github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #11138] README: add mcp-client-for-ollama into terminal community integrations #75746

New Issue
Open
opened 2026-05-05 08:10:10 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 08:10:10 -05:00
Owner
Copy Link

Original Pull Request: https://github.com/ollama/ollama/pull/11138

State: open
Merged: No

457129464-258eaba5-6530-4559-b3ce-70826178ff54

Adds mcp-client-for-ollama to the Community Integrations → Terminal list in README.md.

About mcp-client-for-ollama (ollmcp)

ollmcp-demo (10)

Python CLI/TUI that lets any local Ollama model call every tool on any Model Context Protocol (MCP) server.

  • 🌐 Multi-server support (STDIO / SSE / streamable HTTP)
  • 🎛️ Dynamic model switching & config persistence
  • 🎨 Rich rich-based interface with real-time streaming
  • 🧑‍💻 Human-in-the-Loop confirmations for tool calls
  • 🤔 Thinking Mode with visible chain-of-thought for models that support it (e.g. deepseek-r1, qwen3)
  • 🔄 Hot-reload of MCP servers during development
  • MIT-licensed and published on PyPI

GitHub Repo: https://github.com/jonigl/mcp-client-for-ollama
PyPI: https://pypi.org/project/mcp-client-for-ollama

Quick start

# one-liner install & run
pip install -U ollmcp && ollmcp
# or, if you use uv
uvx ollmcp

Demo 1

Demo 2

**Original Pull Request:** https://github.com/ollama/ollama/pull/11138 **State:** open **Merged:** No --- ![457129464-258eaba5-6530-4559-b3ce-70826178ff54](https://github.com/user-attachments/assets/35454f40-048a-4f2a-ad42-6d0c90623de4) Adds **mcp-client-for-ollama** to the *Community Integrations → Terminal* list in `README.md`. ## About `mcp-client-for-ollama` (`ollmcp`) ![ollmcp-demo (10)](https://github.com/user-attachments/assets/b48d368c-f010-47ae-a186-7e1297d57519) Python CLI/TUI that lets any local Ollama model call **every tool on any Model Context Protocol (MCP) server**. * 🌐 Multi-server support (STDIO / SSE / streamable HTTP) * 🎛️ Dynamic model switching & config persistence * 🎨 Rich `rich`-based interface with real-time streaming * 🧑‍💻 Human-in-the-Loop confirmations for tool calls * 🤔 Thinking Mode with visible chain-of-thought for models that support it (e.g. deepseek-r1, qwen3) * 🔄 Hot-reload of MCP servers during development * MIT-licensed and published on PyPI GitHub Repo: https://github.com/jonigl/mcp-client-for-ollama PyPI: https://pypi.org/project/mcp-client-for-ollama ### Quick start ```bash # one-liner install & run pip install -U ollmcp && ollmcp # or, if you use uv uvx ollmcp ``` ## Demo 1 <a href="https://asciinema.org/a/723801" target="_blank"><img src="https://github.com/user-attachments/assets/68fec311-4b92-45a5-9a1f-d7ae79474e72" /></a> ## Demo 2 <a href="https://asciinema.org/a/722730" target="_blank"><img src="https://github.com/user-attachments/assets/6b1862df-9503-45ac-95e3-56475ec2814a" /></a>
GiteaMirror added the pull-request label 2026-05-05 08:10:11 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#75746
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?