prelaunch-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub personal access token for higher API rate limits when searching repositories. | |
| GOOGLE_CSE_ID | No | Google Custom Search Engine ID. Required if GOOGLE_CSE_KEY is set. | |
| GOOGLE_CSE_KEY | No | Google Custom Search API key. Falls back to DuckDuckGo if not provided. | |
| OPENAI_API_KEY | No | API key for OpenAI or compatible API for LLM intent parsing. Alternative to ANTHROPIC_API_KEY. | |
| OPENAI_BASE_URL | No | Custom endpoint for OpenAI-compatible API (e.g., Ollama, LM Studio). Ignored without OPENAI_API_KEY. | |
| ANTHROPIC_API_KEY | No | API key for Anthropic (Claude Haiku) for LLM intent parsing. Recommended for richer analysis. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| prelaunch_checkA | Check if a product idea already exists before building it. A smarter pre-build reality check that uses LLM-powered intent parsing (when API key is available) and multi-source scanning. Uses:
Environment variables (user provides their own):
Args: idea_text: Natural-language description of the idea. depth: - "quick": GitHub + HN only, no LLM (fastest) - "standard": All sources in parallel + LLM intent parsing (recommended) - "deep": Everything in standard + extra query variants (most thorough) Returns: Reality check report with competition score, demand score, evidence, similar projects, pain signals, and actionable insights. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool available, there is no possibility of selecting the wrong tool or confusing it with another. The purpose of prelaunch_check is clearly defined and unambiguous.
The single tool name 'prelaunch_check' follows a clean verb_noun pattern that is consistent with common MCP naming conventions. No inconsistent naming schemes exist since there is only one tool.
A single tool feels thin for a server, but it is acceptable for a narrowly focused prelaunch validation utility. The tool bundles several internal capabilities (LLM parsing, source scanning) into one entry point, making the count borderline but not unreasonable.
The tool covers the server's core purpose of checking whether a product idea already exists, with multiple depth modes and evidence gathering. However, it lacks secondary operations like saving results, comparing multiple ideas, or managing check history, leaving minor gaps.