Add graph-tool-call to Frameworks section

README.md

@@ -1939,6 +1939,7 @@ Interact with Git repositories and version control platforms. Enables repository
 - [Epistates/TurboMCP](https://github.com/Epistates/turbomcp) 🦀 - TurboMCP SDK: Enterprise MCP SDK in Rust
 - [FastMCP](https://github.com/jlowin/fastmcp) 🐍 - A high-level framework for building MCP servers in Python
 - [FastMCP](https://github.com/punkpeye/fastmcp) 📇 - A high-level framework for building MCP servers in TypeScript
+- [SonAIengine/graph-tool-call](https://github.com/SonAIengine/graph-tool-call) 🐍 🏠 - When tool count exceeds LLM context limits, accuracy collapses (248 tools → 12%). graph-tool-call builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy to 82% with 79% fewer tokens. Zero dependencies. Also works as an MCP Proxy — aggregate multiple MCP servers behind 3 meta-tools.
 - [vinkius-labs/mcp-fusion](https://github.com/vinkius-labs/mcp-fusion) 📇 [![Glama](https://glama.ai/mcp/servers/badge/@vinkius-labs/mcp-fusion)](https://glama.ai/mcp/servers/@vinkius-labs/mcp-fusion) - A TypeScript framework for building production-ready MCP servers with automatic tool discovery, multi-transport support (stdio/SSE/HTTP), built-in validation, and zero-config setup.
 - [MervinPraison/praisonai-mcp](https://github.com/MervinPraison/praisonai-mcp) 🐍 - AI Agents framework with 64+ built-in tools for search, memory, workflows, code execution, and file operations. Turn any AI assistant into a multi-agent system with MCP.