mcp-client-for-ollama MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Agent mode with configurable iteration limits for multi-step tool execution
Multi-server support: connect to multiple MCP servers simultaneously (STDIO, SSE, HTTP)
Human-in-the-loop: review and approve each tool call before execution
Model switching between any Ollama model mid-conversation
Thinking mode for visible chain-of-thought reasoning
Performance metrics: token counts, generation speed, timing data
Auto-discovery of existing Claude Desktop MCP configs

라이브 데모

실제 사용 모습

client-for-ollama.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "client-for-ollama": {
      "command": "uvx",
      "args": [
        "mcp-client-for-ollama"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "client-for-ollama": {
      "command": "uvx",
      "args": [
        "mcp-client-for-ollama"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "client-for-ollama": {
      "command": "uvx",
      "args": [
        "mcp-client-for-ollama"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "client-for-ollama": {
      "command": "uvx",
      "args": [
        "mcp-client-for-ollama"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "client-for-ollama",
      "command": "uvx",
      "args": [
        "mcp-client-for-ollama"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "client-for-ollama": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-client-for-ollama"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add client-for-ollama -- uvx mcp-client-for-ollama

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: mcp-client-for-ollama

How to use MCP tools with local LLMs for free

👤 Developers who want MCP functionality without cloud API costs ⏱ ~15 min beginner

언제 쓸까: You have MCP servers configured but want to use them with a local model instead of Claude or GPT.

사전 조건

Ollama installed and running — ollama.com — install, then ollama pull llama3.2:3b
ollmcp installed — pip install ollmcp

흐름

Launch with auto-discovery

ollmcp --auto-discovery --model llama3.2:3b✓ 복사됨

→ TUI launches, shows discovered MCP servers from Claude config
Test a tool call

List the files in my current directory.✓ 복사됨

→ Model calls the filesystem MCP tool and returns results
Enable agent mode for multi-step tasks

Type /agent to enable agent mode, then: 'Find all TODO comments in this project and summarize them.'✓ 복사됨

→ Model iterates: searches files, reads matches, produces summary

결과: Working MCP tool-use powered entirely by a local model — zero API cost.

함정

Small models (3B) struggle with complex tool-use chains — Use 7B+ models for agent mode; 3B is fine for single tool calls
Model calls wrong tool or wrong params — Enable human-in-the-loop (/hil) to catch and correct bad tool calls

함께 쓰기: filesystem

Connect to multiple MCP servers for a cross-tool workflow

👤 Power users running several MCP servers ⏱ ~20 min intermediate

언제 쓸까: You want a local LLM to orchestrate across filesystem, GitHub, and other MCP servers in one session.

사전 조건

MCP server config JSON — Create a JSON file with all your server definitions (same format as Claude Desktop config)

흐름

Launch with config

ollmcp --servers-json ~/mcp-servers.json --model qwen2.5:7b✓ 복사됨

→ All servers connected, tools listed
Use /tools to manage

Type /tools to see all available tools across servers. Disable any you don't need.✓ 복사됨

→ Tool list with enable/disable toggles
Run a cross-server task

Read my project's README.md, then search GitHub for similar projects and compare their approaches.✓ 복사됨

→ Model chains filesystem read + GitHub search

결과: A local LLM orchestrating tools from multiple MCP servers in one conversation.

함정

Too many tools confuse smaller models — Disable unused tools with /tools — fewer tools means better tool selection

함께 쓰기: github

Use human-in-the-loop to safely test MCP servers

👤 Developers building or testing new MCP servers ⏱ ~15 min beginner

언제 쓸까: You're developing an MCP server and want to test tool calls with approval before execution.

흐름

Enable HIL mode

ollmcp -s ./my-mcp-server.py --model llama3.2:3b then type /hil to enable✓ 복사됨

→ Human-in-the-loop enabled
Trigger tool calls

Ask the model to use your server's tools. Each call pauses for your approval.✓ 복사됨

→ Tool call preview shown, waiting for y/n
Review and iterate

Reject bad calls, approve good ones. Check /show-metrics for timing.✓ 복사됨

→ Approved calls execute; rejected ones prompt retry

결과: A safe testing loop for MCP server development with full visibility into every tool call.

조합

다른 MCP와 조합해 10배 효율

client-for-ollama + filesystem

Local Ollama model reads and edits files via filesystem MCP — fully offline coding assistant

ollmcp --auto-discovery --model qwen2.5:7b then: 'Read src/main.py and add error handling to the parse function.'✓ 복사됨

client-for-ollama + github

Use a local model to search GitHub repos and create issues without cloud API costs

Connect GitHub MCP to ollmcp, then: 'Search our org for repos with no CI config and create tracking issues.'✓ 복사됨

비용 및 제한

운영 비용

API 쿼터: No external API quota — runs on local Ollama. MCP server limits apply per-server.
호출당 토큰: Depends on Ollama model context window (typically 2k-128k)
금액: Completely free. Ollama is free. ollmcp is MIT-licensed. You only pay for electricity.
팁: This is the zero-cost option for MCP tool-use. Use smaller models (3B) for simple tasks, larger (7B+) for agent mode.

보안

권한, 시크릿, 파급범위

자격 증명 저장: MCP server credentials configured in the servers JSON file or environment variables — same as Claude Desktop config

데이터 외부 송신: Ollama runs locally. MCP servers egress to their own backends. No data leaves your machine by default unless an MCP server sends it.

Agent mode can execute multiple tool calls in a loop. Use human-in-the-loop (/hil) when running with write-capable MCP servers.
Ollama Cloud models route through external servers — use local models for sensitive data.

문제 해결

자주 발생하는 오류와 해결

Connection refused to Ollama

Ensure Ollama is running: ollama serve. Default port is 11434. Use --host to specify a custom host if needed.

확인: curl http://localhost:11434/api/tags

Model doesn't call tools / ignores MCP

Not all models support tool-use well. Use qwen2.5:7b or llama3.1:8b which have good tool-use training. Avoid tiny models for complex chains.

확인: Test with a simple single-tool prompt first

MCP server fails to connect

Check your servers JSON config. Ensure the command path is absolute and the server binary/script exists. Run the server command manually to see errors.

확인: Run the MCP server command directly in a terminal

Auto-discovery finds no servers

ollmcp looks for Claude Desktop config at the standard path. On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

확인: ls ~/Library/Application\ Support/Claude/claude_desktop_config.json

대안

mcp-client-for-ollama 다른 것과 비교

대안	언제 쓰나	단점/장점
Claude Desktop	You want the best MCP experience and are willing to pay for Claude API	Cloud-based, costs money, but much better tool-use than local models
oterm	You want an Ollama TUI without MCP focus	No MCP integration; just chat

mcp-client-for-ollama

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

설치

클라이언트 선택

사용 사례

실전 활용법: mcp-client-for-ollama

How to use MCP tools with local LLMs for free

사전 조건

흐름

함정

Connect to multiple MCP servers for a cross-tool workflow

사전 조건

흐름

함정

Use human-in-the-loop to safely test MCP servers

흐름

조합

다른 MCP와 조합해 10배 효율

비용 및 제한

운영 비용

보안

권한, 시크릿, 파급범위

문제 해결

자주 발생하는 오류와 해결

대안

mcp-client-for-ollama 다른 것과 비교

더 보기

리소스