Zcash MCP Server
Allows AI agents to send and receive private Zcash payments with full shielded transaction support, including generating shielded addresses, checking balances, sending private payments with encrypted memos, viewing transaction history, and fetching ZEC/USD price.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Zcash MCP Serversend 0.1 ZEC to my shielded address with memo 'test'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Zcash MCP Server - Private Payments for AI Agents
Track: Building Cool Agents
An MCP (Model Context Protocol) server that enables AI agents to send and receive private Zcash payments with full shielded transaction support.
Features
Shielded Addresses: Generate and manage private Zcash addresses
Private Payments: Send ZEC with encrypted memos
Balance Checking: Query shielded balances
Transaction History: View private transaction history
Price Info: Real-time ZEC/USD pricing
Related MCP server: AgentBTC MCP Server
Why This Matters
Privacy in digital payments is critical. This MCP server brings private, blockchain-based payments to AI agents, enabling:
Private agent-to-agent transfers
Secure payment automation
Privacy-preserving transactions
Decentralized finance integration
Installation
npm installUsage
As MCP Server
Add to your MCP client configuration:
{
"mcpServers": {
"zcash": {
"command": "node",
"args": ["/path/to/zcash-mcp-server/index.js"]
}
}
}Available Tools
create_shielded_address - Generate new private Zcash address
get_balance - Check shielded balance
send_private_payment - Send ZEC with encrypted memo
get_transactions - View transaction history
get_price - Get current ZEC/USD price
Architecture
Built on MCP SDK
Connects to Zcash RPC node
Uses shielded (Sapling/Orchard) addresses
Encrypts transaction memos
Security
Private keys never exposed to AI agent
All transactions use shielded pools
Encrypted memo support
No metadata leakage
Demo
See demo/ folder for example usage with Claude Desktop and other MCP clients.
License
MIT
Author
decentrathai - Built for MCP & AI Agents Hackathon 2026
Available Tools
5 toolscreate_shielded_addressA
Generate a new shielded Zcash address for private transactions. Returns a z-address that can receive private payments.
| Name | Required | Description | Default |
|---|---|---|---|
| label | No | Optional label for the address (e.g., "donations", "payments") |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies a non-destructive creation operation and states it returns a z-address, but omits potential costs, limits, or side effects. Adequate for a simple tool but could be more transparent.
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 a single, front-loaded sentence that efficiently conveys purpose and output. Every word contributes 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?
Given the simple tool (1 optional parameter, no output schema), the description adequately covers the tool's action and return value. It explains what a shielded address is and its use for private payments, making it complete for the agent.
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 description coverage is 100% with one optional 'label' parameter well-described. Tool description adds no extra meaning beyond the schema, meeting the baseline expectation.
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 specifies the action (generate), resource (shielded Zcash address), and purpose (private transactions). It distinguishes itself from sibling tools like get_balance and send_private_payment by focusing on address 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?
No guidance on when to use this tool versus alternatives. The description lacks context about prerequisites, cases where address creation might be inappropriate, or relationship to other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_balanceB
Get the current shielded balance in ZEC. Shows only the private (shielded) balance.
| Name | Required | Description | Default |
|---|---|---|---|
| address | No | Optional: specific z-address to check balance for |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It states the tool gets a shielded balance but does not reveal what happens if no address is provided (e.g., returns all balances), required authentication, rate limits, or any side effects. For a read operation, basic transparency is missing.
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, no fluff, front-loaded with key information. Every word is purposeful and efficiently conveys the tool's function.
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?
Given the tool's simplicity (one optional param, no output schema), the description is adequate but incomplete. It does not explain the return format or behavior when no address is provided. The mention of 'ZEC' and 'shielded balance' is helpful, but more detail would improve completeness.
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 minimal context beyond the schema, merely repeating that the address is optional and for a z-address. The phrase 'shows only the private (shielded) balance' provides some interpretation but does not compensate for missing parameter details.
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?
Description clearly states the tool retrieves the current shielded balance in ZEC, distinguishing it from siblings like get_price and get_transactions. It specifies that it shows only the private (shielded) balance, providing a specific verb and resource.
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?
No explicit when-to-use or when-not-to-use guidance. While it mentions 'only the private (shielded) balance,' it does not clarify when to use this tool versus other balance-related tools (if any) or suggest alternatives. No prerequisites or exclusions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_priceA
Get current ZEC/USD price from CoinGecko API
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose behavioral traits like caching, update frequency, rate limits, or error behavior, which is insufficient for a tool with no other metadata.
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?
A single sentence that is front-loaded with the key action and resource, containing no extraneous words. 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?
Given the tool's simplicity (no parameters, no output schema), the description covers the essential purpose and source. It could optionally mention return format, but remains adequate for a trivial 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?
The tool has zero parameters and schema coverage is 100%, so the description adds no parameter-specific meaning but includes context about the data source and currency pair, which is above the baseline expectation.
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 explicitly states the verb 'get', the resource 'ZEC/USD price', and the source 'CoinGecko API', clearly differentiating from sibling tools like get_balance or send_private_payment.
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 implies usage for retrieving the current price, but provides no explicit guidance on when to use versus alternatives or any exclusions. Sibling context helps but the description itself lacks such guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_transactionsB
Get shielded transaction history. Shows recent private transactions with memos.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of transactions to retrieve (default: 10) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It mentions 'recent private transactions with memos' but does not disclose authentication needs, idempotency, or side effects. Inadequate for a query tool.
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 efficient sentences, front-loaded with key action, no superfluous words. Excellent conciseness.
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?
Minimalist tool with 1 parameter and no output schema. Description covers what the tool returns but omits response format, pagination details, and error scenarios. Adequate but not thorough.
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%, and the description adds context about the nature of the data returned ('private transactions with memos') beyond what the schema provides for the limit parameter.
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 'Get shielded transaction history' with specific verbs and resources, and distinguishes from sibling tools like send_private_payment by focusing on viewing, not sending.
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?
No guidance on when to use this tool versus alternatives like get_balance or send_private_payment. Missing context on use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
send_private_paymentB
Send a private Zcash payment to a shielded address. Transaction is fully encrypted with optional memo.
| Name | Required | Description | Default |
|---|---|---|---|
| to_address | Yes | Recipient z-address (shielded) | |
| amount | Yes | Amount to send in ZEC | |
| memo | No | Optional encrypted memo (max 512 bytes) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It states 'fully encrypted' and optional memo, which are key behavioral traits. However, it omits crucial details like transaction finality, fee handling, or error conditions.
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 concise with two sentences and front-loaded. It wastes no words, though slightly more detail could be included without harming conciseness.
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?
Missing output schema and description of return value (e.g., transaction ID). No mention of prerequisites like balance sufficiency. The description is adequate for a simple tool but incomplete for full context.
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% with descriptions for all three parameters. The description adds that the memo is optional and encrypted, but does not exceed the schema's detail. Baseline 3 is appropriate.
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 tool sends a private Zcash payment to a shielded address, with specific verb and resource. It unambiguously distinguishes from sibling tools that handle address creation, balance queries, price, and transaction history.
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?
No guidance on when to use this tool versus alternatives, no exclusions or prerequisites. The description does not mention scenarios like insufficient funds or network requirements, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Each tool targets a distinct aspect of Zcash shielded operations: creating addresses, checking balance, getting price, viewing transactions, and sending payments. No overlap.
All tools follow a consistent verb_noun pattern with underscores (e.g., create_shielded_address, get_balance). Naming is uniform and predictable.
Five tools is appropriate for a focused Zcash private transaction server. Each tool serves a clear purpose without unnecessary bloat or deficiency.
Covers the core shielded workflow: address creation, balance, send, and history. Minor gap: no tool for receiving payments or viewing public balances, but scope is well-defined for shielded operations.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Complete financial infrastructure for AI agents — payments, lending, escrow & more.
Non-custodial crypto payments for AI assistants: balances, payments, and create payment links.
Provide AI agents and automation tools with contextual access to blockchain data including balance…
Connect AI agents to bank accounts, transactions, balances, and investments.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI agents to interact with MIST.cash privacy-preserving payment protocol on Starknet, supporting private transactions with multiple tokens (ETH, USDC, USDT, DAI) through zero-knowledge proofs.51
- AlicenseAqualityDmaintenanceEnables AI agents to perform Bitcoin and Lightning Network payments using a non-custodial, zero-trust architecture. It provides 13 tools for wallet management, invoice creation, and payment processing while keeping node credentials local to the user's machine.1317MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI agents to perform financial transactions such as direct payments, escrows, and bounty management using natural language with zero code integration. It provides a comprehensive suite of tools for fund streaming, subscriptions, and reputation tracking to facilitate secure agent-to-agent commerce.22MIT
- AlicenseAqualityCmaintenanceZcash MCP server for AI agents. 12 tools for shielded operations, memo decoding, ZAP1 attestation. Works with Claude, ChatGPT, OpenClaw.20811MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/decentrathai/zcash-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server