Zecheng Zhang

What is Function calling & MCP for LLMs? (explained with visuals and code) Before MCPs became popular, AI workflows relied on traditional Function Calling for tool access. Now, MCP is standardizing it for Agents/LLMs. The visual below explains how Function Calling and MCP work under the hood. Today, let's learn: - Function calling by building custom tools for Agents. - How MCPs help by building a local MCP client with mcp-use and using tools from Browserbase MCP server. In Function Calling: - The LLM receives a prompt. - The LLM decides the tool. - The programmer implements a procedure to accept a tool call request from the LLM and prepare a function call. The tool call request is found in the LLM's response when you prompt it. - A backend service executes the tool. This Function Calling takes place within our stack: - We host the tool. - We implement a logic to determine the tool to invoke and its parameters. - We execute it. So Function Calling requires us to wire everything manually. MCP simplifies this! Instead of hard-wiring tools, MCP: - Standardizes defining, hosting, and exposing tools. - Makes it easy to discover tools, understand schemas, and use them. - Demands approval before invoking them. - Detaches implementation from consumption. For instance, whenever you integrate an MCP server, you never write a line of Python code to integrate the tools. Instead, you just integrate the MCP server and everything beyond this follows a standard protocol handled by the MCP client and the LLM: - They identify the MCP tool. - They prepare the input argument. - They invoke the tool. - They use the tool’s output to generate a response. Everything happens through a standard (but abstracted) protocol. So here’s the key point: MCP and Function Calling are not in conflict. They’re two sides of the same workflow. - Function Calling helps an LLM decide what it wants to do. - MCP ensures that tools are reliably available, discoverable, and executable, without you needing to custom-integrate everything. For example, an agent might say, “I need to search the web,” using function calling. That request can be routed through MCP to select from available web search tools, invoke the correct one, and return the result. Check the workflow in the diagram below. In this setup, to build a local MCP client, I used mcp-use because it lets us connect any LLM to MCP servers & build private MCP clients, unlike Claude/Cursor. - Compatible with Ollama & LangChain - Stream Agent output async - Built-in debugging mode, etc Find the mcp-use GitHub repo in the comments! ____ Find me → Avi Chawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.

270

11 Comments

What is Function calling & MCP for LLMs? (explained with visuals and code) Before MCPs became popular, AI workflows relied on traditional Function Calling for tool access. Now, MCP is standardizing it for Agents/LLMs. The visual below explains how Function Calling and MCP work under the hood. Today, let's learn: - Function calling by building custom tools for Agents. - How MCPs help by building a local MCP client with mcp-use and using tools from Browserbase MCP server. In Function Calling: - The LLM receives a prompt. - The LLM decides the tool. - The programmer implements a procedure to accept a tool call request from the LLM and prepare a function call. The tool call request is found in the LLM's response when you prompt it. - A backend service executes the tool. This Function Calling takes place within our stack: - We host the tool. - We implement a logic to determine the tool to invoke and its parameters. - We execute it. So Function Calling requires us to wire everything manually. MCP simplifies this! Instead of hard-wiring tools, MCP: - Standardizes defining, hosting, and exposing tools. - Makes it easy to discover tools, understand schemas, and use them. - Demands approval before invoking them. - Detaches implementation from consumption. For instance, whenever you integrate an MCP server, you never write a line of Python code to integrate the tools. Instead, you just integrate the MCP server and everything beyond this follows a standard protocol handled by the MCP client and the LLM: - They identify the MCP tool. - They prepare the input argument. - They invoke the tool. - They use the tool’s output to generate a response. Everything happens through a standard (but abstracted) protocol. So here’s the key point: MCP and Function Calling are not in conflict. They’re two sides of the same workflow. - Function Calling helps an LLM decide what it wants to do. - MCP ensures that tools are reliably available, discoverable, and executable, without you needing to custom-integrate everything. For example, an agent might say, “I need to search the web,” using function calling. That request can be routed through MCP to select from available web search tools, invoke the correct one, and return the result. Check the workflow in the diagram below. In this setup, to build a local MCP client, I used mcp-use because it lets us connect any LLM to MCP servers & build private MCP clients, unlike Claude/Cursor. - Compatible with Ollama & LangChain - Stream Agent output async - Built-in debugging mode, etc Find the mcp-use GitHub repo in the comments! ____ Find me → Avi Chawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.

156

7 Comments

Transformer attention layers operate by projecting high-dimensional token representations into low-rank subspaces defined by per-head key/query/value projections. This inherently places a rank constraint on how relationships between items can be represented, and it forces the model to approximate rich interactions via combinations of rank-limited components. Our paper “Orthogonalization of data via Gromov-Wasserstein type feedback for clustering and visualization” provides a theoretical and algorithmic framework for dealing with full and low-rank structure in relational data representations by adapting transition probabilities and iteratively refining cluster orthogonality via Gromov-Wasserstein-inspired feedback. It shows how a low-rank Markov transition representation can be refined to better reflect true structure and interpretability, and how such refinements converge to meaningful solutions with spectral gap enhancement. This connects directly to issues in multi-head attention: -Both involve representing pairwise relationships (attention scores vs. transition affinities) in a full-rank or approximately low-rank form. -Low-rank factorization can produce spurious grouping or similarity structure that doesn’t reflect the true geometry, unless guided by careful feedback or regularization. -The GW-feedback orthogonalization that we exemplify with shows some ideas how to improve, stabilize, and interpret the geometry of such low-rank relational structures, offering insight into how optimization can go astray in ill-conditioned, low-rank parameter spaces, but also how the implication of the approximation can be assessed. Give it a read: Low-rank constraints are not just computational conveniences — they have real geometric and optimization implications, and without appropriate mechanisms (feedback, orthogonalization, spectral refinement), learned low-rank representations (like attention maps or transition matrices) can be misleading or unstable. I’d like to hear your thoughts on this. Is it needed? Should we care? What’s a good future architecture? What should I read? Merry Christmas!

10

𝐑𝐋 𝐑𝐞𝐢𝐠𝐧𝐬 𝐒𝐮𝐩𝐫𝐞𝐦𝐞 Reinforcement Learning (RL) is having its moment. RL is foundational to the future of AI according to Chemistry: 🤖 RLHF is giving way to RLAIF, replacing slow and costly human feedback with scalable, AI-driven evaluations. 🧪 GRPO from DeepSeek introduces a novel method that avoids value function estimation yet generalizes effectively. 🧮 Autograders enable reliable RL by offering structured, testable rewards for tasks like coding and software use. 🌀 Reward hacking remains a risk. 🔍 RLVR (Reinforcement Learning from Verifiable Rewards) helps counter this by tying feedback to objective, testable outcomes. 🌱 The RL ecosystem is quickly maturing. 🧰 Open-source tools like Gymnasium and RLlib are making experimentation more accessible than ever. 🏢 Enterprise adoption is still early, but new infrastructure and scalable pipelines are accelerating that shift. RL is stepping into the spotlight. With advances like GRPO, RLAIF, and RLVR, the groundwork is being laid for AI systems that can learn, align, and adapt at scale. More ➡️ https://lnkd.in/gkvh7Wan

8