extended thinking via thinking_budget.
chat_with_visionAnalyse an image given an image URL and a text prompt.
chat_with_searchChat with live web search — Claude searches server-side and answers with cited sources.
list_modelsList available Claude models and their IDs (cached for 5 minutes).

Note: Anthropic has no embeddings endpoint (they recommend Voyage AI), so unlike the grok/gpt servers there is no embedding tool.

chat

NameTypeRequiredDescription
promptstringyesThe user message to send
system_promptstringnoSystem prompt to set context/behaviour
messagesstringnoConversation history as a JSON array of {role, content} objects (roles: user/assistant only — use system_prompt for system instructions)
modelstringnoModel ID (default: server default, claude-opus-4-8). Call list_models.
temperaturefloatnoSampling temperature (0.0–1.0). Ignored when thinking_budget is set.
max_tokensintegernoMax tokens to generate (defaults to the server default)
thinking_budgetintegernoEnable extended thinking with this token budget (min 1024). Reasoning is returned in a [thinking] block; max_tokens is auto-raised above the budget.

chat_with_vision

NameTypeRequiredDescription
promptstringyesText prompt describing what to analyse
image_urlstringyesURL of the image (must be http:// or https://)
modelstringnoVision-capable model ID (default: server default)
temperaturefloatnoSampling temperature (0.0–1.0)
max_tokensintegernoMax tokens to generate

chat_with_search

NameTypeRequiredDescription
promptstringyesThe user message
system_promptstringnoSystem prompt
modelstringnoModel ID (default: server default)
temperaturefloatnoSampling temperature (0.0–1.0)
max_tokensintegernoMax tokens to generate
max_usesintegernoMax web searches Claude may run for this request (default: 5)

Web search is billed by Anthropic at $10 per 1,000 searches on top of token costs, and an org admin must enable web search in the Claude Console.

list_models

No parameters. Results cached for 5 minutes.

Prerequisites

Setup

bash
mkdir -p ~/.config/mcp-server-claude-chatcp config.toml.example ~/.config/mcp-server-claude-chat/config.toml# then edit it and set api_key

Config (~/.config/mcp-server-claude-chat/config.toml):

toml
api_key = "sk-ant-..."
# Optional:# base_url = "https://api.anthropic.com/v1"   # or a compatible gateway# default_model = "claude-opus-4-8"# default_max_tokens = 4096

The server fails fast at startup if the config is missing or api_key is empty.

Build

bash
cargo build --release   # produces target/release/claude-chatcargo build             # debug buildcargo run               # run in dev modeRUST_LOG=debug cargo runcargo test              # unit tests (response formatting, validation, message building)

MCP Configuration

Claude Desktop (~/.config/Claude/claude_desktop_config.json) or any MCP client:

json
{  "mcpServers": {    "claude-chat": {      "command": "/media/codechap/4TB/develop/mcps/mcp-server-claude-chat/target/release/claude-chat"    }  }}

Claude Code:

bash
claude mcp add claude-chat -- /media/codechap/4TB/develop/mcps/mcp-server-claude-chat/target/release/claude-chat

Project Structure

src/  main.rs    - entry point, config loading, stdio transport setup  server.rs  - MCP tool definitions (chat, chat_with_vision, chat_with_search, list_models)  api.rs     - Anthropic HTTP client, Messages/Models types, response formatter  params.rs  - tool parameter types with serde + JSON Schema derives  config.rs  - TOML config loading

License

MIT

Source: README.md at commit 96225ee

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Claude integrations