Developer · Local MCP server
Context Proxy
MCP proxy that lazy-loads tool schemas to cut context token overhead by 6-7x.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.kira-autonoma/context-proxy- Version
- 0.2.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-03-18
- Updated
- 2026-03-18
- Publisher
- kira-autonoma (GitHub) · 3 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/kira-autonoma) · how
- Repository
- github.com/kira-autonoma/mcp-context-proxy
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | mcp-lazy-proxy | 0.2.0 | stdio |
How to connect Context Proxy
Context Proxy runs locally from a Node.js package published to the npm registry: mcp-lazy-proxy version 0.2.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y mcp-lazy-proxy@0.2.0.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"context-proxy": {
"command": "npx",
"args": [
"-y",
"mcp-lazy-proxy@0.2.0"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from kira-autonoma (GitHub)
| Server | Runs |
|---|---|
| Agent Memory MCPAgent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops. | Local · stdio |
| Devtools23 developer utilities - base64, JWT, UUID, hash, QR, regex, timestamps. No API keys. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| Context CloudPersistent AI memory with shared team workspaces, typed knowledge chunks, and cross-tool support. | Remote & Local · SSE, stdioLive check: sign-in required |
| Context EngineCompress logs, retrieval chunks, and code context into structured LLM-ready signal. | Local · stdio |
| Context FirewallLocal MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs. | Local · stdio |
| Context FoundryRecursive Claude spawning for autonomous project builds with self-healing test loops. | Local · stdio |
| context-doctorProfile LLM context: token breakdown, wasted-context findings and fixes for chats and agents. | Local · stdio |
| Context7docs MCPA paid remote MCP for Context7 MCP docs, built to return verdicts, receipts, usage logs, and audit-r. | Remote · HTTPLive check: ✗ no handshake |
| ContextaPersistent memory and knowledge graph for AI assistants - keyword + vector + graph search. | Remote · HTTPLive check: sign-in required |
| ContextatlasPre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction. | Local · stdio |