# toolrush-mcp

> toolrush-mcp — dhava-gautama-toolrush-mcp. Use this tool when you need to optimize MCP agent performance by reducing tool-call overhead, enabling fast read and search capabilities, and utilizing a warm persistent shell for batched calls. It solves problems related to slow tool invocation and high latency in MCP agent harnesses. Ideal for use cases requiring frequent tool calls, such as automated workflows and continuous integration pipelines.

Canonical page: https://skillsregistry.net/skills/dhava-gautama-toolrush-mcp  
JSON: https://api.skillsregistry.net/v1/skills/dhava-gautama-toolrush-mcp

## Description

Kill the tool-call tax in any MCP agent harness: fast read/search, warm persistent shell, batched calls. Go port of OnlyTerp/toolrush.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/dhava-gautama/toolrush-mcp)

## 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": "dhava-gautama-toolrush-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dhava-gautama-toolrush-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dhava-gautama-toolrush-mcp/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