extract_links — Axiom Works AgentReader MCP Tool
extract_links
(extract links) is one of 10 tools on the
Axiom Works AgentReader
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call extract_links from your client
- Claude Code Axiom Works AgentReader extract_links run in your project directory
- Claude Desktop Axiom Works AgentReader extract_links ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Axiom Works AgentReader extract_links ~/.cursor/mcp.json
- VS Code Axiom Works AgentReader extract_links .vscode/mcp.json
- Zed Axiom Works AgentReader extract_links ~/.config/zed/settings.json
- Windsurf Axiom Works AgentReader extract_links ~/.codeium/windsurf/mcp_config.json
- Cline Axiom Works AgentReader extract_links ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Axiom Works AgentReader extract_links ~/.gemini/settings.json
- Grok Axiom Works AgentReader extract_links .mcp.json (in your project root)
- ChatGPT Axiom Works AgentReader extract_links Settings → Connectors → Advanced → Developer mode
- Claude.ai Axiom Works AgentReader extract_links Settings → Connectors → Add custom connector
- LangChain Axiom Works AgentReader extract_links pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentreader https://api.axiomworks.co.uk/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 5 November 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.