Alternatives
Products that do what MCP file tools silently eat your context window.I built one that doesnt does
Hi, I am Anthony. Every token your filesystem tools consume is context the model cannot use for reasoning. Most MCP file servers are O(file size) on every operation: reads return the whole file, edits rewrite the whole file. The context window fills up before the agent gets anything meaningful done, and the problem compounds silently as your files grow. Chisel makes edits O(diff) and reads O(match). The agent sends a unified diff instead of a full rewrite, and queries with grep or sed instead of reading entire files. On a 500-line file this is nearly two orders of magnitude less context per…
- 1CM
Every MCP tool call dumps raw data into Claude Code's 200K context window. A Playwright snapshot costs 56 KB, 20 GitHub issues cost 59 KB. After 30 minutes, 40% of your context is gone. I built an MCP server that sits between Claude Code and these outputs. It processes them in sandboxes and only returns summaries. 315 KB becomes 5.4 KB. It supports 10 language runtimes, SQLite FTS5 with BM25 ranking for search, and batch execution. Session time before slowdown goes from ~30 min to ~3 hours. MIT licensed, single command install: /plugin marketplace add mksglu/claude-context-mode…
Feb 2026 · github.com
- 2
- 3AP
After having cycled through various CLI-based todo apps, I started to realise that I actually don’t need a tool at all for managing my todos. Most of the time, my use cases are quite simple, like viewing my todo items, checking them off, or adding a new one. Rather than having to memorise CLI commands for these interactions (which I’m not super good at), I figured that it’s easier for me to use my text editor directly, and have an editor plugin help me with the visual structure and some convenience functionality. So, kind-of similar to Emacs Org Mode, but without having to use Emacs. I…
2022
- 4
- 5
- 6
- 7OS
Large Language Models (LLMs) are powerful, but they’re limited by fixed context windows and outdated knowledge. What if your AI could access live search, structured data extraction, OCR, and more—all through a standardized interface? We built the JigsawStack MCP Server, an open-source implementation of the Model Context Protocol (MCP) that lets any AI model call external tools effortlessly. Here’s what it unlocks: - Web Search & Scraping: Fetch live information and extract structured data from web pages. - OCR & Structured Data Extraction: Process images, receipts, invoices, and handwritten…
2025
- 8
- 9MS
Hey, I'm Nick from Nutrient, I want to share our newly released MCP Server that enables document workflows using natural language — things like redacting, merging, signing, converting formats, or extracting data. While many MCP servers have traditionally been developer-focused, we recognized that the technology could be highly effective in promoting the adoption of tools that are often hidden from end-user interfaces. We’re really interested to see if this side of the protocol could continue to mature. One thing we struggled with was the inability to receive documents from the client (no…
2025 · github.com
- 10MT
https://github.com/mcp-shark/mcp-shark Site: https://mcpshark.sh/ I built MCPShark, a traffic inspector for the Model Context Protocol (MCP). It sits between your editor/LLM client and MCP servers so you can: • See all MCP traffic (requests, responses, tools, resources) in one place • Debug sessions when tools don’t behave as expected • Optionally run “Smart Scan” checks to flag risky tools / configs
Dec 2025
- 11GF
I kept re-Googling the same flags, so I built a tiny, fast directory of copy-ready CLI commands. It’s static (vanilla JS), instant search, keyboard nav (↑/↓ + Enter), favorites (localStorage), and linkable queries. Examples: • grep errors → https://www.greppers.com/?q=grep%20error%20logs • list open ports (macOS) → https://www.greppers.com/?q=list%20open%20ports • show git branch graph → https://www.greppers.com/?q=git%20graph • tail with colors → https://www.greppers.com/?q=tail%20colors Tech notes: static site on Netlify, no…
2025 · greppers.com
- 12MF
Hey everyone, I've wanted an easy way to control which mcp server tools are available to clients. So for example, I might want a gmail server to only expose the read tool (but not send, delete etc). I figured if I create a cli for spawning mcp servers, I could intercept the stdin, stdout, stderr etc and modify what the clients see when they are making calls to list tools, resources, and prompts. Well it worked! In the initial version you can easily add a server to claude with a safe list of tools: npx -y mcpgod add @modelcontextprotocol/server-everything --client claude --tools=echo,add…
2025 · github.com
- 13OS
2025 · github.com
- 14AC
We built a reference MCP server that lets your editor/agent learn a codebase directly from source (signatures, types, AST, comments). Docs are optional. The reference impl runs on our open-source project’s codebase. Why we built it Docs are important, but they add another abstraction layer between your code and your users. Keeping them at the right quality is hard (especially at a startup), and LLM-generated docs are often mediocre until you invest real polish. Exposing code to the model in a structured way keeps answers grounded and current, and it’s always available. You can even…
Sep 2025 · github.com
- 15MV
A few days ago I posted MCPShark (a traffic inspector for the Model Context Protocol). I just shipped a VS Code / Cursor extension that lets you view MCP traffic directly in the editor, so you’re not jumping between terminals, logs, and "I think this is what got sent". VS Code Marketplace: https://marketplace.visualstudio.com/items?itemName=MCPShark... Main repo: https://github.com/mcp-shark/mcp-shark Feature requests / issues: https://github.com/mcp-shark/mcp-shark/issues Site: https://mcpshark.sh/ If…
Dec 2025
- 16MT
Hi HN, I built mcp-tidy to solve a problem I kept running into with Claude Code. As I tried different MCP servers over the past few months, my ~/.claude.json accumulated servers I'd forgotten about. Claude Code loads all tool descriptions (built-in + MCP) into context, so unused servers add overhead you don't need. The tool is simple: three commands. - `mcp-tidy list` - see what's configured (global + per-project) - `mcp-tidy stats` - check actual usage from transcript logs - `mcp-tidy remove --unused` - clean up with automatic backup It parses the JSONL transcript logs in…
Jan 2026 · github.com
- 17MA
I’ve been building and using agents heavily lately. The Model Context Protocol ecosystem is growing insanely fast, but discovering and configuring new tools is still highly manual. Every time I needed to connect an agent to a new service, I had to browse registries, figure out the transport type, identify required env vars, and manually update "mcp.json" files. So I built MCPfinder. It aggregates servers from the official MCP registry, Glama, and Smithery (around 25,000 combined entries) into a deduplicated, ranked catalog. But the real twist is the DX: MCPfinder is itself an MCP server :D…
Apr 2026 · mcpfinder.dev
- 18MM
I built MCPlexor to solve a token waste problem I kept running into with MCP-based agents. The Problem: MCP (Model Context Protocol) is great for giving LLMs access to external tools. But if you connect multiple servers (GitHub, Linear, Postgres, Slack), you end up with 40-50k tokens of tool definitions injected into every request – before the agent even does anything. On a 200k context model, that's 25% gone. On smaller models, it's worse. And most runs only use 1-2 tools. The Solution: MCPlexor sits between your agent and your MCP servers. Instead of loading all tool definitions upfront:…
Feb 2026 · mcplexor.com
- 19IB
Mar 2026 · github.com
- 20CC
If you had to build a context window manager in 24h, would you stick to the existing model or come up with something better? Here's what I did: 1. Built a proxy that intercepts Codex's calls to OpenAI and rewrites them on the fly. 2. Replayed 3,807 rounds of SWE-bench Verified traces through it: avg prompt 44k → 6k tokens (-87%). 3. Posted it to HN to get the next reduction applied to my confidence interval — starting with the inevitable "How about accuracy?" npx -y pando-proxy · github.com/human-software-us/pando-proxy
Apr 2026 · npmjs.com
- 21
- 22
- 23M1
Got tired of every MCP example being overly verbose, or needing Docker or Mac-only scripts, so I threw together MCP-123. Point it at a tools.py, run `server.run_server(...)`, and the client auto-discovers/calls functions with OpenAI. I hope this is useful to you all.
2025 · github.com
- 24AM
Hey HN! One of the biggest limitations of tools like Cursor is that they only have context over the project you have open. We built this MCP to allow you to fetch code context from all of your repos. It uses Sourcebot under the hood, an open source code search tool that supports indexing thousands of repos from multiple platforms. The MCP server leverages Sourcebot's index to rapidly fetch relevant code snippets and inject it into your agents context. Some use cases this unlocks include: - Finding all references of an API across your companies repos to allow the agent to provide accurate…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →