This server lets AI agents accept non-custodial crypto payments and sell digital products through MCP tools, with optional API-key invoice management.
Create one-time payment links (create_payment_link) with a destination wallet, amount, chain/asset, memo, and optional email; returns a shareable pay URL, embeddable button, and manage URL.
Create reusable tip jars (create_tip_jar) where payers choose the amount; supports title, description, suggested amounts, custom slug, and is idempotent per wallet.
Sell digital products or pay-to-unlock content (create_unlock) by setting a price and payload such as a secret text, license key, or file link for automatic reveal after purchase.
Look up keyless account status (get_account_status) using a manage_token to see settlement details, tip jars, totals, and invoices.
With SHIELDZ_API_KEY set, manage full merchant invoices via create_invoice, get_invoice, and list_invoices.
All tools work keyless with no account/API key; funds settle directly to the provided wallet and Shieldz never holds the keys.
Model Context Protocol (MCP) server for Shieldz. Lets an AI agent (Claude, etc.) accept non-custodial crypto payments and sell digital products.
Funds always settle to the wallet address you provide. Shieldz never holds your keys.
Give a destination wallet address and start accepting crypto in one call:
create_payment_link — a one-time payment link (shareable URL + embeddable button + QR). Args: address, amount_usd, optional chain (default base), asset (default USDC), memo, email.
create_tip_jar — a reusable "pay what you want" page; the payer chooses the amount. Args: address, optional chain, asset, title, suggested_amounts_usd, slug, email.
create_unlock — sell a digital product: a pay-to-unlock page for a file link, license key, or secret text (up to 100k chars). The buyer pays and the payload is revealed on their paid confirmation, automatically. Args: address, price_usd, payload, aup_accepted, optional title, description, chain, asset, email. (To deliver an uploaded file up to 10 MB, post multipart to /api/v1/unlocks.)
get_account_status — look up settlement details, tip jars, totals, and invoices by manage_token.
These work with zero configuration. Pass an optional email so the owner can claim a full dashboard later via magic link.
Remote (no install) — point any MCP client at the hosted server:
{ "mcpServers": { "shieldz": { "url": "https://shieldz.cash/mcp" } } }Local (stdio) — run via npx:
{
"mcpServers": {
"shieldz": {
"command": "npx",
"args": ["-y", "@shieldz/mcp"]
}
}
}Related MCP server: PayRam MCP Server
Set SHIELDZ_API_KEY to additionally enable richer invoice management: create_invoice, get_invoice, list_invoices.
{
"mcpServers": {
"shieldz": {
"command": "npx",
"args": ["-y", "@shieldz/mcp"],
"env": { "SHIELDZ_API_KEY": "sk_live_…" }
}
}
}Get an API key from your merchant dashboard → Developers.
SHIELDZ_API_KEY (optional) — enables the invoice tools. Omit for keyless mode.
SHIELDZ_BASE_URL (optional) — defaults to https://shieldz.cash.
MIT © Deniz Yanbollu / Shieldz
Create a one-time crypto payment link with ZERO setup, no account, no API key. Give a destination wallet address and an amount; get back a shareable pay_url, an embeddable button, and a manage_url. Non-custodial: funds settle directly to the address you provide. Optionally pass an email so the owner can claim a full dashboard later.
| Name | Required | Description | Default |
|---|---|---|---|
| memo | No | Description shown on the checkout | |
| asset | No | Defaults to USDC | |
| chain | No | Defaults to base | |
| No | Optional, lets the owner claim a dashboard later | ||
| address | Yes | Destination wallet; funds settle here. Shieldz never holds them. | |
| amount_usd | Yes | Amount in USD, e.g. 49 for $49.00 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses non-custodial nature, direct settlement, and optional email for dashboard. However, it does not mention rate limits, authentication, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the key purpose, and every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 6 parameters and no output schema, the description adequately explains inputs and what the user gets back (pay_url, button, manage_url). It is sufficient for an AI agent to understand usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining the non-custodial aspect, default values, and optional functionality, e.g., email for dashboard.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it creates a one-time crypto payment link with zero setup, distinguishing it from sibling tools like create_tip_jar (tips) and get_account_status (status). The verb 'Create' and resource 'payment link' are explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies when to use (no account, no API key) but does not explicitly state when not to use or provide alternatives beyond the implied context. It clearly sets expectations for what the tool does.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a reusable 'pay what you want' tip jar with ZERO setup, no account, no API key. The payer chooses the amount. Returns a shareable /tip url, an embeddable button, and a manage_url. Idempotent per wallet address: calling again updates the same tip jar. Non-custodial: funds settle directly to the address you provide.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | Optional custom URL slug; auto-generated if omitted | |
| asset | No | Defaults to USDC | |
| chain | No | Defaults to base | |
| No | Optional, lets the owner claim a dashboard later | ||
| title | No | Heading shown on the tip page, e.g. 'Buy me a coffee' | |
| address | Yes | Destination wallet; funds settle here. Shieldz never holds them. | |
| description | No | ||
| suggested_amounts_usd | No | Preset amount buttons in USD, e.g. [3, 5, 10] |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and discloses key behaviors: idempotent per wallet address, non-custodial, funds settle directly, and updates the same jar on repeat calls. Could mention potential side effects of updates (e.g., overwriting settings) but overall strong.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no fluff. First sentence packs purpose and key value propositions; second covers idempotence and non-custodial nature. Every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 8 parameters (1 required) and no output schema, the description covers overall function, return types, and behavioral traits. It lacks error cases or edge conditions, but completeness is adequate for a creation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 88% (high), so baseline is 3. The description adds context beyond schema: confirms the address parameter is the destination and that funds are non-custodial, and suggests amount parameters relate to payer choice. This adds meaningful semantic value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it creates a reusable 'pay what you want' tip jar with zero setup, and specifies return values (shareable URL, embeddable button, manage_url). It distinguishes from siblings like create_payment_link (likely fixed amounts) and get_account_status (different function).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says 'Create a reusable tip jar with ZERO setup' which implies when to use. However, it does not explicitly contrast with sibling tools or state when NOT to use this tool. The context is clear but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up a keyless Shieldz account by its manage_token (returned when you create a payment link or tip jar). Returns settlement details, tip jars, totals (paid/pending), and the full invoice list as structured JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| manage_token | Yes | The manage_token from create_payment_link / create_tip_jar |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It specifies exactly what is returned (settlement details, tip jars, totals, invoice list), which discloses the tool's output. However, it does not explicitly state that the operation is read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero wasted words. The purpose is front-loaded ('Look up a keyless Shieldz account'), and the output is concisely listed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple, one-parameter lookup tool with no output schema or annotations, the description covers all essential aspects: input source, output contents (structured JSON). No additional information is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema describes the required parameter 'manage_token' as the token from sibling tools. The description reinforces this by referencing the same origin, adding practical context beyond the schema. Schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'look up' and the resource 'keyless Shieldz account' by a specific token. It distinguishes from sibling tools (create_payment_link, create_tip_jar) by focusing on retrieval vs. creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the token origin ('returned when you create a payment link or tip jar'), linking to sibling tools. It implies use after creation, but does not explicitly state when not to use or provide alternative conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.3.0create_payment_linkcreate_tip_jarget_account_statusEach tool has a clearly distinct purpose: fixed-amount payment link, flexible tip jar, and account status. There is no overlap or ambiguity.
All tools follow a consistent verb_noun snake_case pattern (create_payment_link, create_tip_jar, get_account_status), making it easy to infer function from name.
With 3 tools, the server is tightly scoped to its 'zero setup' philosophy, covering the essential operations without unnecessary bloat.
The server covers creation of two payment types and status retrieval, but lacks update/delete capabilities for payment links or tip jars, which slightly limits agent workflows.
Non-custodial crypto payments for AI assistants: balances, payments, and create payment links.
Agent Commerce Protocol MCP — bridges Stripe ACP + Google AP2 + Coinbase x402 for agent payments
Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
Pay-per-action access to APIs and MCP tools over Lightning L402 and Base USDC x402.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ShieldZCash/shieldz-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
