Skip to main content
Glama

get_technique_guide

Discover Context Engineering techniques for reasoning, workflow, code, or project tasks to identify the best tool for specific needs.

Instructions

Returns a guide to available Context Engineering techniques (The Librarian).
Use this to discover the best tool for a given task.

Args:
    category: Filter by 'reasoning', 'workflow', 'code', 'project', or 'all'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoall

Implementation Reference

  • The core handler function for the 'get_technique_guide' tool, decorated with @mcp.tool() for automatic registration in the FastMCP server. It validates the 'category' input using TechniqueGuideInput and returns a comprehensive markdown guide listing available Context Engineering techniques, categorized by use case.
    @mcp.tool()
    def get_technique_guide(category: str = "all") -> str:
        """
        Returns a guide to available Context Engineering techniques (The Librarian).
        Use this to discover the best tool for a given task.
    
        Args:
            category: Filter by 'reasoning', 'workflow', 'code', 'project', or 'all'.
        """
        try:
            _ = TechniqueGuideInput(category=category)
        except ValidationError as e:
            return f"Input Validation Error: {e}"
    
        guide = """
        # Context Engineering Technique Guide
    
        | Category | Tool | Complexity | Best For |
        |----------|------|------------|----------|
        | **Architect** | `design_context_architecture` | Variable | **Constructor Mode**: Building custom agents/systems. |
        | **Router** | `analyze_task_complexity` | Low | **YOLO Mode**: Finding the right tool automatically. |
        | **Reasoning** | `reasoning.systematic` | High | Complex problems requiring step-by-step logic. |
        | **Reasoning** | `thinking.extended` | Very High | Deep exploration, trade-off analysis, simulation. |
        | **Workflow** | `workflow.test_driven` | High | Implementing features with TDD. |
        | **Code** | `code.analyze` | Medium | Understanding code structure and quality. |
        | **Project** | `project.explore` | Medium | Mapping a new codebase. |
        | **Basic** | `Standard Molecule` | Low | Simple pattern matching (use `get_molecular_template`). |
    
        **Usage:**
        - **YOLO Mode**: Call `analyze_task_complexity` to get a quick tool recommendation.
        - **Constructor Mode**: Call `design_context_architecture` to get a full system blueprint.
        """
        # Simple filtering (mock implementation for now based on description)
        # Ideally, this would filter the text, but the current implementation returns static text.
        # The validation ensures 'category' is safe.
        return guide
  • Pydantic BaseModel defining the input schema for the get_technique_guide tool, enforcing valid categories via regex pattern and providing a default value.
    class TechniqueGuideInput(BaseModel):
        category: str = Field(
            "all",
            pattern="^(reasoning|workflow|code|project|all)$",
            description="Filter category.",
        )
  • The @mcp.tool() decorator line that registers the get_technique_guide function as an MCP tool in the FastMCP server instance 'mcp'.
    @mcp.tool()

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/4rgon4ut/sutra'

If you have feedback or need assistance with the MCP directory API, please join our Discord server