Skip to main content
Glama
BrainDAO

NEAR MCP Server

by BrainDAO
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

🌊 NEAR MCP Server

npm version License: ISC

📖 Overview

The NEAR MCP Server enables AI agents to interact with the NEAR Protocol blockchain. This server provides smart contract interaction, transaction handling, and event listening capabilities with AI-driven processing.

By implementing the Model Context Protocol (MCP), this server allows Large Language Models (LLMs) to monitor blockchain events, process them with AI intelligence, and respond back to smart contracts, bridging the gap between AI and decentralized applications.

Related MCP server: thegraph-mcp

✨ Features

  • Event Watching: Monitor NEAR smart contracts for specific events in real-time.

  • AI-Driven Processing: Automatically process blockchain events with AI and send responses back to contracts.

  • Subscription Management: Manage multiple event subscriptions with detailed statistics.

  • Flexible Configuration: Customizable polling intervals, response methods, and network settings.

📦 Installation

🚀 Using npx (Recommended)

To use this server without installing it globally:

npx @iqai/mcp-near

🔧 Build from Source

git clone https://github.com/IQAIcom/mcp-near.git
cd mcp-near
pnpm install
pnpm run build

⚡ Running with an MCP Client

Add the following configuration to your MCP client settings (e.g., claude_desktop_config.json).

📋 Minimal Configuration

{
  "mcpServers": {
    "near": {
      "command": "npx",
      "args": ["-y", "@iqai/mcp-near"],
      "env": {
        "ACCOUNT_ID": "your-account.near",
        "ACCOUNT_KEY": "ed25519:your_private_key_here"
      }
    }
  }
}

⚙️ Advanced Configuration (Local Build)

{
  "mcpServers": {
    "near": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-near/dist/index.js"],
      "env": {
        "ACCOUNT_ID": "your-account.near",
        "ACCOUNT_KEY": "ed25519:your_private_key_here",
        "NEAR_NETWORK_ID": "mainnet",
        "NEAR_NODE_URL": "https://rpc.mainnet.near.org"
      }
    }
  }
}

🔐 Configuration (Environment Variables)

Variable

Required

Description

Default

ACCOUNT_ID

Yes

Your NEAR account ID for authentication

-

ACCOUNT_KEY

Yes

Private key for your NEAR account (ed25519: or secp256k1: format)

-

NEAR_NETWORK_ID

No

NEAR network ("mainnet", "testnet", "betanet")

mainnet

NEAR_NODE_URL

No

Custom NEAR RPC endpoint

-

NEAR_GAS_LIMIT

No

Gas limit for transactions

-

💡 Usage Examples

🔔 Event Watching

  • "Watch for 'run_agent' events on contract oracle.near"

  • "Start monitoring price_request events on my-contract.testnet"

  • "Set up a listener for transfer events with 5-second polling"

📊 Subscription Management

  • "List all my active event subscriptions"

  • "Show statistics for my event watchers"

  • "Stop watching events on contract oracle.near"

🤖 AI-Driven Workflows

  • "Process incoming oracle requests and respond with AI analysis"

  • "Monitor for user queries and provide intelligent responses"

🛠️ MCP Tools

👨‍💻 Development

🏗️ Build Project

pnpm run build

👁️ Development Mode (Watch)

pnpm run watch

✅ Linting & Formatting

pnpm run lint
pnpm run format

🧪 Running Tests

pnpm test

📁 Project Structure

  • src/tools/: Individual tool definitions

  • src/services/: Event watcher, auth manager, and business logic

  • src/types.ts: TypeScript type definitions

  • src/index.ts: Server entry point

🔄 AI-Driven Event Processing Workflow

The server enables an "AI in the loop" workflow:

  1. 🔗 Smart contract transaction triggers an event and pauses execution

  2. 🤖 MCP server detects the event and requests AI processing from the client

  3. 🧠 AI client processes the event data and provides intelligent response

  4. ↩️ Server sends AI response back to blockchain via transaction

  5. ✅ Original smart contract resumes with the AI-provided data

📚 Resources

⚠️ Disclaimer

This project interacts with the NEAR blockchain and requires private keys for transaction signing. Users should exercise caution, secure their credentials, and verify all transactions independently. Blockchain operations involve risk and may incur gas fees.

📄 License

ISC

Available Tools

3 tools
list_watched_near_eventsA

List all currently watched NEAR events and their status

ParametersJSON Schema
NameRequiredDescriptionDefault
includeStatsNoInclude detailed statistics

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It correctly identifies as a read operation without side effects. However, it could mention output details like the structure of returned data or whether pagination applies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single, concise sentence with no wasted words. Front-loaded with the core action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 optional param, no output schema), the description is mostly complete. It could be improved by hinting at the return value format (e.g., list of events with fields).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with one parameter 'includeStats' documented. The description does not add extra meaning beyond the schema, meeting the baseline for full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (list), the resource (currently watched NEAR events), and the included information (status). It distinctly separates from sibling tools stop_watching_near_event and watch_near_event.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for viewing watched events but does not provide explicit when-to-use or when-not-to-use guidance compared to siblings. It lacks context on prerequisites or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

stop_watching_near_eventC

Stop watching for specific events on a NEAR contract

ParametersJSON Schema
NameRequiredDescriptionDefault
contractIdYesNEAR contract ID to stop monitoring
eventNameYesName of the event to stop watching

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden. It only states the action without describing side effects, idempotency, or prerequisites (e.g., whether a watch must exist).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loading the core purpose. While brief, it avoids unnecessary words and is efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two required parameters and no output schema, the description is adequate. However, it could mention the expected result or behavior when no watch exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters. The description adds no additional meaning beyond the schema's parameter descriptions, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Stop watching for specific events on a NEAR contract' clearly states the tool's purpose with a specific verb and resource. However, it does not differentiate from the sibling tool 'watch_near_event' beyond the opposite action, which could be clearer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 'watch_near_event' or 'list_watched_near_events'. The description implies use for stopping a watch but lacks explicit context or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

watch_near_eventC

Start watching for specific events on a NEAR contract and process them with AI responses

ParametersJSON Schema
NameRequiredDescriptionDefault
eventNameYesName of the NEAR event to watch for
contractIdYesNEAR contract ID to monitor
responseMethodNameNoContract method to call with the response (defaults to agent_response)agent_response
responseParameterNameNoName of the parameter to pass to the response method (defaults to response)response
cronExpressionNoCron expression for polling frequency (default: every 10 seconds)*/10 * * * * *

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description must disclose behavioral traits. It mentions 'process them with AI responses' but does not explain how responses are generated, polling behavior, or persistence. Lacks details on side effects or requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that is clear and front-loaded. Could be slightly more structured, but efficiently conveys the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the polling mechanism, lifecycle (e.g., how to stop), or what 'process with AI responses' entails. Sibling tools hint at a monitor/stop pattern.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents each parameter. The description does not add significant meaning beyond what is in the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb 'start watching' and the resource 'events on a NEAR contract', and adds the purpose 'process them with AI responses'. Differentiates from siblings by specifying the start action, but could be more explicit about the lifecycle.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs siblings (list_watched_near_events, stop_watching_near_event). Does not provide context about prerequisites or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 3 tool updatesv0.1.2
    • First observedlist_watched_near_events
    • First observedstop_watching_near_event
    • First observedwatch_near_event
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clear, distinct purpose: listing, stopping, or starting event watches. No overlap or ambiguity.

Naming Consistency4/5

All tools use a verb_near_event pattern (list_watched, stop_watching, watch). Minor inconsistency in tense (watched vs watching) but overall predictable.

Tool Count4/5

3 tools is appropriate for a focused event-watching server. Not over- or under-scoped.

Completeness4/5

Covers the basic lifecycle: create (watch), read (list), delete (stop). Missing update but that is often unnecessary for event filters.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers