# IBM/mcp-cli

Repository: https://github.com/IBM/mcp-cli
Canonical: https://ross.abutalabs.com/products/mcp-cli
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-05T08:38:27+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 94, longevity 45
- inputs: {"age_days": 642, "days_push": 28, "days_rel": 42, "gap_med": 0, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2020, forks 310 (observed 2026-08-28T04:06:06.298582+00:00)

## What it is
A Python command-line client for interacting with Model Context Protocol (MCP) servers, integrating LLMs via CHUK Tool Processor and CHUK-LLM. It supports tool usage, conversation management, execution plans, and experimental OS-style virtual memory for context management, defaulting to local Ollama operation.

## Use cases
- chat with LLMs from the terminal using MCP tools
- connect to MCP servers and invoke their tools
- run multi-step tool orchestration plans with an LLM
- manage long conversations with token budgeting and virtual memory
- use local models via Ollama without API keys
- inspect and resume interrupted tool call graphs

## When to choose
- you need a terminal-based MCP client for testing or daily LLM workflows
- you want local, privacy-focused LLM usage via Ollama
- you need reproducible, checkpointed multi-step tool execution
- you want to experiment with context/memory management strategies

## When to avoid
- you need a GUI or web-based chat interface
- you require a production server-side MCP integration rather than a CLI
- you depend on features from a single vendor's closed ecosystem

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, llm-inference, agent-framework, chat-interface, mcp
- domain: large-language-models, developer-tools
- platform: cli, python, cross-platform
- tags: model-context-protocol, mcp-client, ollama, tool-orchestration, conversation-management, execution-plans, virtual-memory, ai-agents, command-line

## Member repositories
- IBM/mcp-cli (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.298582+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:00:13.375437+00:00, confidence not recorded.
  - readme: https://github.com/IBM/mcp-cli (fetched 2026-08-28T04:06:06.298582+00:00, sha 040c2900dae1)
- Data as of 2026-08-30T08:39:29.467469+00:00.