# io.github.kira-autonoma/context-proxy

> Use this tool when you need to optimize context token overhead in MCP proxies, as it lazy-loads and caches tool schemas to reduce overhead by 4-32x. This proxy takes in MCP requests and outputs optimized responses, making it ideal for applications with high context token usage. It is particularly useful in scenarios where performance and efficiency are critical, such as large-scale data processing or real-time systems.

Canonical page: https://skillsregistry.net/skills/io-github-kira-autonoma-context-proxy  
JSON: https://api.skillsregistry.net/v1/skills/io-github-kira-autonoma-context-proxy

## Description

MCP proxy that lazy-loads tool schemas to cut context token overhead by 6-7x

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 0.1.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.kira-autonoma%2Fcontext-proxy)
- **Repository:** <https://github.com/kira-autonoma/mcp-context-proxy>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "io-github-kira-autonoma-context-proxy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-kira-autonoma-context-proxy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-kira-autonoma-context-proxy/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt