MCP serverOfficialCurated by metahubEval warningscoding

@stripe/mcp

Name: @stripe/mcp
Author: stripe

A command line tool for setting up Stripe MCP server

pinned to #89ffbeeupdated 3 days ago

8/11Verified publisherCurated by MetaHubActively maintainedLicensedDocumentedMCP SDK linkedRunnableClean repo

Ask your AI client: “install mcps/stripe-mcp”.

Requires the metahub MCP server installed in your client. Set up MCP.

mh install mcps/stripe-mcp

metahub onboarded this repo on the author's behalf.

If you own github.com/stripe/ai on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.

Claim this repo

Stars

1,730

Last commit

3 days ago

89ffbee

Latest release

published

3 days ago

#ai
#llm
#llm-agents
#mcp
#modelcontextprotocol
#python
#stripe
#typescript
#workflows

What this server exposes

Surfaces parsed from this server's source at publish time.

Launches: @stripe/mcp

Evaluation report

Warnings

Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.89ffbee· 3 days ago

Structural

8 passed2 warnings

Declared files existwarn
2 declared file entries do not exist. LICENSE; VERSION
Remove the stale entries, or add the missing paths — the published tarball will not contain them.
Declared entry point existswarn
Declared entry point dist/index.js is not present.
Ship the built output, or declare a prepare/build script that produces it.
Repository is reachable
https://github.com/stripe/ai @ 89ffbee — ★ 1,730 · TypeScript · MIT · last push yesterday
Manifest detected
kind=mcp slug=stripe-mcp · path=tools/modelcontextprotocol · source=package.json
Slug is URL-safe
"stripe-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/stripe-mcp
Version is semver
0.3.3
Manifest present and parseable
Manifest found at package.json.
Name declared and well-formed
Name "@stripe/mcp" is well-formed.
Version is semver
Version 0.3.3.

Release history

releasecurrent89ffbeewarn3 days ago

View on GitHub

Stripe Model Context Protocol

The Stripe Model Context Protocol server allows you to integrate with Stripe APIs through function calling. This protocol supports various tools to interact with different Stripe services.

Setup

Stripe hosts a remote MCP server at https://mcp.stripe.com. View the docs here.

Local

To run the Stripe MCP server locally using npx, use the following command:

# Basic usage
npx -y @stripe/mcp --api-key=YOUR_STRIPE_SECRET_KEY

# To configure a Stripe connected account
npx -y @stripe/mcp --api-key=YOUR_STRIPE_SECRET_KEY --stripe-account=CONNECTED_ACCOUNT_ID

Make sure to replace YOUR_STRIPE_SECRET_KEY with your actual Stripe secret key. Alternatively, you could set the STRIPE_SECRET_KEY in your environment variables.

Note: Tool permissions are controlled by your Restricted API Key (RAK). Create a RAK with the desired permissions at https://dashboard.stripe.com/apikeys

Usage with Claude Desktop

Add the following to your claude_desktop_config.json. See here for more details.

{
  "mcpServers": {
    "stripe": {
      "command": "npx",
      "args": ["-y", "@stripe/mcp", "--api-key=STRIPE_SECRET_KEY"]
    }
  }
}

or if you're using Docker

{
  "mcpServers": {
    "stripe": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "mcp/stripe", "--api-key=STRIPE_SECRET_KEY"]
    }
  }
}

Usage with Gemini CLI

Install Gemini CLI through your preferred method.
Install the Stripe MCP extension: gemini extensions install https://github.com/stripe/ai.
Start Gemini CLI: gemini.
Go through the OAUTH flow: /mcp auth stripe.

Available tools

See the Stripe MCP documentation for a list of tools.

Debugging the Server

To debug your server, you can use the MCP Inspector.

First build the server

npm run build

Run the following command in your terminal:

# Start MCP Inspector and server
npx @modelcontextprotocol/inspector node dist/index.js --api-key=YOUR_STRIPE_SECRET_KEY

Build using Docker

First build the server

docker build -t mcp/stripe .

Run the following command in your terminal:

docker run -p 3000:3000 -p 5173:5173 -v /var/run/docker.sock:/var/run/docker.sock mcp/inspector docker run --rm -i mcp/stripe --api-key=YOUR_STRIPE_SECRET_KEY

Instructions

Replace YOUR_STRIPE_SECRET_KEY with your actual Stripe API secret key.
Run the command to start the MCP Inspector.
Open the MCP Inspector UI in your browser and click Connect to start the MCP server.
You can see the list of tools you selected and test each tool individually.

Reviews

No reviews yet. Be the first.

MCPOfficial

vercel-example

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

#a0f37a7UnknownCoding & Refactoring+5

mcp-example

Example project for Mcp

#a0f37a7UnknownCoding & Refactoring+5

headroom

The Context Optimization Layer for LLM Applications - Cut costs by 50-90%

#ad0034fUnknownPrompts, Context & Memory+3

headroomlabs-ai

53,908

agentaianthropic+9

mh install mcps/stripe-mcp

MCP serverOfficialCurated by metahubEval warningscoding

@stripe/mcp

A command line tool for setting up Stripe MCP server

pinned to #89ffbeeupdated 3 days ago

8/11Verified publisherCurated by MetaHubActively maintainedLicensedDocumentedMCP SDK linkedRunnableClean repo

Ask your AI client: “install mcps/stripe-mcp”.

Requires the metahub MCP server installed in your client. Set up MCP.

mh install mcps/stripe-mcp

metahub onboarded this repo on the author's behalf.

Claim this repo

Stars

1,730

Last commit

3 days ago

89ffbee

Latest release

published

3 days ago

#ai
#llm
#llm-agents
#mcp
#modelcontextprotocol
#python
#stripe
#typescript
#workflows

What this server exposes

Surfaces parsed from this server's source at publish time.

Launches: @stripe/mcp

Evaluation report

Warnings

Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.89ffbee· 3 days ago

Structural

8 passed2 warnings

Declared files existwarn
2 declared file entries do not exist. LICENSE; VERSION
Remove the stale entries, or add the missing paths — the published tarball will not contain them.
Declared entry point existswarn
Declared entry point dist/index.js is not present.
Ship the built output, or declare a prepare/build script that produces it.
Repository is reachable
https://github.com/stripe/ai @ 89ffbee — ★ 1,730 · TypeScript · MIT · last push yesterday
Manifest detected
kind=mcp slug=stripe-mcp · path=tools/modelcontextprotocol · source=package.json
Slug is URL-safe
"stripe-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/stripe-mcp
Version is semver
0.3.3
Manifest present and parseable
Manifest found at package.json.
Name declared and well-formed
Name "@stripe/mcp" is well-formed.
Version is semver
Version 0.3.3.

Release history

releasecurrent89ffbeewarn3 days ago

View on GitHub

Stripe Model Context Protocol

The Stripe Model Context Protocol server allows you to integrate with Stripe APIs through function calling. This protocol supports various tools to interact with different Stripe services.

Setup

Stripe hosts a remote MCP server at https://mcp.stripe.com. View the docs here.

Local

To run the Stripe MCP server locally using npx, use the following command:

# Basic usage
npx -y @stripe/mcp --api-key=YOUR_STRIPE_SECRET_KEY

# To configure a Stripe connected account
npx -y @stripe/mcp --api-key=YOUR_STRIPE_SECRET_KEY --stripe-account=CONNECTED_ACCOUNT_ID

Make sure to replace YOUR_STRIPE_SECRET_KEY with your actual Stripe secret key. Alternatively, you could set the STRIPE_SECRET_KEY in your environment variables.

Note: Tool permissions are controlled by your Restricted API Key (RAK). Create a RAK with the desired permissions at https://dashboard.stripe.com/apikeys

Usage with Claude Desktop

Add the following to your claude_desktop_config.json. See here for more details.

{
  "mcpServers": {
    "stripe": {
      "command": "npx",
      "args": ["-y", "@stripe/mcp", "--api-key=STRIPE_SECRET_KEY"]
    }
  }
}

or if you're using Docker

{
  "mcpServers": {
    "stripe": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "mcp/stripe", "--api-key=STRIPE_SECRET_KEY"]
    }
  }
}

Usage with Gemini CLI

Install Gemini CLI through your preferred method.
Install the Stripe MCP extension: gemini extensions install https://github.com/stripe/ai.
Start Gemini CLI: gemini.
Go through the OAUTH flow: /mcp auth stripe.

Available tools

See the Stripe MCP documentation for a list of tools.

Debugging the Server

To debug your server, you can use the MCP Inspector.

First build the server

npm run build

Run the following command in your terminal:

# Start MCP Inspector and server
npx @modelcontextprotocol/inspector node dist/index.js --api-key=YOUR_STRIPE_SECRET_KEY

Build using Docker

First build the server

docker build -t mcp/stripe .

Run the following command in your terminal:

docker run -p 3000:3000 -p 5173:5173 -v /var/run/docker.sock:/var/run/docker.sock mcp/inspector docker run --rm -i mcp/stripe --api-key=YOUR_STRIPE_SECRET_KEY

Instructions

Replace YOUR_STRIPE_SECRET_KEY with your actual Stripe API secret key.
Run the command to start the MCP Inspector.
Open the MCP Inspector UI in your browser and click Connect to start the MCP server.
You can see the list of tools you selected and test each tool individually.

Reviews

No reviews yet. Be the first.

MCPOfficial

vercel-example

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

#a0f37a7UnknownCoding & Refactoring+5