Skip to content
Back to search

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.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/beehiveinnovations--pal-mcp-server/badge.svg)](/listings/beehiveinnovations--pal-mcp-server)

HTML

<a href="/listings/beehiveinnovations--pal-mcp-server"><img src="/api/listings/beehiveinnovations--pal-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Prerequisites:** Python 3.10+, Git, [uv installed](https://docs.astral.sh/uv/getting-started/installation/)

**1. Get API Keys** (choose one or more): - **[OpenRouter](https://openrouter.ai/)** - Access multiple models with one API - **[Gemini](https://makersuite.google.com/app/apikey)** - Google's latest models - **[OpenAI](https://platform.openai.com/api-keys)** - O3, GPT-5 series - **[Azure OpenAI](https://learn.microsoft.com/azure/ai-services/openai/)** - Enterprise deployments of GPT-4o, GPT-4.1, GPT-5 family - **[X.AI](https://console.x.ai/)** - Grok models - **[DIAL](https://dialx.ai/)** - Vendor-agnostic model access - **[Ollama](https://ollama.ai/)** - Local models (free)

**2. Install** (choose one):

**Option A: Clone and Automatic Setup** (recommended)

git clone https://github.com/BeehiveInnovations/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](https://docs.astral.sh/uv/getting-started/installation/)**

// Add to ~/.claude/settings.json or .mcp.json
// Don't forget to add your API keys under env
{
  "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/BeehiveInnovations/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!**

"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"

πŸ‘‰ **[Complete Setup Guide](docs/getting-started.md)** with detailed installation, configuration for Gemini / Codex / Qwen, and troubleshooting πŸ‘‰ **[Cursor & VS Code Setup](docs/getting-started.md#ide-clients)** for IDE integration instructions πŸ“Ί **[Watch tools in action](#-watch-tools-in-action)** to see real-world examples

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 450 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # PAL MCP: Many Workflows. One Context.
  2. <div align="center">
  3. <em>Your AI's PAL – a Provider Abstraction Layer</em><br />
  4. <sub><a href="docs/name-change.md">Formerly known as Zen MCP</a></sub>
  5. [PAL in action](https://github.com/user-attachments/assets/0d26061e-5f21-4ab1-b7d0-f883ddc2c3da)
  6. πŸ‘‰ **[Watch more examples](#-watch-tools-in-action)**
  7. ### Your CLI + Multiple Models = Your AI Dev Team
  8. **Use the πŸ€– CLI you love:**
  9. [Claude Code](https://www.anthropic.com/claude-code) Β· [Gemini CLI](https://github.com/google-gemini/gemini-cli) Β· [Codex CLI](https://github.com/openai/codex) Β· [Qwen Code CLI](https://qwenlm.github.io/qwen-code-docs/) Β· [Cursor](https://cursor.com) Β· _and more_
  10. **With multiple models within a single prompt:**
  11. Gemini Β· OpenAI Β· Anthropic Β· Grok Β· Azure Β· Ollama Β· OpenRouter Β· DIAL Β· On-Device Model
  12. </div>
  13. ---
  14. ## πŸ†• Now with CLI-to-CLI Bridge
  15. The new **[`clink`](docs/tools/clink.md)** (CLI + Link) tool connects external AI CLIs directly into your workflow:
  16. - **Connect external CLIs** like [Gemini CLI](https://github.com/google-gemini/gemini-cli), [Codex CLI](https://github.com/openai/codex), and [Claude Code](https://www.anthropic.com/claude-code) directly into your workflow
  17. - **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.
  18. - **Context Isolation** - Run separate investigations without polluting your primary workspace
  19. - **Role Specialization** - Spawn `planner`, `codereviewer`, or custom role agents with specialized system prompts
  20. - **Full CLI Capabilities** - Web search, file inspection, MCP tool access, latest documentation lookups
  21. - **Seamless Continuity** - Sub-CLIs participate as first-class members with full conversation context between tools
  22. ```bash
  23. # Codex spawns Codex subagent for isolated code review in fresh context
  24. clink with codex codereviewer to audit auth module for security issues
  25. # Subagent reviews in isolation, returns final report without cluttering your context as codex reads each file and walks the directory structure
  26. # Consensus from different AI models β†’ Implementation handoff with full context preservation between tools
  27. Use consensus with gpt-5 and gemini-pro to decide: dark mode or offline support next
  28. Continue with clink gemini - implement the recommended feature
  29. # Gemini receives full debate context and starts coding immediately
  30. ```
  31. πŸ‘‰ **[Learn more about clink](docs/tools/clink.md)**
  32. ---
  33. ## Why PAL MCP?
  34. **Why rely on one AI model when you can orchestrate them all?**
  35. A Model Context Protocol server that supercharges tools like [Claude Code](https://www.anthropic.com/claude-code), [Codex CLI](https://developers.openai.com/codex/cli), and IDE clients such
  36. as [Cursor](https://cursor.com) or the [Claude Dev VS Code extension](https://marketplace.visualstudio.com/items?itemName=Anthropic.claude-vscode). **PAL MCP connects your favorite AI tool
  37. to multiple AI models** for enhanced code analysis, problem-solving, and collaborative development.
  38. ### True AI Collaboration with Conversation Continuity
  39. 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.
  40. 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 β†’ automated planning β†’ implementation β†’ pre-commit validation.
  41. > **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.
  42. <details>
  43. <summary><b>Reasons to Use PAL MCP</b></summary>
  44. A typical workflow with Claude Code as an example:
  45. 1. **Multi-Model Orchestration** - Claude coordinates with Gemini Pro, O3, GPT-5, and 50+ other models to get the best analysis for each task
  46. 2. **Context Revival Magic** - Even after Claude's context resets, continue conversations seamlessly by having other models "remind" Claude of the discussion
  47. 3. **Guided Workflows** - Enforces systematic investigation phases that prevent rushed analysis and ensure thorough code examination
  48. 4. **Extended Context Windows** - Break Claude's limits by delegating to Gemini (1M tokens) or O3 (200K tokens) for massive codebases
  49. 5. **True Conversation Continuity** - Full context flows across tools and models - Gemini remembers what O3 said 10 steps ago
  50. 6. **Model-Specific Strengths** - Extended thinking with Gemini Pro, blazing speed with Flash, strong reasoning with O3, privacy with local Ollama
  51. 7. **Professional Code Reviews** - Multi-pass analysis with severity levels, actionable feedback, and consensus from multiple AI experts
  52. 8. **Smart Debugging Assistant** - Systematic root cause analysis with hypothesis tracking and confidence levels
  53. 9. **Automatic Model Selection** - Claude intelligently picks the right model for each subtask (or you can specify)
  54. 10. **Vision Capabilities** - Analyze screenshots, diagrams, and visual content with vision-enabled models
  55. 11. **Local Model Support** - Run Llama, Mistral, or other models locally for complete privacy and zero API costs
  56. 12. **Bypass MCP Token Limits** - Automatically works around MCP's 25K limit for large prompts and responses
  57. **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!
  58. #### Example: Multi-Model Code Review Workflow
  59. 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`
  60. 2. This triggers a [`codereview`](docs/tools/codereview.md) workflow where Claude walks the code, looking for all kinds of issues
  61. 3. After multiple passes, collects relevant code and makes note of issues along the way
  62. 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
  63. 5. Generates a detailed list of critical -> low issues
  64. 6. Shares the relevant files, findings, etc with **Gemini Pro** to perform a deep dive for a second [`codereview`](docs/tools/codereview.md)
  65. 7. Comes back with a response and next does the same with o3, adding to the prompt if a new discovery comes to light
  66. 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
  67. 9. It then uses the [`planner`](docs/tools/planner.md) workflow to break the work down into simpler steps if a major refactor is required
  68. 10. Claude then performs the actual work of fixing highlighted issues
  69. 11. When done, Claude returns to Gemini Pro for a [`precommit`](docs/tools/precommit.md) review
  70. All within a single conversation thread! Gemini Pro in step 11 _knows_ what was recommended by O3 in step 7! Taking that context
  71. and review into consideration to aid with its final pre-commit review.
  72. **Think of it as Claude Code _for_ Claude Code.** This MCP isn't magic. It's just **super-glue**.
  73. > **Remember:** Claude stays in full control β€” but **YOU** call the shots.
  74. > PAL is designed to have Claude engage other models only when needed β€” and to follow through with meaningful back-and-forth.
  75. > **You're** the one who crafts the powerful prompt that makes Claude bring in Gemini, Flash, O3 β€” or fly solo.
  76. > You're the guide. The prompter. The puppeteer.
  77. > #### You are the AI - **Actually Intelligent**.
  78. </details>
  79. #### Recommended AI Stack
  80. <details>
  81. <summary>For Claude Code Users</summary>
  82. For best results when using [Claude Code](https://claude.ai/code):
  83. - **Sonnet 4.5** - All agentic work and orchestration
  84. - **Gemini 3.0 Pro** OR **GPT-5.2 / Pro** - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis
  85. </details>
  86. <details>
  87. <summary>For Codex Users</summary>
  88. For best results when using [Codex CLI](https://developers.openai.com/codex/cli):
  89. - **GPT-5.2 Codex Medium** - All agentic work and orchestration
  90. - **Gemini 3.0 Pro** OR **GPT-5.2-Pro** - Deep thinking, additional code reviews, debugging and validations, pre-commit analysis
  91. </details>
  92. ## Quick Start (5 minutes)
  93. **Prerequisites:** Python 3.10+, Git, [uv installed](https://docs.astral.sh/uv/getting-started/installation/)
  94. **1. Get API Keys** (choose one or more):
  95. - **[OpenRouter](https://openrouter.ai/)** - Access multiple models with one API
  96. - **[Gemini](https://makersuite.google.com/app/apikey)** - Google's latest models
  97. - **[OpenAI](https://platform.openai.com/api-keys)** - O3, GPT-5 series
  98. - **[Azure OpenAI](https://learn.microsoft.com/azure/ai-services/openai/)** - Enterprise deployments of GPT-4o, GPT-4.1, GPT-5 family
  99. - **[X.AI](https://console.x.ai/)** - Grok models
  100. - **[DIAL](https://dialx.ai/)** - Vendor-agnostic model access
  101. - **[Ollama](https://ollama.ai/)** - Local models (free)
  102. **2. Install** (choose one):
  103. **Option A: Clone and Automatic Setup** (recommended)
  104. ```bash
  105. git clone https://github.com/BeehiveInnovations/pal-mcp-server.git
  106. cd pal-mcp-server
  107. # Handles everything: setup, config, API keys from system environment.
  108. # Auto-configures Claude Desktop, Claude Code, Gemini CLI, Codex CLI, Qwen CLI
  109. # Enable / disable additional settings in .env
  110. ./run-server.sh
  111. ```
  112. **Option B: Instant Setup with [uvx](https://docs.astral.sh/uv/getting-started/installation/)**
  113. ```json
  114. // Add to ~/.claude/settings.json or .mcp.json
  115. // Don't forget to add your API keys under env
  116. {
  117. "mcpServers": {
  118. "pal": {
  119. "command": "bash",
  120. "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/BeehiveInnovations/pal-mcp-server.git pal-mcp-server; done; echo 'uvx not found' >&2; exit 1"],
  121. "env": {
  122. "PATH": "/usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin:~/.local/bin",
  123. "GEMINI_API_KEY": "your-key-here",
  124. "DISABLED_TOOLS": "analyze,refactor,testgen,secaudit,docgen,tracer",
  125. "DEFAULT_MODEL": "auto"
  126. }
  127. }
  128. }
  129. }
  130. ```
  131. **3. Start Using!**
  132. ```
  133. "Use pal to analyze this code for security issues with gemini pro"
  134. "Debug this error with o3 and then get flash to suggest optimizations"
  135. "Plan the migration strategy with pal, get consensus from multiple models"
  136. "clink with cli_name=\"gemini\" role=\"planner\" to draft a phased rollout plan"
  137. ```
  138. πŸ‘‰ **[Complete Setup Guide](docs/getting-started.md)** with detailed installation, configuration for Gemini / Codex / Qwen, and troubleshooting
  139. πŸ‘‰ **[Cursor & VS Code Setup](docs/getting-started.md#ide-clients)** for IDE integration instructions
  140. πŸ“Ί **[Watch tools in action](#-watch-tools-in-action)** to see real-world examples
  141. ## Provider Configuration
  142. PAL activates any provider that has credentials in your `.env`. See `.env.example` for deeper customization.
  143. ## Core Tools
  144. > **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](#tool-configuration) below to enable them.
  145. **Collaboration & Planning** *(Enabled by default)*
  146. - **[`clink`](docs/tools/clink.md)** - Bridge requests to external AI CLIs (Gemini planner, codereviewer, etc.)
  147. - **[`chat`](docs/tools/chat.md)** - Brainstorm ideas, get second opinions, validate approaches. With capable models (GPT-5.2 Pro, Gemini 3.0 Pro), generates complete code / implementation
  148. - **[`thinkdeep`](docs/tools/thinkdeep.md)** - Extended reasoning, edge case analysis, alternative perspectives
  149. - **[`planner`](docs/tools/planner.md)** - Break down complex projects into structured, actionable plans
  150. - **[`consensus`](docs/tools/consensus.md)** - Get expert opinions from multiple AI models with stance steering
  151. **Code Analysis & Quality**
  152. - **[`debug`](docs/tools/debug.md)** - Systematic investigation and root cause analysis
  153. - **[`precommit`](docs/tools/precommit.md)** - Validate changes before committing, prevent regressions
  154. - **[`codereview`](docs/tools/codereview.md)** - Professional reviews with severity levels and actionable feedback
  155. - **[`analyze`](docs/tools/analyze.md)** *(disabled by default - [enable](#tool-configuration))* - Understand architecture, patterns, dependencies across entire codebases
  156. **Development Tools** *(Disabled by default - [enable](#tool-configuration))*
  157. - **[`refactor`](docs/tools/refactor.md)** - Intelligent code refactoring with decomposition focus
  158. - **[`testgen`](docs/tools/testgen.md)** - Comprehensive test generation with edge cases
  159. - **[`secaudit`](docs/tools/secaudit.md)** - Security audits with OWASP Top 10 analysis
  160. - **[`docgen`](docs/tools/docgen.md)** - Generate documentation with complexity analysis
  161. **Utilities**
  162. - **[`apilookup`](docs/tools/apilookup.md)** - Forces current-year API/SDK documentation lookups in a sub-process (saves tokens within the current context window), prevents outdated training data responses
  163. - **[`challenge`](docs/tools/challenge.md)** - Prevent "You're absolutely right!" responses with critical analysis
  164. - **[`tracer`](docs/tools/tracer.md)** *(disabled by default - [enable](#tool-configuration))* - Static analysis prompts for call-flow mapping
  165. <details>
  166. <summary><b id="tool-configuration">πŸ‘‰ Tool Configuration</b></summary>
  167. ### Default Configuration
  168. To optimize context window usage, only essential tools are enabled by default:
  169. **Enabled by default:**
  170. - `chat`, `thinkdeep`, `planner`, `consensus` - Core collaboration tools
  171. - `codereview`, `precommit`, `debug` - Essential code quality tools
  172. - `apilookup` - Rapid API/SDK information lookup
  173. - `challenge` - Critical thinking utility
  174. **Disabled by default:**
  175. - `analyze`, `refactor`, `testgen`, `secaudit`, `docgen`, `tracer`
  176. ### Enabling Additional Tools
  177. To enable additional tools, remove them from the `DISABLED_TOOLS` list:
  178. **Option 1: Edit your .env file**
  179. ```bash
  180. # Default configuration (from .env.example)
  181. DISABLED_TOOLS=analyze,refactor,testgen,secaudit,docgen,tracer
  182. # To enable specific tools, remove them from the list
  183. # Example: Enable analyze tool
  184. DISABLED_TOOLS=refactor,testgen,secaudit,docgen,tracer
  185. # To enable ALL tools
  186. DISABLED_TOOLS=
  187. ```
  188. **Option 2: Configure in MCP settings**
  189. ```json
  190. // In ~/.claude/settings.json or .mcp.json
  191. {
  192. "mcpServers": {
  193. "pal": {
  194. "env": {
  195. // Tool configuration
  196. "DISABLED_TOOLS": "refactor,testgen,secaudit,docgen,tracer",
  197. "DEFAULT_MODEL": "pro",
  198. "DEFAULT_THINKING_MODE_THINKDEEP": "high",
  199. // API configuration
  200. "GEMINI_API_KEY": "your-gemini-key",
  201. "OPENAI_API_KEY": "your-openai-key",
  202. "OPENROUTER_API_KEY": "your-openrouter-key",
  203. // Logging and performance
  204. "LOG_LEVEL": "INFO",
  205. "CONVERSATION_TIMEOUT_HOURS": "6",
  206. "MAX_CONVERSATION_TURNS": "50"
  207. }
  208. }
  209. }
  210. }
  211. ```
  212. **Option 3: Enable all tools**
  213. ```json
  214. // Remove or empty the DISABLED_TOOLS to enable everything
  215. {
  216. "mcpServers": {
  217. "pal": {
  218. "env": {
  219. "DISABLED_TOOLS": ""
  220. }
  221. }
  222. }
  223. }
  224. ```
  225. **Note:**
  226. - Essential tools (`version`, `listmodels`) cannot be disabled
  227. - After changing tool configuration, restart your Claude session for changes to take effect
  228. - Each tool adds to context window usage, so only enable what you need
  229. </details>
  230. ## πŸ“Ί Watch Tools In Action
  231. <details>
  232. <summary><b>Chat Tool</b> - Collaborative decision making and multi-turn conversations</summary>
  233. **Picking Redis vs Memcached:**
  234. [Chat Redis or Memcached_web.webm](https://github.com/user-attachments/assets/41076cfe-dd49-4dfc-82f5-d7461b34705d)
  235. **Multi-turn conversation with continuation:**
  236. [Chat With Gemini_web.webm](https://github.com/user-attachments/assets/37bd57ca-e8a6-42f7-b5fb-11de271e95db)
  237. </details>
  238. <details>
  239. <summary><b>Consensus Tool</b> - Multi-model debate and decision making</summary>
  240. **Multi-model consensus debate:**
  241. [PAL Consensus Debate](https://github.com/user-attachments/assets/76a23dd5-887a-4382-9cf0-642f5cf6219e)
  242. </details>
  243. <details>
  244. <summary><b>PreCommit Tool</b> - Comprehensive change validation</summary>
  245. **Pre-commit validation workflow:**
  246. <div align="center">
  247. <img src="https://github.com/user-attachments/assets/584adfa6-d252-49b4-b5b0-0cd6e97fb2c6" width="950">
  248. </div>
  249. </details>
  250. <details>
  251. <summary><b>API Lookup Tool</b> - Current vs outdated API documentation</summary>
  252. **Without PAL - outdated APIs:**
  253. [API without PAL](https://github.com/user-attachments/assets/01a79dc9-ad16-4264-9ce1-76a56c3580ee)
  254. **With PAL - current APIs:**
  255. [API with PAL](https://github.com/user-attachments/assets/5c847326-4b66-41f7-8f30-f380453dce22)
  256. </details>
  257. <details>
  258. <summary><b>Challenge Tool</b> - Critical thinking vs reflexive agreement</summary>
  259. **Without PAL:**
  260. ![without_pal@2x](https://github.com/user-attachments/assets/64f3c9fb-7ca9-4876-b687-25e847edfd87)
  261. **With PAL:**
  262. ![with_pal@2x](https://github.com/user-attachments/assets/9d72f444-ba53-4ab1-83e5-250062c6ee70)
  263. </details>
  264. ## Key Features
  265. **AI Orchestration**
  266. - **Auto model selection** - Claude picks the right AI for each task
  267. - **Multi-model workflows** - Chain different models in single conversations
  268. - **Conversation continuity** - Context preserved across tools and models
  269. - **[Context revival](docs/context-revival.md)** - Continue conversations even after context resets
  270. **Model Support**
  271. - **Multiple providers** - Gemini, OpenAI, Azure, X.AI, OpenRouter, DIAL, Ollama
  272. - **Latest models** - GPT-5, Gemini 3.0 Pro, O3, Grok-4, local Llama
  273. - **[Thinking modes](docs/advanced-usage.md#thinking-modes)** - Control reasoning depth vs cost
  274. - **Vision support** - Analyze images, diagrams, screenshots
  275. **Developer Experience**
  276. - **Guided workflows** - Systematic investigation prevents rushed analysis
  277. - **Smart file handling** - Auto-expand directories, manage token limits
  278. - **Web search integration** - Access current documentation and best practices
  279. - **[Large prompt support](docs/advanced-usage.md#working-with-large-prompts)** - Bypass MCP's 25K token limit
  280. ## Example Workflows
  281. **Multi-model Code Review:**
  282. ```
  283. "Perform a codereview using gemini pro and o3, then use planner to create a fix strategy"
  284. ```
  285. β†’ Claude reviews code systematically β†’ Consults Gemini Pro β†’ Gets O3's perspective β†’ Creates unified action plan
  286. **Collaborative Debugging:**
  287. ```
  288. "Debug this race condition with max thinking mode, then validate the fix with precommit"
  289. ```
  290. β†’ Deep investigation β†’ Expert analysis β†’ Solution implementation β†’ Pre-commit validation
  291. **Architecture Planning:**
  292. ```
  293. "Plan our microservices migration, get consensus from pro and o3 on the approach"
  294. ```
  295. β†’ Structured planning β†’ Multiple expert opinions β†’ Consensus building β†’ Implementation roadmap
  296. πŸ‘‰ **[Advanced Usage Guide](docs/advanced-usage.md)** for complex workflows, model configuration, and power-user features
  297. ## Quick Links
  298. **πŸ“– Documentation**
  299. - [Docs Overview](docs/index.md) - High-level map of major guides
  300. - [Getting Started](docs/getting-started.md) - Complete setup guide
  301. - [Tools Reference](docs/tools/) - All tools with examples
  302. - [Advanced Usage](docs/advanced-usage.md) - Power user features
  303. - [Configuration](docs/configuration.md) - Environment variables, restrictions
  304. - [Adding Providers](docs/adding_providers.md) - Provider-specific setup (OpenAI, Azure, custom gateways)
  305. - [Model Ranking Guide](docs/model_ranking.md) - How intelligence scores drive auto-mode suggestions
  306. **πŸ”§ Setup & Support**
  307. - [WSL Setup](docs/wsl-setup.md) - Windows users
  308. - [Troubleshooting](docs/troubleshooting.md) - Common issues
  309. - [Contributing](docs/contributions.md) - Code standards, PR process
  310. ## License
  311. Apache 2.0 License - see [LICENSE](LICENSE) file for details.
  312. ## Acknowledgments
  313. Built with the power of **Multi-Model AI** collaboration 🀝
  314. - **A**ctual **I**ntelligence by real Humans
  315. - [MCP (Model Context Protocol)](https://modelcontextprotocol.com)
  316. - [Codex CLI](https://developers.openai.com/codex/cli)
  317. - [Claude Code](https://claude.ai/code)
  318. - [Gemini](https://ai.google.dev/)
  319. - [OpenAI](https://openai.com/)
  320. - [Azure OpenAI](https://learn.microsoft.com/azure/ai-services/openai/)
  321. ### Star History
  322. [![Star History Chart](https://api.star-history.com/svg?repos=BeehiveInnovations/pal-mcp-server&type=Date)](https://www.star-history.com/#BeehiveInnovations/pal-mcp-server&Date)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.