Skip to main content
Glama
Prompt Refiner MCP

Prompt Refiner MCP

by TechQuanta

Prompt Refiner MCP

Built openly by TechQuanta Community. Contributions are welcome through the repository's issues and pull requests.

An independent FastMCP server for Prompt Refiner's schema v1.3 one-prompt plus optional controls contract. It refines prompt intent, structure, constraints, and output instructions before a prompt reaches an LLM. It never calls an AI provider, reads local files, or runs generated prompts.

Run

python -m venv .venv
.venv\Scripts\activate
python -m pip install -e .
prompt-builder-mcp

MCP client configuration:

{"mcpServers":{"prompt-builder":{"command":"prompt-builder-mcp"}}}

Tools: get_schema, validate_brief, and build_prompt_variants.

Before connecting a client, inspect the server locally:

prompt-builder-mcp --list-tools
prompt-builder-mcp --schema

Related MCP server: PromptArchitect MCP

Horizon Deploy

Use the repository form with these values:

Field

Value

Server name

prompt-builder

Entrypoint

server.py

Requirements

requirements.txt

Transport

Streamable HTTP

The root server.py adds the src/ package path, binds to HOST (default 0.0.0.0) and PORT (default 8000), and serves the MCP endpoint at /mcp. It is intended for hosted deployment and does not replace the local stdio entry point.

For local HTTP testing:

python server.py

For a local stdio client:

prompt-builder-mcp

Available Tools

3 tools
build_prompt_variantsC

Build focused, detailed, and structured prompt variants without calling an LLM.

Inputs: brief (required). Returns: object

get_schemaA

Return the JSON schema for a deterministic prompt brief.

Inputs: no named parameters. Returns: object

validate_briefC

Validate a prompt brief and report its completeness score.

Inputs: brief (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: retrieving the schema, validating a brief, and generating prompt variants. There is no meaningful overlap or ambiguity between them.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern: get_schema, validate_brief, build_prompt_variants. The naming is predictable and uniform.

    Tool Count5/5

    Three tools is a reasonable, focused count for a narrow domain like prompt refining. Each tool serves a distinct step in the workflow without unnecessary bloat.

    Completeness5/5

    The toolset covers the full core workflow: understanding the schema, validating input, and producing the deliverable. No obvious missing operations are needed for the stated purpose.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      C
      maintenance
      Refines and improves AI prompts using workspace-aware context from your project's tech stack, structure, and dependencies. Includes tools to analyze prompt quality and generate well-structured prompts from raw ideas.
      4
      209 npm
      5
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Refines and optimizes prompts for LLMs through adaptive questioning and intelligent clarification workflows. Supports multiple AI providers (Google, OpenAI, Anthropic, Groq, Qwen) with interactive prompt enhancement and targeted modifications.
      17
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Automatically analyzes and optimizes AI prompts by calculating clarity scores, detecting risks, asking clarifying questions, and adding domain-specific requirements to improve AI interaction quality.
      1
      MIT