MCPlexor
MCP multiplexer that cuts agent context usage by 95%
Details
- External ID
- 46942466
- Source
- HN
- Company
- —
- Product
- MCPlexor
- Website domain
- mcplexor.com
- Launched
- Feb. 9, 2026
- Cohort
- —
- Upvotes
- 6
- Upvotes percentile
- 0.28099730458221023
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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:Agent asks for a capability ("create an issue") MCPlexor routes to the right server using semantic matching Only relevant tools get exposed Result: ~500 tokens overhead instead of ~20k.Technical Details: - Written in Go, single binary, no runtime deps - Supports both stdio and HTTP transports - Stores credentials in OS keychain (macOS Keychain, Windows Credential Manager, Linux keyring via zalando/go-keyring) - Works with Claude Desktop, Cursor, Augment Code, or any MCP-compatible clientThe routing logic can run entirely locally using Ollama. No API calls, no cost, works offline.Business Model (for transparency): - Local/Ollama users: completely free - Cloud tier (on waitlist): we run inference on efficient small models instead of Opus/Pro, pass on savings, take a margin The bet is that routing is a narrow enough task that a fine-tuned 7B model does it as well as a frontier model. Early testing suggests this works.CLI uploads: https://github.com/arustagi101/mcplexor Install: `curl -fsSL https://mcplexor.com/install.sh | bash` Happy to answer questions about the architecture, the routing approach, or anything else.
Enrichment
- Theme
- Model Context Protocol developer tools
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- mcp multiplexer for agents
- Manually corrected
- False
Could you build this?
Yes It acts as a lightweight proxy/multiplexer for MCP servers, exposing a single entry point or dynamic schema retrieval to minimize agent prompt tokens, which is straightforward middleware to vibe code.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 159 launches clear the similarity bar, closest 8 shown.
Attention rank: #131 of 160 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 95 days after the earliest competitor.
- MCP Mesh · hn · 2025-12-30 · 8 upvotes · similarity 0.54
- MCP Gateway · hn · 2025-12-03 · 10 upvotes · similarity 0.53
- MCPfinder · hn · 2026-04-20 · 9 upvotes · similarity 0.52
- Mcp2cli · hn · 2026-03-09 · 146 upvotes · similarity 0.50
- MCP server gives your agent a budget (save tokens, get smarter results) · hn · 2026-04-15 · 6 upvotes · similarity 0.46
- TokenControlPlane · ph · 2026-09-15 · 1 upvotes · similarity 0.45
- ContextVM · hn · 2026-02-25 · 6 upvotes · similarity 0.45
- MCPShark · hn · 2025-12-10 · 37 upvotes · similarity 0.44
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.