# BeehiveInnovations/pal-mcp-server

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

Repository: https://github.com/BeehiveInnovations/pal-mcp-server
Canonical: https://ross.abutalabs.com/products/pal-mcp-server
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-12-15T17:07:31+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 57, release rhythm 49, longevity 32
- inputs: {"age_days": 451, "days_push": 261, "days_rel": 261, "gap_med": 0, "n_releases_24m": 74}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11724, forks 1029 (observed 2026-08-28T04:10:49.590881+00:00)

## What it is
PAL MCP (formerly Zen MCP) is a Model Context Protocol server that lets AI coding CLIs like Claude Code, Gemini CLI, and Codex CLI orchestrate multiple LLM providers (Gemini, OpenAI, Anthropic, Grok, Ollama, OpenRouter, Azure) within a single workflow. It includes a CLI-to-CLI bridge ('clink') for spawning isolated subagent CLIs with role specialization and context preservation.

## Use cases
- route coding tasks to multiple AI models from one CLI session
- get consensus answers from several LLMs before implementing a feature
- spawn isolated subagent CLIs for code review without polluting my context window
- use Ollama local models alongside cloud models in Claude Code
- hand off a model debate to another CLI with full conversation context
- connect Gemini CLI and Codex CLI as subagents in my workflow

## When to choose
- you use AI coding CLIs and want to mix multiple model providers in one session
- you need consensus or second opinions from different LLMs during development
- you want isolated subagent contexts for heavy tasks like code review or bug hunting

## When to avoid
- you only use a single model provider and a single CLI
- you need a simple chat interface rather than CLI-based developer workflows
- you want a fully permissive license - the license is non-standard

## Facets
- artifact type: service
- maturity: active
- function: mcp, agent-framework, llm-inference, developer-tools
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: model-orchestration, cli-bridge, multi-provider, consensus, subagents, ai-agents

## Member repositories
- BeehiveInnovations/pal-mcp-server (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:49.590881+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 2026-08-29T17:15:22.373973+00:00, confidence not recorded.
  - readme: https://github.com/BeehiveInnovations/pal-mcp-server (fetched 2026-08-28T04:10:49.590881+00:00, sha 88faf5b0f7bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.