Anchor

Provides an MCP interface for Anchor programs to connect with LLMs and external data sources.

other

3

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "honey-guard-anchor-mcp": {
      "command": "security_check_program",
      "args": [
        "--mcp"
      ]
    }
  }
}

Anchor MCP enables seamless integration between large language model (LLM) workflows and external data sources or tools by exposing MCP endpoints from Anchor-based programs. This server template lets you run MCP-enabled helpers that your AI applications can query to access program context, prompts, and tools in a standardized way.

How to use

You connect your MCP-enabled client to the two provided stdio MCP endpoints to enable context sharing and tool access for Anchor programs. The two endpoints are designed to be run locally and expose the MCP interface when started with the required flag.

How to install

Prerequisites: You should have a working environment where you can run the MCP server commands and edit the configuration used by your AI client interface (in this example, Claude Desktop). Ensure Claude Desktop is installed and you can access the Developer configuration panel for editing MCP server entries.

Step 1. Open Claude Desktop settings.

Step 2. Navigate to Settings → Developer → Edit Config.

Step 3. Add the MCP server configuration shown below to the servers section. This enables two local MCP endpoints that your AI workflows can connect to.

{
  "mcpServers": {
    "security_check_program": {
      "command": "security_check_program",
      "args": [
        "--mcp"
      ]
    },
    "security_check_file": {
      "command": "security_check_file",
      "args": [
        "--mcp"
      ]
    }
  }
}

Additional sections

Step 4. Save the changes and restart Claude Desktop to apply the new MCP server configuration.

Step 5. If you want to monitor MCP activity, tail the log file for real-time updates using the provided path: tail -n 20 -f ~/Library/Logs/Claude/mcp*.log.