Free tools Windows power users keep installed
One-click scans. No signup required.
A reported measurement of Chrome DevTools MCP put its tool definitions at roughly 18,000 tokens—about 9% of a 200,000-token context window—before an agent did useful work. The figure, attributed to Pi creator Mario Zechner by The New Stack on October 5, 2026, is not a universal MCP cost. Pi’s workaround is to keep most tool definitions out of the prompt until they are needed, discovering and calling tools through JavaScript instead.
What the 18,000-token figure measures
The reported figure is the context cost of Chrome DevTools MCP’s tool definitions: descriptions that tell a model which tools exist and how to call them. It is not a count of tokens spent completing a browser task, nor does it include every possible tool result. The New Stack attributes the approximate measurement to Zechner; it is a reported example, not an independently replicated benchmark.
As an Amazon Associate I earn from qualifying purchases.
The same article reports that Playwright MCP used about 13,700 tokens to describe 21 tools, framed as roughly 6.8% of a 200,000-token context window. These measurements illustrate how a large set of detailed definitions can occupy prompt space before a task begins. Actual overhead depends on the server, client, model, and configuration; the figures do not establish a typical cost for MCP as a whole.
How Pi’s Codemode workaround works
Pi’s approach is to avoid placing every MCP tool definition in the model’s context by default. Instead, its system prompt gives a one-line description of each server. When the agent needs a capability, it can use Codemode to discover and call the relevant tools from JavaScript, then return selected output to the model.
#1 Best Overall
- EVOLUTION CORE ULTRA 9 285H MINI PC - GMKtec EVO-T1 is the next evolution in AI mini PC Ultra 9 series. The Core Ultra 9 285H offers 16 cores (six P-cores + eight E-cores + two LPE-cores) and 16 threads with a turbo clock of 5.4 GHz. It is currently one of the best value for performance AI mini PC computers.
- AI NPU - The 285H features an Intel AI Boost NPU, capable of up to 13 TOPS (Tera Operations per Second) for INT8 calculations, which is designed to accelerate AI tasks.
- INTEL ARC 140T GAMING PC - The Arc 140T GPU includes 8 Xe cores and supports features like DirectX 12, OpenGL 4.5, and OpenCL 3, making it capable of handling modern games and creative applications. It also supports Quick Sync Video for efficient video encoding and decoding, as well as AV1 encoding and decoding.
- 64GB DDR5 RAM + 1TB SSD - The EVO-T1 is equipped with Dual 32GB (Total 64GB) SO-DIMM DDR5 5600MHz memory sticks. 2TB PCIE 4.0 SSD Drive with 3x M.2 2280 Expansion slots. Each slot capable of reading up to 4TB. (12TB MAX)
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-T1 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and USB Type-C Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
This changes when tool details reach the model: discovery happens as needed rather than loading all definitions up front. It can reduce the initial schema burden, but it does not mean that tool results or useful information never enter the model’s context. The agent still needs relevant results to reason about the task.
Choose which tools are directly exposed
Pi also allows developers to mix direct exposure with deferred discovery and blocking. A tool that should be immediately available can be exposed directly; less frequently needed tools can stay behind Codemode; tools that should not be callable can be blocked. The New Stack’s example is to expose GitHub’s search_code, defer get_* tools, and block delete_* tools.
Rank #2
- LOW ENERGY HIGH PERFORMANCE MINI PC - The Intel Core Ultra 5 125U is part of the Ultra 5 lineup, using the Meteor Lake architecture with BGA 2049. Intel Hyper-Threading technology is available and effectly doubles the core-count of the P-Cores, to a total of 14 threads. Core Ultra 5 125U has 12 MB of L3 cache and operates at 1300 MHz by default, but can boost up to 4.3 GHz, depending on the workload. With a TDP of 15 W, the Core Ultra 5 125U consumes very little energy but outputs high performance efficiency
- 32GB DDR5 RAM + 512GB SSD - The K15 mini computer is equipped with Dual 16GB (Total 32GB) SO-DIMM DDR5 4800MHz memory sticks. 512GB PCIE 4.0 SSD Drive with 3x M.2 2280 Expansion slots. Each slot capable of reading up to 8TB. (24TB MAX)
- QUAD SCREEN 4K DISPLAY SUPPORT - K15 Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and USB Type-C Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support
- OCULINK PORT - The Oculink port on the rear interface enables higher bandwidth capabilities, better frame rates and lower lag. The standard also operates at PCIe x4 speeds, compared to Thunderbolt's x3. Gamers and content creators can benefit from Oculink's higher bandwidth, resulting in better performance and lower lag for eGPU setups
- DUAL NIC FAST 2.5GBE + WIFI 6E + BT 5.2 - Dual Ethernet 2.5GbE LAN port design provides more applications, such as firewall, multichannel aggregation, soft routing, file storage server. Built-in WIFI 6E / Bluetooth 5.2 is more stable and efficient to connect multiple wireless devices such as projector, printer, monitor, speakers and etc
The article reports a default Codemode tool-declaration budget of 3,000 tokens. Tools beyond that budget remain discoverable, while MCP tools using default exposure do not count against it. These are Pi-specific implementation details, not general MCP limits or a promise that every other agent platform will produce the same savings.
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Fix the driver behind crashes, sound loss and screen glitches3Repair Windows errors before they cause bigger problemsHow this compares with Pi’s earlier CLI approach
Before Codemode, Zechner’s approach used Bash and a small set of scripts. The New Stack says the CLI-based browser tools needed a 225-token README, and that outputs could be piped, filtered, or saved without first passing through the model. That comparison is reported by the article, not a separately verified head-to-head benchmark.
Rank #3
- Entry-level NAS Personal Storage：UGREEN NAS DH2300 is your first and best NAS made easy. It is designed for beginners who want a simple, private way to store videos, photos and personal files, which is intuitive for users moving from cloud storage or external drives and move away from scattered date across devices. This entry-level NAS 2-bay perfect for personal entertainment, photo storage, and easy data backup (doesn't support Docker or virtual machines).
- Set Your Devices Free, Expand Your Digital World: This unified storage hub supports massive capacity up to 64TB.*Storage drives not included. Stop Deleting, Start Storing. You can store 22 million 3MB images, or 2 million 30MB songs, or 43K 1.5GB movies or 67 million 1MB documents! UGREEN NAS is a better way to free up storage across all your devices such as phones, computers, tablets and also does automatic backups across devices regardless of the operating system—Window, iOS, Android or macOS.
- The Smarter Long-term Way to Store: Unlike cloud storage with recurring monthly fees, a UGREEN NAS enclosure requires only a one-time purchase for long-term use. For example, you only need to pay $459.98 for a NAS, while for cloud storage, you need to pay $719.88 per year, $2,159.64 for 3 years, $3,599.40 for 5 years. You will save $6,738.82 over 10 years with UGREEN NAS! *NAS cost based on DH2300 + 12TB HDD; cloud cost based on 12TB plan (e.g. $59.99/month).
- Blazing Speed, Minimal Power: Equipped with a high-performance processor, 1GbE port, and 4GB RAM on Board, this NAS handles multiple tasks with ease. File transfers reach up to 125MB/s—a 1GB file takes only 8 seconds. Don't let slow clouds hold you back; they often need over 100 seconds for the same task. The difference is clear.
- Let AI Better Organize Your Memories: UGREEN NAS uses AI to tag faces, locations, texts, and objects—so you can effortlessly find any photo by searching for who or what's in it in seconds. It also automatically finds and deletes similar or duplicate photo, backs up live photos and allows you to share them with your friends or family with just one tap. Everything stays effortlessly organized, powered by intelligent tagging and recognition.
The practical distinction is not simply “MCP versus no MCP.” It is whether tool descriptions and intermediate results must enter the model’s context early, or whether scripts can discover, filter, combine, or save information before returning a smaller useful result. The reported comparison does not establish that one approach is best for every workflow.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.A separate Pi prompt-token comparison
The New Stack also reports that Pi 1.0 release notes described a GPT-5.6 request with default tools and Codemode falling from roughly 5,300 prompt tokens to 3,300. The reported changes included shortening Codemode’s description, moving model API documentation out of the prompt, and avoiding repeated declarations for tools scripts could already access.
Rank #4
- [Powerful PC] Gaming PC equipped with Core i9-14900F, 24 Cores 32 Threads, 36M Cache, Max Turbo Frequency: 5.8GHz, Windows 11 pro (64 Bit). With GeForce RTX 50 Series GPUs. Adopting DLSS 4 technology, it dramatically improves frame rate performance, supports FP4 low-precision computing, and doubles the efficiency of AI inference. SD graph generation speed is 3 times faster than RTX 4070 Super, significantly increasing creative productivity. Graphics work productivity has increased significantly.
- [High Speed DDR5 RAM & PCIE4.0 SSD] The desktop computer is equipped with Dual-DDR5 RAM (dual channel DDR5 high-speed memory, which can support up to 128GB RAM), 1 x M.2 2280 PCIE4.0 high-speed SSD, and support add 2 x 2.5-inch SATA HDD/SSD(not include) is enough to accommodate system files and massive games, Excellent reading and writing speed greatly shortening your boot time.
- [8K@60Hz Quad-Display] Desktop PC with GeForce RTX 5070 12G GDDR7, supporting DLSS 4, ray tracing, and AI cores. Easily connect 4 monitors via 1×HDMI 2.1 + 3×DP 1.4a — all ports support 8K@60Hz. Delivers stunning visuals and ultra-smooth performance for home entertainment, live streaming, video editing, AI workloads, 3D rendering, and AAA gaming.
- [Functional Interfaces] Mini computer is equipped with 4 x USB 3.2, 4 x USB2.0, 1 x HDMI2.1 port, 3 x DP ports, 2xRJ-45 Gigabit Network Ethernet, 1 x Fiber Optic PORT, 1 x Audio in/out. Built-in Bluetooth 5.4 and IEEE 802.11be wifi 7, Higher transfer rates and lower latency. Mini PC supports multiple device connection and can be used with servers, monitoring equipment, office equipment, projectors, televisions, etc, Mini desktop computer support automatic power on and Wake On Lan.
- [Warranty & Liquid Cooling] Warrant: 2 year/24 months. The compact computer size: 11.6*9.3*3.9in, 9.25lb, Chassis built-in 2 large copper fans, built-in liquid cooling device, to further enhance the computer heat dissipation, and at the same time can reduce noise, give full play to the overall performance of the computer.
This is a Pi-specific request comparison, distinct from the Chrome DevTools MCP measurement. It should not be read as a direct estimate of how much Codemode will save in another setup.
What Codemode does not solve
Deferring definitions addresses prompt overhead, but the New Stack says it does not resolve all of Zechner’s objections to MCP, particularly composability. Pi’s described implementation runs scripts inside QuickJS without Node APIs, filesystem access, network access, or timers. Those are constraints of this Pi implementation, not defining properties of MCP or of every Codemode-style system.
For a team evaluating the approach, the useful questions are how many schemas enter context before a task, how tools are discovered, whether intermediate results can be filtered or saved without being sent through the model, and which tools should be direct, deferred, or blocked. The reported examples show design options, not a controlled evaluation proving a universal winner.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
