Skip to main content
Glama
patreon-mcp-server

patreon-mcp-server

Patreon MCP Server

License: MIT Python 3.11+ MCP PyPI

mcp-name: io.github.KyuRish/patreon-mcp-server

Give AI assistants access to your Patreon creator data. The first authenticated Patreon MCP server - works with Claude Desktop, Cursor, Windsurf, VS Code Copilot, and any MCP-compatible client.

Quick Start

1. Get your Creator Access Token

Go to Patreon Developer Portal and copy your Creator Access Token. This token gives access to your own campaign data only.

2. Configure your MCP client

Claude Desktop - add to claude_desktop_config.json:

{
  "mcpServers": {
    "patreon": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/patreon-mcp-server", "src/patreon_mcp_server/server.py"],
      "env": {
        "PATREON_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

Claude Code - add to .mcp.json in your project root:

{
  "mcpServers": {
    "patreon": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/patreon-mcp-server", "src/patreon_mcp_server/server.py"],
      "env": {
        "PATREON_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

3. Start using it

Ask your AI assistant things like:

  • "Show me my Patreon campaigns"

  • "Who are my top patrons by lifetime support?"

  • "How many patrons are on each tier?"

  • "Which patrons have declining payments?"

  • "List my recent posts"

Related MCP server: Telegram Account MCP Connector

Available Tools

Tool

Description

Returns

fetch_identity

Your authenticated profile

User

fetch_campaigns

List all your campaigns

Campaign[]

fetch_campaign

Campaign details with tier breakdown

CampaignDetail

fetch_members

Paginated patron list (100/page)

MemberPage

fetch_posts

Paginated post list (20/page)

PostPage

fetch_post

Single post by ID

Post

Pagination: fetch_members and fetch_posts return a next_cursor field. Pass it as the cursor parameter to fetch the next page.

Data Fields

Member

full_name, patron_status, pledge_cadence, lifetime_support_cents, currently_entitled_amount_cents, last_charge_date, last_charge_status, will_pay_amount_cents, is_follower, tiers, user_name

Campaign

creation_name, patron_count, pledge_url, published_at, url, vanity, is_monthly, created_at, image_url, summary, one_liner, pay_per_name

Tier

title, amount_cents, description, published, patron_count

Post

title, content, is_paid, is_public, published_at, url, embed_data, embed_url

Privacy & Data

This server is designed with patron privacy in mind:

  • No patron emails - email addresses are never requested from the API

  • No private notes - creator notes about patrons are excluded

  • Read-only - no write operations, the server only reads your data

  • No data storage - the MCP server itself does not cache or persist any data

Important: When using this server with an AI assistant, patron data (names, pledge amounts, charge status) is sent to your AI provider (e.g., Anthropic, OpenAI) and may be temporarily retained per their data processing policies. You are responsible for ensuring your use complies with Patreon's Creator Privacy Promise and applicable data protection laws.

This project is not affiliated with or endorsed by Patreon.

Prerequisites

  • Python 3.11+

  • uv package manager

# Clone the repo
git clone https://github.com/kyurish/patreon-mcp-server.git
cd patreon-mcp-server

# Install dependencies
uv sync

# Test it runs
PATREON_ACCESS_TOKEN=your_token uv run src/patreon_mcp_server/server.py

Project Structure

src/patreon_mcp_server/
  server.py        # Entry point
  mcp_server.py    # FastMCP init + client instance
  tools.py         # @mcp.tool() definitions
  models.py        # Pydantic models + JSON:API parsers
  utils/
    client.py      # PatreonClient (HTTP layer)

Roadmap

This server is currently read-only. Write operations (create posts, manage tiers, send messages to patrons) will be added if there's enough demand - open an issue or star the repo to show interest.

License

MIT License - see LICENSE for details.

Support

If you find this useful, consider supporting development on Patreon.

Available Tools

6 tools
fetch_campaignC

Fetch details for a specific campaign including tiers.

Args: campaign_id: The campaign ID to fetch (numeric)

Inputs: campaign_id (required). Returns: campaign, tiers

fetch_campaignsA

Fetch all campaigns for the authenticated creator.

Inputs: no named parameters. Returns: result

fetch_identityA

Fetch the authenticated Patreon user's profile.

Inputs: no named parameters. Returns: id, full_name, email, image_url, +3 more

fetch_membersA

Fetch members/patrons of a campaign with pagination. Returns up to 100 members per page. Pass next_cursor from the response as cursor to get the next page.

Args: campaign_id: The campaign ID (numeric) cursor: Pagination cursor for next page (from previous response)

Inputs: campaign_id (required), cursor. Returns: members, next_cursor

fetch_postA

Fetch a specific post by ID.

Args: post_id: The post ID to fetch (numeric)

Inputs: post_id (required). Returns: id, title, content, is_paid, +7 more

fetch_postsA

Fetch posts from a campaign with pagination. Returns up to 20 posts per page. Pass next_cursor from the response as cursor to get the next page.

Args: campaign_id: The campaign ID (numeric) cursor: Pagination cursor for next page (from previous response)

Inputs: campaign_id (required), cursor. Returns: posts, next_cursor

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 6 tools

    Disambiguation5/5

    Each tool fetches a distinct resource (campaign, campaigns, identity, members, post, posts) with clear singular/plural differentiation, so an agent can easily distinguish them.

    Naming Consistency5/5

    All tool names follow the consistent pattern 'fetch_noun' (or 'fetch_nouns' for plurals), using lowercase and underscores without deviation.

    Tool Count5/5

    6 tools is well-scoped for a Patreon API server covering core fetching of campaigns, identity, members, and posts, offering essential reads without bloat.

    Completeness2/5

    The server only provides read operations ('fetch_*') and lacks any create, update, or delete capabilities, which are essential for managing Patreon resources, leaving significant gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants read-only access to Sprinklr data via MCP, allowing querying reports, searching cases, and calling Sprinklr API endpoints.
      8 npm
      ISC
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI assistants to access Saxo Bank portfolio data, account balances, positions, orders, transactions, and market data such as instruments, quotes, and charts. It is read-only by default, with trading tools available only when explicitly enabled.
      10
      MIT