torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: rebranding, see [docs/name-change.md](docs/name-change.md) for details

Browse Source
This commit is contained in:
Fahad
2025-12-04 18:11:55 +04:00
parent bcfaccecd4
commit b2dc84992d
122 changed files with 1423 additions and 1056 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/tools/apilookup.md
View File

@@ -5,7 +5,7 @@ Most importantly, it does this within in a sub-process / sub-agent, saving you p
## Why Use This Tool?
### Without Zen (Using Standard AI)
### Without PAL (Using Standard AI)
```
User: "How do I add glass look to a button in Swift?"
@@ -17,11 +17,11 @@ Result: You get outdated APIs for iOS 18, not the iOS 26 effect you're after
<div align="center">
[API without Zen](https://github.com/user-attachments/assets/01a79dc9-ad16-4264-9ce1-76a56c3580ee)
[API without PAL](https://github.com/user-attachments/assets/01a79dc9-ad16-4264-9ce1-76a56c3580ee)
</div>
### With Zen (Using apilookup)
### With PAL (Using apilookup)
```
User: "use apilookup how do I add glass look to a button in swift?"
@@ -36,7 +36,7 @@ Result: You get the correct, current APIs that work with today's iOS version
<div align="center">
[API with Zen](https://github.com/user-attachments/assets/5c847326-4b66-41f7-8f30-f380453dce22)
[API with PAL](https://github.com/user-attachments/assets/5c847326-4b66-41f7-8f30-f380453dce22)
</div>
@@ -110,7 +110,7 @@ The AI then performs the actual web searches and synthesizes the results into ac
## Codex CLI Configuration Reminder
If you use Zen through the Codex CLI, the assistant needs Codex's native web-search tool to fetch current documentation. After adding the Zen MCP entry to `~/.codex/config.toml`, confirm the file also contains:
If you use PAL through the Codex CLI, the assistant needs Codex's native web-search tool to fetch current documentation. After adding the PAL MCP entry to `~/.codex/config.toml`, confirm the file also contains:
```toml
[tools]

10
docs/tools/challenge.md
View File

@@ -20,11 +20,11 @@ bigger picture or ignoring architectural constraints.
`challenge` fixes this. Claude can even _detect_ when you're challenging something and automatically invokes this tool
to ensure thoughtful analysis instead of reflexive agreement.
**Without Zen:**
![without_zen@2x](https://github.com/user-attachments/assets/64f3c9fb-7ca9-4876-b687-25e847edfd87)
**Without PAL:**
![without_pal@2x](https://github.com/user-attachments/assets/64f3c9fb-7ca9-4876-b687-25e847edfd87)
**With Zen:**
![with_zen@2x](https://github.com/user-attachments/assets/9d72f444-ba53-4ab1-83e5-250062c6ee70)
**With PAL:**
![with_pal@2x](https://github.com/user-attachments/assets/9d72f444-ba53-4ab1-83e5-250062c6ee70)
## Why Use Challenge?
@@ -32,4 +32,4 @@ AI assistants sometimes tend to agree too readily. The challenge tool helps you:
- Get genuine critical evaluation of your ideas
- Challenge assumptions constructively
- Receive honest feedback on proposals
- Validate approaches with thoughtful analysis
- Validate approaches with thoughtful analysis

10
docs/tools/chat.md
View File

@@ -26,7 +26,7 @@ word verdict in the end.
* We ask Claude code to pick one of two frameworks, then `chat` with `gemini` to make a final decision
* Gemini responds, confirming choice. We use `continuation` to ask another question using the same conversation thread
* Gemini responds with explanation. We use continuation again, using `/zen:continue (MCP)` command the second time
* Gemini responds with explanation. We use continuation again, using `/pal:continue (MCP)` command the second time
<div style="center">
@@ -39,7 +39,7 @@ word verdict in the end.
- **Collaborative thinking partner** for your analysis and planning
- **Get second opinions** on your designs and approaches
- **Brainstorm solutions** and explore alternatives together
- **Structured code generation**: When using GPT-5.1 or Gemini 3.0 / 2.5 Pro, get complete, production-ready implementations saved to `zen_generated.code` for your CLI to review and apply
- **Structured code generation**: When using GPT-5.1 or Gemini 3.0 / 2.5 Pro, get complete, production-ready implementations saved to `pal_generated.code` for your CLI to review and apply
- **Validate your checklists** and implementation plans
- **General development questions** and explanations
- **Technology comparisons** and best practices
@@ -67,8 +67,8 @@ When using advanced reasoning models like **GPT-5 Pro** or **Gemini 3.0 Pro**, t
### How It Works
1. You ask your AI agent to implement a complex new feature using `chat` with a higher-reasoning model such as **GPT-5 Pro** or **Gemini 3.0 Pro**
2. The model generates structured implementation and shares the complete implementation with Zen
3. Zen saves the code to `zen_generated.code` and asks AI agent to implement the plan
2. The model generates structured implementation and shares the complete implementation with PAL
3. PAL saves the code to `pal_generated.code` and asks AI agent to implement the plan
4. AI agent continues from the previous context, reads the file, applies the implementation
### When Code Generation Activates
@@ -101,7 +101,7 @@ See the [Configuration Guide](../configuration.md#code-generation-capability) fo
**Basic Development Chat:**
```
"Chat with zen about the best approach for user authentication in my React app"
"Chat with pal about the best approach for user authentication in my React app"
```
**Technology Comparison:**

16
docs/tools/clink.md
View File

@@ -53,7 +53,7 @@ Gemini receives the full conversation context from `consensus` including the con
- **Role-based prompts**: Pre-configured roles for planning, code review, or general questions
- **Full CLI capabilities**: Gemini can use its own web search, file tools, and latest features
- **Token efficiency**: File references (not full content) to conserve tokens
- **Cross-tool collaboration**: Combine with other Zen tools like `planner` → `clink` → `codereview`
- **Cross-tool collaboration**: Combine with other PAL tools like `planner` → `clink` → `codereview`
- **Free tier available**: Gemini offers 1,000 requests/day free with a personal Google account - great for cost savings across tools
## Available Roles
@@ -120,18 +120,18 @@ then codereview to verify the implementation"
## How Clink Works
1. **Your request** - You ask your current CLI to use `clink` with a specific CLI and role
2. **Background execution** - Zen spawns the configured CLI (e.g., `gemini --output-format json`)
2. **Background execution** - PAL spawns the configured CLI (e.g., `gemini --output-format json`)
3. **Context forwarding** - Your prompt, files (as references), and conversation history are sent as part of the prompt
4. **CLI processing** - Gemini (or other CLI) uses its own tools: web search, file access, thinking modes
5. **Seamless return** - Results flow back into your conversation with full context preserved
6. **Continuation support** - Future tools and models can reference Gemini's findings via [continuation support](../context-revival.md) within Zen.
6. **Continuation support** - Future tools and models can reference Gemini's findings via [continuation support](../context-revival.md) within PAL.
## Best Practices
- **Pre-authenticate CLIs**: Install and configure Gemini CLI first (`npm install -g @google/gemini-cli`)
- **Choose appropriate roles**: Use `planner` for strategy, `codereviewer` for code, `default` for general questions
- **Leverage CLI strengths**: Gemini's 1M context for large codebases, web search for current docs
- **Combine with Zen tools**: Chain `clink` with `planner`, `codereview`, `debug` for powerful workflows
- **Combine with PAL tools**: Chain `clink` with `planner`, `codereview`, `debug` for powerful workflows
- **File efficiency**: Pass file paths, let the CLI decide what to read (saves tokens)
## Configuration
@@ -153,9 +153,9 @@ Each preset points to role-specific prompts in `systemprompts/clink/`. Duplicate
## When to Use Clink vs Other Tools
- **Use `clink`** for: Leveraging external CLI capabilities (Gemini's web search, 1M context), specialized CLI features, cross-CLI collaboration
- **Use `chat`** for: Direct model-to-model conversations within Zen
- **Use `planner`** for: Zen's native planning workflows with step validation
- **Use `codereview`** for: Zen's structured code review with severity levels
- **Use `chat`** for: Direct model-to-model conversations within PAL
- **Use `planner`** for: PAL's native planning workflows with step validation
- **Use `codereview`** for: PAL's structured code review with severity levels
## Setup Requirements
@@ -168,7 +168,7 @@ Ensure the relevant CLI is installed and configured:
## Related Guides
- [Chat Tool](chat.md) - Direct model conversations
- [Planner Tool](planner.md) - Zen's native planning workflows
- [Planner Tool](planner.md) - PAL's native planning workflows
- [CodeReview Tool](codereview.md) - Structured code reviews
- [Context Revival](../context-revival.md) - Continuing conversations across tools
- [Advanced Usage](../advanced-usage.md) - Complex multi-tool workflows

4
docs/tools/consensus.md
View File

@@ -27,7 +27,7 @@ The following is a hypothetical example designed to demonstrate how one consensu
<div style="center">
[Zen Consensus Debate](https://github.com/user-attachments/assets/76a23dd5-887a-4382-9cf0-642f5cf6219e)
[PAL Consensus Debate](https://github.com/user-attachments/assets/76a23dd5-887a-4382-9cf0-642f5cf6219e)
</div>
@@ -35,7 +35,7 @@ The following is a hypothetical example designed to demonstrate how one consensu
**For/Against Analysis:**
```
Use zen consensus with flash taking a supportive stance and pro being critical to evaluate whether
Use pal consensus with flash taking a supportive stance and pro being critical to evaluate whether
we should migrate from REST to GraphQL for our API
```

2
docs/tools/docgen.md
View File

@@ -32,7 +32,7 @@ Documentation generation excels with analytical models like Gemini Pro or O3, wh
**Basic Usage:**
```
"Use zen to generate documentation for the UserManager class"
"Use pal to generate documentation for the UserManager class"
"Document the authentication module with complexity analysis using gemini pro"
"Add comprehensive documentation to all methods in src/payment_processor.py"
```

2
docs/tools/listmodels.md
View File

@@ -7,7 +7,7 @@ The `listmodels` tool shows which providers are configured, available models, th
## Usage
```
"Use zen to list available models"
"Use pal to list available models"
```
## Key Features

14
docs/tools/planner.md
View File

@@ -19,7 +19,7 @@ The planner tool enables step-by-step thinking with incremental plan building:
#### Pro Tip
Claude supports `sub-tasks` where it will spawn and run separate background tasks. You can ask Claude to
run Zen's planner with two separate ideas. Then when it's done, use Zen's `consensus` tool to pass the entire
run PAL's planner with two separate ideas. Then when it's done, use PAL's `consensus` tool to pass the entire
plan and get expert perspective from two powerful AI models on which one to work on first! Like performing **AB** testing
in one-go without the wait!
@@ -31,7 +31,7 @@ I implement first?
```
```
Use zen's planner and show me how to add real-time notifications to our mobile app
Use pal's planner and show me how to add real-time notifications to our mobile app
```
```
@@ -55,11 +55,11 @@ Using planner, plan the architecture for a new real-time chat system with 100k c
```
```
Create a plan using zen for migrating our React app from JavaScript to TypeScript
Create a plan using pal for migrating our React app from JavaScript to TypeScript
```
```
Develop a plan using zen for implementing CI/CD pipelines across our development teams
Develop a plan using pal for implementing CI/CD pipelines across our development teams
```
## Best Practices
@@ -73,11 +73,11 @@ Develop a plan using zen for implementing CI/CD pipelines across our development
## Continue With a New Plan
Like all other tools in Zen, you can `continue` with a new plan using the output from a previous plan by simply saying
Like all other tools in PAL, you can `continue` with a new plan using the output from a previous plan by simply saying
```
Continue with zen's consensus tool and find out what o3:for and flash:against think of the plan
Continue with pal's consensus tool and find out what o3:for and flash:against think of the plan
```
You can mix and match and take one output and feed it into another, continuing from where you left off using a different
tool / model combination.
tool / model combination.

10
docs/tools/precommit.md
View File

@@ -32,7 +32,7 @@ After Claude completes the investigation (unless precommit_type is **internal**)
- Default validation type is **external** (uses expert model for additional review)
- To skip expert validation, explicitly request "don't use any other model" or set precommit_type to "internal"
- **CRITICAL**: Minimum 3 steps are enforced - tool will prevent setting `next_step_required=false` before final step
- **MANDATORY**: Changeset file (zen_precommit.changeset) must be created for external validation
- **MANDATORY**: Changeset file (pal_precommit.changeset) must be created for external validation
## Model Recommendation
@@ -62,7 +62,7 @@ passing, it went ahead with an initial review with O3; came back clean - all goo
Then it shared the changes and relevant code with Gemini 3.0 Pro - the following is the outcome:
```
⏺ zen:precommit (MCP)(step: "FINAL VALIDATION COMPLETE. All changes have been thoroughly analyzed and are ready for
⏺ pal:precommit (MCP)(step: "FINAL VALIDATION COMPLETE. All changes have been thoroughly analyzed and are ready for
commit. The modifications successfully fix 4 GitHub CI test failures with high-quality, defensive
implementations that maintain architectural integrity and coding standards. No issues or regressions
detected.", step_number: 4, total_steps: 4, next_step_required: false, findings: "COMMIT
@@ -101,12 +101,12 @@ Then it shared the changes and relevant code with Gemini 3.0 Pro - the following
- Fix Required: Apply the same defensive pattern to the missed location
```
A subtle but critical issue spotted by Gemini that both Claude + O3 missed. This is the power of running these workflows with Zen.
A subtle but critical issue spotted by Gemini that both Claude + O3 missed. This is the power of running these workflows with PAL.
## Example Prompts
```
Use zen and perform a thorough precommit ensuring there aren't any new regressions or bugs introduced
Use pal and perform a thorough precommit ensuring there aren't any new regressions or bugs introduced
```
## Key Features
@@ -155,7 +155,7 @@ Use zen and perform a thorough precommit ensuring there aren't any new regressio
**Basic Pre-commit Validation:**
```
"Use zen precommit to validate my changes before committing"
"Use pal precommit to validate my changes before committing"
```
**Security-Focused Validation:**

4
docs/tools/refactor.md
View File

@@ -35,13 +35,13 @@ The refactor tool excels with models that have large context windows like Gemini
```
"Use gemini pro to decompose my_crazy_big_class.m into smaller extensions"
"Using zen's refactor decompose the all_in_one_sync_code.swift into maintainable extensions"
"Using pal's refactor decompose the all_in_one_sync_code.swift into maintainable extensions"
```
💡**Example of a powerful prompt** to get the best out of both Claude + Flash's 1M Context:
```
"First, think about how the authentication module works, find related classes and find
any code smells, then using zen's refactor ask flash to confirm your findings but ask
any code smells, then using pal's refactor ask flash to confirm your findings but ask
it to find additional code smells and any other quick-wins and then fix these issues"
```

2
docs/tools/testgen.md
View File

@@ -35,7 +35,7 @@ Test generation excels with extended reasoning models like Gemini Pro or O3, whi
**Basic Usage:**
```
"Use zen to generate tests for User.login() method"
"Use pal to generate tests for User.login() method"
"Generate comprehensive tests for the sorting method in src/new_sort.py using o3"
"Create tests for edge cases not already covered in our tests using gemini pro"
```

4
docs/tools/tracer.md
View File

@@ -36,13 +36,13 @@ The `tracer` tool is a specialized prompt-generation tool that creates structure
**Method Execution Tracing:**
```
"Use zen tracer to analyze how UserAuthManager.authenticate is used and why"
"Use pal tracer to analyze how UserAuthManager.authenticate is used and why"
```
→ Uses `precision` mode to trace the method's execution flow
**Class Dependency Mapping:**
```
"Use zen to generate a dependency trace for the PaymentProcessor class to understand its relationships"
"Use pal to generate a dependency trace for the PaymentProcessor class to understand its relationships"
```
→ Uses `dependencies` mode to map structural relationships

6
docs/tools/version.md
View File

@@ -2,12 +2,12 @@
**Get server version, configuration details, and list of available tools**
The `version` tool provides information about the Zen MCP Server version, configuration details, and system capabilities. This is useful for debugging, understanding server capabilities, and verifying your installation.
The `version` tool provides information about the PAL MCP Server version, configuration details, and system capabilities. This is useful for debugging, understanding server capabilities, and verifying your installation.
## Usage
```
"Get zen to show its version"
"Get pal to show its version"
```
## Key Features
@@ -48,7 +48,7 @@ The tool provides:
## Example Output
```
🔧 Zen MCP Server Information
🔧 PAL MCP Server Information
📋 Version: 2.15.0
🏗️ Build: 2024-01-15T10:30:00Z (commit: abc123f)