PAL MCP: Many Workflows. One Context.

[!IMPORTANT]
This project is maintained with the help of Claude-Code. Is it, however, reviewed, tested, and reworked with a human-in-the-loop.

No AI slop here. Purely AI-made<->AI-consumed tooling is hot garbage, and that's putting it mildly.

That said, if you have any problems with code that is written by AI - you've been warned. But, then again, why would you be interested in an AI-related tool in the first place... ¯\_(ツ)_/¯

---

🆕 Now with CLI-to-CLI Bridge

The new clink (CLI + Link) tool connects external AI CLIs directly into your workflow:

• Connect external CLIs like Gemini CLI, Codex CLI, Claude Code, and Antigravity (agy) directly into your workflow
• CLI Subagents - Launch isolated CLI instances from within your current CLI! Claude Code can spawn Codex subagents, Codex can spawn Gemini CLI subagents, etc. Offload heavy tasks (code reviews, bug hunting) to fresh contexts while your main session's context window remains unpolluted. Each subagent returns only final results.
• Context Isolation - Run separate investigations without polluting your primary workspace
• Role Specialization - Spawn planner, codereviewer, or custom role agents with specialized system prompts
• Full CLI Capabilities - Web search, file inspection, MCP tool access, latest documentation lookups
• Bounded Continuity - Continue with a PAL conversation ID; clink forwards the newest complete exchanges that fit the selected CLI's history budget

No PAL provider key required: use an installed, authenticated CLI for ongoing conversations through clink. PAL starts without model providers and retains available independent tools. See CLI-only setup and first-request/follow-up examples.

Antigravity: check native agy --version (reference: 1.3.5) and authenticate outside PAL. Use cli_name=agy with default, planner, or codereviewer; follow-ups use PAL's continuation ID. False inherits saved permissions and may allow writes; true requests --mode accept-edits, and path-scoped edits are unsupported. Scratch-mode project access may require operator-managed Non-Workspace Access. Google does not support consumer-plan agy wrappers; see setup, authentication coverage, and upstream limits. Final release acceptance remains pending.

# Codex spawns Codex subagent for isolated code review in fresh context
clink with codex codereviewer to audit auth module for security issues
# Subagent reviews in isolation, returns final report without cluttering your context as codex reads each file and walks the directory structure

# Existing agy login; native permissions still apply
clink with agy codereviewer to review /absolute/path/to/project/module.py
# Continue using the returned PAL continuation ID; no native agy session reuse

# With PAL API providers configured: consensus → bounded CLI handoff
Use consensus with gpt-5 and gemini-pro to decide: dark mode or offline support next
Continue with clink cli_name=gemini allow_edits=true - implement the recommended feature
# Supply the PAL continuation ID; edit permission must be explicit on every call

👉 Learn more about clink · CLI history budgets

---

Why PAL MCP?

Why rely on one AI model when you can orchestrate them all?

A Model Context Protocol server that supercharges tools like Claude Code, Codex CLI, and IDE clients such
as Cursor or the Claude Dev VS Code extension. PAL MCP connects your favorite AI tool
to multiple AI models for enhanced code analysis, problem-solving, and collaborative development.

True AI Collaboration with Conversation Continuity

PAL supports conversation threading so your CLI can discuss ideas with multiple AI models, exchange reasoning, get second opinions, and even run collaborative debates between models to help you reach deeper insights and better solutions.

Your CLI always stays in control but gets perspectives from the best AI for each subtask. Context carries forward seamlessly across tools and models, enabling complex workflows like: code reviews with multiple models → automated planning → implementation → pre-commit validation.

You're in control. Your CLI of choice orchestrates the AI team, but you decide the workflow. Craft powerful prompts that bring in Gemini Pro, GPT 5, Flash, or local offline models exactly when needed.

Reasons to Use PAL MCP

A typical workflow with Claude Code as an example:

1. Multi-Model Orchestration - Claude coordinates with Gemini Pro, O3, GPT-5, and 50+ other models to get the best analysis for each task

2. Context Revival Magic - Even after Claude's context resets, continue conversations seamlessly by having other models "remind" Claude of the discussion

3. Guided Workflows - Enforces systematic investigation phases that prevent rushed analysis and ensure thorough code examination

4. Extended Context Windows - Break Claude's limits by delegating to Gemini (1M tokens) or O3 (200K tokens) for massive codebases

5. True Conversation Continuity - Full context flows across tools and models - Gemini remembers what O3 said 10 steps ago

6. Model-Specific Strengths - Extended thinking with Gemini Pro, blazing speed with Flash, strong reasoning with O3, privacy with local Ollama

7. Professional Code Reviews - Multi-pass analysis with severity levels, actionable feedback, and consensus from multiple AI experts

8. Smart Debugging Assistant - Systematic root cause analysis with hypothesis tracking and confidence levels

9. Automatic Model Selection - Claude intelligently picks the right model for each subtask (or you can specify)

10. Vision Capabilities - Analyze screenshots, diagrams, and visual content with vision-enabled models

11. Local Model Support - Run Llama, Mistral, or other models locally for complete privacy and zero API costs

12. Bypass MCP Token Limits - Automatically works around MCP's 25K limit for large prompts and responses

The Killer Feature: When Claude's context resets, just ask to "continue with O3" - the other model's response magically revives Claude's understanding without re-ingesting documents!

Example: Multi-Model Code Review Workflow

1. Perform a codereview using gemini pro and o3 and use planner to generate a detailed plan, implement the fixes and do a final precommit check by continuing from the previous codereview
2. This triggers a codereview workflow where Claude walks the code, looking for all kinds of issues
3. After multiple passes, collects relevant code and makes note of issues along the way
4. Maintains a confidence level between exploring, low, medium, high and certain to track how confidently it's been able to find and identify issues
5. Generates a detailed list of critical -> low issues
6. Shares the relevant files, findings, etc with Gemini Pro to perform a deep dive for a second codereview
7. Comes back with a response and next does the same with o3, adding to the prompt if a new discovery comes to light
8. When done, Claude takes in all the feedback and combines a single list of all critical -> low issues, including good patterns in your code. The final list includes new findings or revisions in case Claude misunderstood or missed something crucial and one of the other models pointed this out
9. It then uses the planner workflow to break the work down into simpler steps if a major refactor is required
10. Claude then performs the actual work of fixing highlighted issues
11. When done, Claude returns to Gemini Pro for a precommit review

All within a single conversation thread! Gemini Pro in step 11 knows what was recommended by O3 in step 7! Taking that context
and review into consideration to aid with its final pre-commit review.

Think of it as Claude Code for Claude Code. This MCP isn't magic. It's just super-glue.

Remember: Claude stays in full control — but YOU call the shots.
PAL is designed to have Claude engage other models only when needed — and to follow through with meaningful back-and-forth.
You're the one who crafts the powerful prompt that makes Claude bring in Gemini, Flash, O3 — or fly solo.
You're the guide. The prompter. The puppeteer.

You are the AI - Actually Intelligent.

Recommended AI Stack

For Claude Code Users

For best results when using Claude Code:

• Sonnet 4.5 - All agentic work and orchestration
• Gemini 3.0 Pro OR GPT-5.2 / Pro - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis

For Codex Users

For best results when using Codex CLI:

• GPT-5.2 Codex Medium - All agentic work and orchestration
• Gemini 3.0 Pro OR GPT-5.2-Pro - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis

Quick Start (5 minutes)

Prerequisites: Python 3.10+, Git, uv installed

1. Choose a setup path:

• CLI conversations: install and authenticate Codex, Claude Code, Gemini CLI, or Antigravity, then use clink. Leave PAL model-provider keys/endpoints unconfigured for provider-free mode. Follow local CLI setup and the agy-specific support limits when applicable.

• API-backed tools: configure a provider for chat, consensus, codereview, and other model-backed workflows. Choose one or more below; a local endpoint may not need a key.

• OpenRouter - Access multiple models with one API

• Gemini - Google's latest models

• OpenAI - O3, GPT-5 series

• Azure OpenAI - Enterprise deployments of GPT-4o, GPT-4.1, GPT-5 family

• X.AI - Grok models

• DIAL - Vendor-agnostic model access

• Ollama - Local models (free)

2. Install (choose one):

Option A: Clone and Automatic Setup (recommended)

git clone https://github.com/serpro69/pal-mcp-server.git
cd pal-mcp-server

# Handles everything: setup, config, API keys from system environment.
# Auto-configures Claude Desktop, Claude Code, Gemini CLI, Codex CLI, Qwen CLI
# Enable / disable additional settings in .env
./run-server.sh

Option B: Instant Setup with uvx

// Add to ~/.claude/settings.json or .mcp.json
// API-backed example: for provider-free clink, omit GEMINI_API_KEY
{
  "mcpServers": {
    "pal": {
      "command": "bash",
      "args": [
        "-c",
        "for p in $(which uvx 2>/dev/null) $HOME/.local/bin/uvx /opt/homebrew/bin/uvx /usr/local/bin/uvx uvx; do [ -x \"$p\" ] && exec \"$p\" --from git+https://github.com/serpro69/pal-mcp-server.git pal-mcp-server; done; echo 'uvx not found' >&2; exit 1"
      ],
      "env": {
        "PATH": "/usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin:~/.local/bin",
        "GEMINI_API_KEY": "your-key-here",
        "DISABLED_TOOLS": "analyze,refactor,testgen,secaudit,docgen,tracer",
        "DEFAULT_MODEL": "auto"
      }
    }
  }
}

3. Start Using!

For CLI conversations, ask your client to call clink:

{"cli_name": "codex", "prompt": "Remember the codeword ORCHID-42."}

Then follow up with the returned ID:

{"continuation_id": "<continuation_offer.continuation_id>", "prompt": "What codeword did I give you?"}

Use your installed CLI's name on the first request; the follow-up inherits the successful CLI/role. Edits default off on each call. History defaults to 16,384 estimated tokens and 50 stored messages, expires after three hours without a successful recorded exchange, and is lost on restart. Permissions, limits, and failure handling explain busy retries, missing executables, and replies that could not be recorded. CLI failures do not fall back to an API provider.

With API providers configured, you can also use these workflows:

"Use pal to analyze this code for security issues with gemini pro"
"Debug this error with o3 and then get flash to suggest optimizations"
"Plan the migration strategy with pal, get consensus from multiple models"
"clink with cli_name=\"gemini\" role=\"planner\" to draft a phased rollout plan"

👉 Complete Setup Guide with detailed installation, configuration for Gemini / Codex / Qwen, and troubleshooting
👉 Cursor & VS Code Setup for IDE integration instructions
📺 Watch tools in action to see real-world examples

Provider Configuration

PAL determines its mode at startup from successfully configured model providers. Configure provider settings in .env or the launch environment for API-backed tools; custom/local endpoints can work without a key. See .env.example for customization. Restart PAL after changes.

Without registered model providers, PAL exposes the enabled subset of clink, version, listmodels, planner, tracer, docgen, challenge, apilookup, and jules (which needs its own service credentials). listmodels reports setup hints and CLI executable observations with authentication unverified. API-backed tools are unavailable until a provider is configured. PAL does not manage CLI login or guarantee subscription billing; see vendor authentication guidance.

Core Tools

Note: Each tool comes with its own multi-step workflow, parameters, and descriptions that consume valuable context window space even when not in use. To optimize performance, some tools are disabled by default. See Tool Configuration below to enable them.

Collaboration & Planning (Enabled by default)

• clink - Bridge requests to external AI CLIs (Gemini planner, codereviewer, etc.)
• chat - Brainstorm ideas, get second opinions, validate approaches. With capable models (GPT-5.2 Pro, Gemini 3.0 Pro), generates complete code / implementation
• thinkdeep - Extended reasoning, edge case analysis, alternative perspectives
• planner - Break down complex projects into structured, actionable plans
• consensus - Get expert opinions from multiple AI models with stance steering

Code Analysis & Quality

• debug - Systematic investigation and root cause analysis
• precommit - Validate changes before committing, prevent regressions
• codereview - Professional reviews with severity levels and actionable feedback
• analyze (disabled by default - enable) - Understand architecture, patterns, dependencies across entire codebases

Development Tools (Disabled by default - enable)

• refactor - Intelligent code refactoring with decomposition focus
• testgen - Comprehensive test generation with edge cases
• secaudit - Security audits with OWASP Top 10 analysis
• docgen - Generate documentation with complexity analysis

Utilities

• apilookup - Forces current-year API/SDK documentation lookups in a sub-process (saves tokens within the current context window), prevents outdated training data responses
• challenge - Prevent "You're absolutely right!" responses with critical analysis
• tracer (disabled by default - enable) - Static analysis prompts for call-flow mapping

👉 Tool Configuration

Default Configuration

To optimize context window usage, only essential tools are enabled by default:

Enabled by default:

• chat, thinkdeep, planner, consensus - Core collaboration tools
• codereview, precommit, debug - Essential code quality tools
• apilookup - Rapid API/SDK information lookup
• challenge - Critical thinking utility

Disabled by default:

• analyze, refactor, testgen, secaudit, docgen, tracer

Enabling Additional Tools

To enable additional tools, remove them from the DISABLED_TOOLS list:

Option 1: Edit your .env file

# Default configuration (from .env.example)
DISABLED_TOOLS=analyze,refactor,testgen,secaudit,docgen,tracer

# To enable specific tools, remove them from the list
# Example: Enable analyze tool
DISABLED_TOOLS=refactor,testgen,secaudit,docgen,tracer

# To enable ALL tools
DISABLED_TOOLS=

Option 2: Configure in MCP settings

// In ~/.claude/settings.json or .mcp.json
{
  "mcpServers": {
    "pal": {
      "env": {
        // Tool configuration
        "DISABLED_TOOLS": "refactor,testgen,secaudit,docgen,tracer",
        "DEFAULT_MODEL": "pro",
        "DEFAULT_THINKING_MODE_THINKDEEP": "high",

        // API configuration
        "GEMINI_API_KEY": "your-gemini-key",
        "OPENAI_API_KEY": "your-openai-key",
        "OPENROUTER_API_KEY": "your-openrouter-key",

        // Logging and performance
        "LOG_LEVEL": "INFO",
        "CONVERSATION_TIMEOUT_HOURS": "6",
        "MAX_CONVERSATION_TURNS": "50"
      }
    }
  }
}

Option 3: Enable all tools

// Remove or empty the DISABLED_TOOLS to enable everything
{
  "mcpServers": {
    "pal": {
      "env": {
        "DISABLED_TOOLS": ""
      }
    }
  }
}

Note:

• Essential tools (version, listmodels) cannot be disabled
• Enabling a tool does not satisfy its provider requirements; listmodels reports actual startup availability
• After changing tool configuration, restart your Claude session for changes to take effect
• Each tool adds to context window usage, so only enable what you need

📺 Watch Tools In Action

Chat Tool - Collaborative decision making and multi-turn conversations

Picking Redis vs Memcached:

Chat Redis or Memcached_web.webm

Multi-turn conversation with continuation:

Chat With Gemini_web.webm

Consensus Tool - Multi-model debate and decision making

Multi-model consensus debate:

PAL Consensus Debate

PreCommit Tool - Comprehensive change validation

Pre-commit validation workflow:

API Lookup Tool - Current vs outdated API documentation

Without PAL - outdated APIs:

API without PAL

With PAL - current APIs:

API with PAL

Challenge Tool - Critical thinking vs reflexive agreement

Without PAL:

With PAL:

Key Features

AI Orchestration

• Auto model selection - Claude picks the right AI for each task
• Multi-model workflows - Chain different models in single conversations
• Conversation continuity - Context preserved across tools and models
• Context revival - Continue conversations even after context resets

Model Support

• Multiple providers - Gemini, OpenAI, Azure, X.AI, OpenRouter, DIAL, Ollama
• Latest models - GPT-5, Gemini 3.0 Pro, O3, Grok-4, local Llama
• Thinking modes - Control reasoning depth vs cost
• Vision support - Analyze images, diagrams, screenshots

Developer Experience

• Guided workflows - Systematic investigation prevents rushed analysis
• Smart file handling - Auto-expand directories, manage token limits
• Web search integration - Access current documentation and best practices
• Large prompt support - Bypass MCP's 25K token limit

Example Workflows

Multi-model Code Review:

"Perform a codereview using gemini pro and o3, then use planner to create a fix strategy"

→ Claude reviews code systematically → Consults Gemini Pro → Gets O3's perspective → Creates unified action plan

Collaborative Debugging:

"Debug this race condition with max thinking mode, then validate the fix with precommit"

→ Deep investigation → Expert analysis → Solution implementation → Pre-commit validation

Architecture Planning:

"Plan our microservices migration, get consensus from pro and o3 on the approach"

→ Structured planning → Multiple expert opinions → Consensus building → Implementation roadmap

👉 Advanced Usage Guide for complex workflows, model configuration, and power-user features

Quick Links

📖 Documentation

• Docs Overview - High-level map of major guides
• Getting Started - Complete setup guide
• CLI-only conversations - Local setup without PAL provider keys
• Tools Reference - All tools with examples
• Advanced Usage - Power user features
• Configuration - Environment variables, restrictions
• Architecture - Request isolation, async providers and memory ownership
• Logging and transcripts - State paths and opt-in conversation audit resources
• Reliability verification - Tested scope and release gates (linked to tracking issues)
• Adding Providers - Provider-specific setup (OpenAI, Azure, custom gateways)
• Model Ranking Guide - How intelligence scores drive auto-mode suggestions

🔧 Setup & Support

• WSL Setup - Windows users
• Troubleshooting - Common issues
• Contributing - Code standards, PR process

License

Apache 2.0 License - see LICENSE file for details.
Existing project attribution is preserved in NOTICE. Source and wheel
distributions include both files and declare the Apache-2.0 SPDX identifier.

Acknowledgments

Built with the power of Multi-Model AI collaboration 🤝

• Actual Intelligence by real Humans
• MCP (Model Context Protocol)
• Codex CLI
• Claude Code
• Gemini
• OpenAI
• Azure OpenAI

Star History