Skip to main content
Glama

ProductPilot MCP

An MCP server that helps digital product creators go from "what should I build?" to a zipped, listing-ready product — end to end.

Built for creators shipping ebooks, prompt packs, wallpaper packs, Notion templates, checklists, printable planners, cheat sheets, resume packs, and study guides to Gumroad/Etsy.

What it does

Ask Claude (or any MCP client connected to this server) things like:

  • "What digital product should I build today?" → find_trending_niches, score_opportunity

  • "Is this niche worth pursuing?" → research_market, analyze_competition, analyze_reviews

  • "Build me a complete product for this niche" → build_product_bundle (the one-shot pipeline)

  • "Write the listing copy" → generate_listing, generate_keywords, generate_tags

  • "What should this cost?" → generate_pricing_strategy

  • "Prep this for Gumroad/Etsy" → prepare_gumroad_listing, prepare_etsy_listing

  • "What sold well, and what should I build next?" → track_product_performance, recommend_next_product

26 tools total — see mcp_server/server.py for the full list, or docs/ARCHITECTURE.md for how they fit together.

Related MCP server: CopyForge MCP Server

Quick start

python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
python -m mcp_server.server

Runs entirely on deterministic mock market data out of the box — no API keys required to try it. Full setup/deployment instructions: docs/SETUP.md, docs/DEPLOYMENT.md.

Using this on claude.ai (web)

Claude.ai's web app only connects to remote MCP servers (a public HTTPS URL) — not local processes. This server supports that via PRODUCTPILOT_TRANSPORT=streamable-http. Full walkthrough (deploy to Render

  • add as a claude.ai custom connector): docs/CLAUDE_AI_CONNECTOR.md.

Status

Functionally complete: all 26 tools registered and runtime-tested end to end (idea → outline → generation → SEO → zipped bundle → analytics tracking), 18 passing unit tests, Docker support.

Known environment gotcha (already fixed here, documented for reference): the mcp PyPI package's 2.0.0 release renamed FastMCP to MCPServer and dropped mcp.server.fastmcp entirely — requirements.txt pins mcp[cli]<2.0.0 to stay on the FastMCP-based API this server is built against. See docs/ARCHITECTURE.md for the full explanation, including a second subtle bug it's worth knowing about (from __future__ import annotations breaking FastMCP's tool introspection).

Project layout

mcp_server/    # all source (agents, market, research, scoring, generation,
               # seo, publishing, analytics, storage, config)
tests/         # pytest suite
docs/          # architecture, setup, deployment, roadmap

See docs/ARCHITECTURE.md for the full breakdown, docs/ROADMAP.md for what's next.

Available Tools

26 tools
analyze_competitionA

Analyze the competitive landscape for a niche: competitor count, pricing, saturation, gaps.

Args: niche: The niche to analyze. marketplace: Optional marketplace to scope to ("gumroad" or "etsy").

Inputs: niche (required), marketplace.

analyze_reviewsC

Analyze review sentiment and recurring themes for products in a niche.

Args: niche: The niche whose reviews should be analyzed.

Inputs: niche (required).

build_product_bundleA

Run the full end-to-end pipeline: generate idea -> outline -> product -> SEO -> zip bundle -> tracking.

This is the "one-shot" tool: give it a niche and it returns a complete, ready-to-publish product.

Args: niche: The niche to build a product for. product_type: Optional product type to constrain to; a suitable type is chosen if omitted. creator_name: Name to use in the generated license file.

Inputs: niche (required), creator_name, product_type.

extract_customer_pain_pointsA

Extract ranked, actionable customer pain points for a niche, each with a suggested solution.

Args: niche: The niche to extract pain points for.

Inputs: niche (required). Returns: result

generate_checklistA

Generate a structured, printable checklist for a product idea of type 'checklist'.

Args: product_idea_id: The ID of a product idea with product_type='checklist'.

Inputs: product_idea_id (required).

generate_ebookA

Generate a full chapter-by-chapter ebook for a product idea of type 'ebook'.

Args: product_idea_id: The ID of a product idea with product_type='ebook'.

Inputs: product_idea_id (required).

generate_keywordsA

Generate SEO keywords for a product idea.

Args: product_idea_id: The ID of a previously generated product idea.

Inputs: product_idea_id (required). Returns: result

generate_listingA

Generate the full SEO/listing package (title, description, keywords, tags, social copy) for a product.

Args: product_idea_id: The originating product idea ID. generated_product_id: The ID of the generated product (from a generate_* tool).

Inputs: product_idea_id (required), generated_product_id (required).

generate_marketing_assetsB

Generate supporting launch marketing assets: social captions, email blurb, launch checklist.

Args: product_idea_id: The originating product idea ID. generated_product_id: The ID of the generated product.

Inputs: product_idea_id (required), generated_product_id (required).

generate_pricing_strategyB

Generate a recommended pricing strategy (price, floor/ceiling, tiers) for a product.

Args: product_idea_id: The originating product idea ID. generated_product_id: The ID of the generated product.

Inputs: product_idea_id (required), generated_product_id (required).

generate_product_ideaA

Generate a concrete digital product idea for a niche, including title, angle, and audience.

Args: niche: The niche to generate an idea for. product_type: Optional product type to constrain to (e.g. "ebook", "prompt_pack"). Random if omitted. suggested_price_usd: Optional target price.

Inputs: niche (required), product_type, suggested_price_usd.

generate_product_outlineA

Generate a structural outline for a previously generated product idea.

Args: product_idea_id: The ID of a product idea previously created via generate_product_idea.

Inputs: product_idea_id (required).

generate_prompt_packA

Generate a categorized AI prompt pack for a product idea of type 'prompt_pack'.

Args: product_idea_id: The ID of a product idea with product_type='prompt_pack'.

Inputs: product_idea_id (required).

generate_tagsB

Generate marketplace tags for a product idea.

Args: product_idea_id: The ID of a previously generated product idea.

Inputs: product_idea_id (required). Returns: result

generate_templateA

Generate a structured template product (Notion template, planner, cheat sheet, resume pack, or study guide).

Args: product_idea_id: The ID of a product idea whose product_type is one of: notion_template, printable_planner, cheat_sheet, resume_pack, study_guide.

Inputs: product_idea_id (required).

generate_thumbnail_promptB

Generate an AI image-generation prompt for a product's cover/thumbnail image.

Args: product_idea_id: The originating product idea ID. generated_product_id: The ID of the generated product.

Inputs: product_idea_id (required), generated_product_id (required).

generate_wallpaper_packA

Generate an AI image-prompt manifest for a wallpaper pack product idea.

Args: product_idea_id: The ID of a product idea with product_type='wallpaper_pack'.

Inputs: product_idea_id (required).

prepare_etsy_listingA

Prepare an Etsy-ready listing (title, description, tags, category, price) for a product.

Args: product_idea_id: The originating product idea ID. generated_product_id: The ID of the generated product.

Inputs: product_idea_id (required), generated_product_id (required).

prepare_gumroad_listingB

Prepare a Gumroad-ready listing (title, description, tags, category, price) for a product.

Args: product_idea_id: The originating product idea ID. generated_product_id: The ID of the generated product.

Inputs: product_idea_id (required), generated_product_id (required).

recommend_next_productA

Recommend the best next product to build, learning from historical performance data.

Falls back to trending-signal-based recommendations if there isn't enough sales history yet.

Inputs: no named parameters.

record_saleA

Record a sale event for a product, updating revenue and conversion rate.

Args: product_id: The ID of the generated product that sold. revenue_usd: The revenue amount for this sale, in USD.

Inputs: product_id (required), revenue_usd (required).

record_viewA

Record a view/impression event for a product listing.

Args: product_id: The ID of the generated product that was viewed.

Inputs: product_id (required).

research_marketA

Run full aggregated market research for a niche across all data sources.

Args: niche: The niche or keyword to research, e.g. "notion templates for students".

Inputs: niche (required).

score_opportunityA

Compute a normalized 0-100 opportunity score for a niche, with a full weighted breakdown.

Args: niche: The niche to score. suggested_price_usd: Optional price point to factor into the profit-margin component.

Inputs: niche (required), suggested_price_usd.

track_product_performanceA

Return aggregate performance analytics, optionally scoped to a single niche.

Args: niche: Optional niche to scope the summary to. Returns all products if omitted.

Inputs: niche.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 26 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes, especially the generate_* family distinguished by product type or asset type. However, research_market overlaps conceptually with the more specific research tools, potentially causing confusion about which to use for a given research need.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (research_market, generate_ebook, track_product_performance). The pattern is predictable and aids agent understanding.

    Tool Count4/5

    26 tools is slightly above the 'heavy' range but the broad end-to-end domain (research, ideation, generation, listing, tracking) justifies the count. Each tool serves a specific step, though a few could be consolidated.

    Completeness3/5

    The pipeline is comprehensive from research to launch to tracking, but there is no tool to list or retrieve a single generated product's details. record_sale and track_product_performance require product IDs, yet no get/list tool exists, leaving a notable gap.

    Related MCP Connectors

    Related MCP Servers