🧿 One MCP, unlimited tools
Works with Claude Code · Cursor · Windsurf · Any MCP client
The Problem
Each MCP server consumes 3K-30K tokens per request. Connect 5 servers and you've burned 55K tokens before the conversation starts. Connect 10+ and you're at 100K tokens.
The math is brutal: Claude Opus 4.5 at $5/M input tokens, 20 days × 10 conversations × 10 messages × 3K tokens = $30/month per MCP server - even if you never use the tools.
And then there's context rot - your AI literally gets dumber as you add more tools (Chroma Research, 2025).
The Solution
OneTool is one MCP server that exposes tools as a Python API. Instead of reading tool definitions, your agent writes code:
__ot brave.search(query="react docs 2026")
Configure one MCP server. Use unlimited tools.
"Agents scale better by writing code to call tools instead. This reduces the token usage from 150,000 tokens to 2,000 tokens...a cost saving of 98.7%"
96% fewer tokens. 24× lower cost. No context rot.
See It In Action
| Demo | Description |
|---|---|
| Compare the Search | Side-by-side token comparison |
| Build a Wikipedia Tool | Create a custom tool in seconds |
Install
Requires uv:
uv tool install onetool-mcp
onetool init
Add to Claude Code:
claude mcp add onetool onetool
Or manually add to ~/.claude/mcp.json:
{
"mcpServers": {
"onetool": {
"command": "onetool"
}
}
}
That's it. All 100+ tools work out of the box.
Verify: onetool init validate
Features
| Feature | Description |
|---|---|
| 96% Token Savings | ~2K tokens no matter how many tools you add |
| 100+ Built-in Tools | Web search, databases, file ops, diagrams, conversions |
| Explicit Execution | See exactly what runs - __ot brave.search(q="AI") |
| MCP Server Proxy | Wrap existing MCP servers without the tool tax |
| Scaffold Tools | Build new tools as part of the conversation |
| Smart Tools | Delegate to cheaper LLMs (10× savings) |
| Single YAML Config | Global and project scopes, per-pack settings |
| Security Layers | AST validation, path boundaries, output sanitisation |
Tools
15 packs, 100+ tools ready to use:
| Pack | Tools | Description |
|---|---|---|
brave | search, news | Web and news search |
code | search, search_batch, status | Semantic code search |
context7 | resolve, get_docs | Library documentation |
convert | pdf_to_md, docx_to_md, pptx_to_md | Document conversion |
db | query, schema, tables | Database operations |
diagram | create | Mermaid diagrams |
excel | read, write, query | Excel files |
file | read, write, list, search | File operations |
ground | search | Google Grounding |
llm | transform, transform_file | LLM-powered transforms |
ot | help, tools, stats | Introspection |
package | npm, pypi, cargo | Package versions |
ripgrep | search, count | Fast code search |
scaffold | tool | Generate new tools |
web | fetch, fetch_batch | Web fetching |
📖 Complete tools reference — full summary table with all 100+ tools
MCP Server Proxy
Wrap any existing MCP server and call it explicitly - without the tool tax:
# .onetool/onetool.yaml
mcp_servers:
chrome-devtools:
command: npx
args: ["-y", "@anthropic-ai/chrome-devtools-mcp@latest"]
github:
command: npx
args: ["-y", "@anthropic-ai/github-mcp-server@latest"]
__ot mcp.call(server="github", tool="get_file_contents", arguments={"path": "README.md"})
Extending
Drop a Python file, get a pack. No registration, no config:
# .onetool/tools/wiki.py
pack = "wiki"
def summary(*, title: str) -> str:
"""Get Wikipedia article summary."""
import httpx
url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{title}"
return httpx.get(url).json().get("extract", "Not found")
__ot wiki.summary(title="Python_(programming_language)")
Documentation
- Quickstart - 30 seconds to first tool call
- Installation - All platforms
- Configuration - YAML schema
- Tools Reference - All 100+ tools
- Security - Security layers
- Extending - Build your own
References
- Code Execution with MCP - Anthropic Engineering
- Context Rot - Chroma Research
Contributing
License
GPLv3 - Will transition to MIT at v2.0.
Support
If you find OneTool useful: