Claude Desktop APISAFE
MCP server implementation for using Claude API with Claude Desktop, providing advanced API integration and conversation management.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
This project provides an MCP server implementation that enables seamless integration between Claude Desktop and the Claude API. It allows you to bypass Professional Plan limitations and access advanced features like custom system prompts and conversation management.
Features
- Direct Claude API integration via MCP
- Conversation history tracking and management
- System prompt support
- Seamless switching between Professional Plan and API usage
- Easy configuration with Claude Desktop
When to Use
- Professional Plan (default):
- Regular conversations in Claude Desktop
- Basic usage within plan limits
- No special configuration needed
- API Token (via this MCP server):
- When you need longer context windows
- To use custom system prompts
- To bypass rate limits
- For advanced conversation management
Setup Instructions
- Clone the Repository
# Using VS Code: # 1. Press Cmd + Shift + P # 2. Type "Git: Clone" # 3. Paste: https://github.com/mlobo2012/Claude_Desktop_API_USE_VIA_MCP.git # Or using terminal: git clone https://github.com/mlobo2012/Claude_Desktop_API_USE_VIA_MCP.git cd Claude_Desktop_API_USE_VIA_MCP
- Install Dependencies
pip install -r requirements.txt
- Configure Environment
# Copy environment template cp .env.example .env # Edit .env and add your API key ANTHROPIC_API_KEY=your_api_key_here
- Configure Claude Desktop
- macOS: Navigate to
~/Library/Application Support/Claude/
# Using Finder: # 1. Press Cmd + Shift + G # 2. Enter: ~/Library/Application Support/Claude/
- Windows: Navigate to
%APPDATA%\Claude\ - Create or edit
claude_desktop_config.json - Copy contents from
config/claude_desktop_config.json - Update paths and API keys
Usage Guide
Basic Usage
- Regular Claude Desktop Usage
- Jus
57c6056a4a82OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add claude-api-mcp --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"claude-api-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
}
}
}
}Exposed tools (4)
2 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
clear_conversation | destructive | Clear a specific conversation history |
get_conversation_history | read | Get the conversation history for a specific ID |
query_claude | read | |
send-message | write | Send a message to Claude |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- UNDECLARED (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
clear_conversation
@modelcontextprotocol/sdk, @anthropic-ai/sdk, typescript
mcp, anthropic, python-dotenv, json5
Gates applied: no_behavioural_pass, no_license.
57c6056a4a82full audit observations/trust-audit/mcp-server/mlobo2012__claude-desktop-api.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 57c6056a4a82 | SAFE | B | 89 | first audit |
Questions
What is the Claude Desktop API MCP server?
MCP server implementation for using Claude API with Claude Desktop, providing advanced API integration and conversation management.
What tools does Claude Desktop API expose?
4 in total: 2 read-only, 1 that write, and 1 that can delete or overwrite (clear_conversation). Every one is listed on this page with its risk.
Is Claude Desktop API safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Claude Desktop API need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Claude Desktop API run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as claude-api-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (57c6056a4a82), read on 2026-10-08. The repository is watched and re-audited when it changes.