How do I use genlayer-cli-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genlayer-cli-mcp Lint my contract and deploy it on localnet" 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.

de en es ja ko ru zh

genlayer-cli-mcp

by ngh1105

Overview Schema Related Servers Score Discussions

JavaScript

Local

GenLayer CLI MCP

MCP server for AI agents that need to work with GenLayer projects.

It exposes:

genlayer: full access to the GenLayer CLI
genvm_lint: access to genvm-lint
genlayer_deploy: deploys contracts with genlayer-js
check_tools: verifies local tool availability and private key config

The server uses stdio transport and executes commands with spawn(command, args).

Requirements

Node.js 18+
GenLayer CLI available on PATH
GenVM linter available on PATH

Install the external tools:

npm install -g genlayer
py -3.12 -m pip install genvm-linter

Check them:

genlayer --version
genvm-lint --version

Related MCP server: MCP Plus

MCP Config

If this package is published to npm:

{
  "mcpServers": {
    "genlayer-cli": {
      "command": "npx",
      "args": ["-y", "genlayer-cli-mcp"],
      "env": {
        "GENLAYER_PRIVATE_KEY": "0x_your_private_key_here"
      }
    }
  }
}

If running from this repository:

{
  "mcpServers": {
    "genlayer-cli": {
      "command": "node",
      "args": ["E:\\genlayer-cli-mcp\\dist\\index.js"],
      "env": {
        "GENLAYER_PRIVATE_KEY": "0x_your_private_key_here"
      }
    }
  }
}

Accepted private key env names:

GENLAYER_PRIVATE_KEY
GENLAYER_PRV_KEY
GENLAYER_PRIVKEY
PRIVATE_KEY

The private key may be either 0x plus 64 hex characters or raw 64 hex characters. If the configured key is missing or invalid, genlayer_deploy generates a new private key and deploys with it in the same tool call. When a new key is generated, the response includes it so you can save it.

Local Development

cd E:\genlayer-cli-mcp
npm install
npm run build
npm run smoke

Run the server:

node E:\genlayer-cli-mcp\dist\index.js

Package locally:

npm pack

Publish to npm:

npm login
npm publish --access public

Tools

`check_tools`

Checks node, genlayer, python, genvm-lint, and private key config.

Example AI prompt:

Use MCP tool check_tools from genlayer-cli.

`genlayer`

Runs genlayer <args...> with full command access.

Example:

{
  "args": ["--version"]
}

Example deploy through the raw CLI:

{
  "args": [
    "deploy",
    "--contract",
    "E:\\path\\to\\contract.py",
    "--rpc",
    "http://localhost:4000/api"
  ],
  "timeoutMs": 120000
}

`genvm_lint`

Runs genvm-lint <args...>.

Example:

{
  "args": ["check", "E:\\path\\to\\contract.py"],
  "timeoutMs": 120000
}

`genlayer_deploy`

Deploys an Intelligent Contract through genlayer-js.

This is the recommended deploy tool for AI agents because it handles private key fallback:

Use privateKey from the tool input if valid.
Otherwise use private key from MCP config env if valid.
Otherwise generate a new private key.
Deploy with the selected/generated private key immediately.

Example:

{
  "contractPath": "E:\\path\\to\\contract.py",
  "chain": "localnet",
  "rpcUrl": "http://localhost:4000/api",
  "autoFundLocalnet": true,
  "waitForReceipt": true,
  "receiptStatus": "ACCEPTED",
  "timeoutMs": 120000
}

Optional fields:

{
  "privateKey": "0x...",
  "args": [],
  "kwargs": {},
  "cwd": "E:\\project",
  "leaderOnly": false,
  "consensusMaxRotations": 5,
  "initializeConsensus": true,
  "fundAmount": 10,
  "receiptRetries": 50,
  "receiptIntervalMs": 5000,
  "exposePrivateKey": false
}

Supported chains:

localnet
studionet
testnetAsimov
testnetBradbury

Agent Setup Examples

Use the same MCP server definition for coding agents that support MCP over stdio. Replace the private key with your own testnet/local key, or leave it invalid if you want genlayer_deploy to generate a fresh key during deploy.

Codex

Add this MCP server to your Codex MCP configuration:

{
  "mcpServers": {
    "genlayer-cli": {
      "command": "npx",
      "args": ["-y", "genlayer-cli-mcp"],
      "env": {
        "GENLAYER_PRIVATE_KEY": "0x_your_private_key_here"
      }
    }
  }
}

Suggested Codex prompt:

Use MCP tool check_tools from genlayer-cli and tell me whether deploy can use the configured private key.

Then lint my GenLayer contract with genvm_lint.

If lint passes, deploy it with genlayer_deploy using:
{
  "contractPath": "E:\\path\\to\\contract.py",
  "chain": "localnet",
  "rpcUrl": "http://localhost:4000/api",
  "autoFundLocalnet": true,
  "waitForReceipt": true,
  "receiptStatus": "ACCEPTED"
}

Antigravity

Add the MCP server in Antigravity's MCP settings:

{
  "mcpServers": {
    "genlayer-cli": {
      "command": "npx",
      "args": ["-y", "genlayer-cli-mcp"],
      "env": {
        "GENLAYER_PRIVATE_KEY": "0x_your_private_key_here"
      }
    }
  }
}

Suggested Antigravity prompt:

Use the genlayer-cli MCP server.

First call check_tools.
Then run genvm_lint on:
{
  "args": ["check", "E:\\path\\to\\contract.py"]
}

If the contract is valid, call genlayer_deploy. If the configured MCP private key is invalid, let the MCP tool generate a new private key and deploy with it automatically.

Claude Code

Add the server with Claude Code's MCP add command:

claude mcp add genlayer-cli -- npx -y genlayer-cli-mcp

If your Claude Code setup supports environment variables in MCP config, add:

{
  "GENLAYER_PRIVATE_KEY": "0x_your_private_key_here"
}

Alternative local-source command:

claude mcp add genlayer-cli -- node E:\genlayer-cli-mcp\dist\index.js

Suggested Claude Code prompt:

Use the genlayer-cli MCP server.

1. Call check_tools.
2. Run genvm_lint for E:\path\to\contract.py.
3. If lint succeeds, deploy with genlayer_deploy.
4. If the private key in MCP config is missing or invalid, generate a new private key and deploy with that generated key in the same tool call.

Arguments:
{
  "contractPath": "E:\\path\\to\\contract.py",
  "chain": "localnet",
  "rpcUrl": "http://localhost:4000/api",
  "autoFundLocalnet": true,
  "waitForReceipt": true,
  "receiptStatus": "ACCEPTED"
}

Security

This MCP server intentionally exposes full GenLayer command access. AI agents can run state-changing commands such as deploy, write, up, stop, and init.

Do not put a mainnet private key in MCP config unless you trust the AI client and all enabled tools.

Available Tools

4 tools

check_toolsA

Check whether node, genlayer, python, and genvm-lint are available to this MCP server.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.2/5.0

Behavior4/5

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

No annotations provided, so description carries full burden. It accurately describes a read-only check operation with no side effects. Could mention output format but adequate for simple health check.

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 sentence, front-loaded with purpose, no extraneous words. Highly concise.

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?

No output schema, but the simple check tool's behavior is largely conveyed. Could clarify what 'available' means (e.g., installed, running), but sufficiently complete for low complexity.

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

Parameters4/5

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

No parameters exist, so schema coverage is 100%. Description need not add parameter info. Baseline score of 4 is appropriate.

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?

Description clearly states it checks availability of specific tools (node, genlayer, python, genvm-lint). Verb 'Check' plus explicit list distinguishes it from sibling tools that perform actions like deploy or lint.

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?

No explicit guidance on when to use this tool versus alternatives. It is implied it should be used as a precondition check, but no direct advice or exclusion criteria are provided.

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

genlayerB

Run the GenLayer CLI with full command access. This can perform state-changing operations.

ParametersJSON Schema

Name	Required	Description
`args`	No	Arguments passed to the command.
`cwd`	No	Working directory for the command. Defaults to the MCP server cwd.
`timeoutMs`	No	Timeout in milliseconds. Defaults to 120000.
`env`	No	Extra environment variables merged over the MCP server environment.

TDQS

B3.2/5.0

Behavior3/5

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

The description notes that it 'can perform state-changing operations', which is a key behavioral trait. However, no annotations are provided, and the description lacks details on security, error handling, or resource impact.

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 very concise with two sentences, no fluff. While efficient, it could include a bit more context without becoming verbose.

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?

Given the tool's complexity (4 parameters, no output schema, no annotations), the description is adequate but not fully complete. It does not describe return values or potential side effects beyond stating state-changing operations.

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 clear parameter descriptions. The description does not add significant meaning beyond the schema, meeting the baseline for this dimension.

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 clearly states 'Run the GenLayer CLI' with 'full command access', distinguishing it from sibling tools like genlayer_deploy and genvm_lint. However, it is somewhat broad without specifying typical commands.

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 is provided on when to use this tool versus the sibling tools. There is no mention of scenarios or alternatives, leaving the agent to infer usage.

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

genlayer_deployB

Deploy a GenLayer Intelligent Contract with genlayer-js. Accepts privateKey; generates one when missing or invalid.

ParametersJSON Schema

Name	Required	Description	Default
`contractPath`	Yes	Path to the Intelligent Contract source file.
`privateKey`	No	GenLayer private key. If missing or invalid, a new private key is generated with genlayer-js.
`args`	No	Constructor arguments passed to deployContract.
`kwargs`	No	Keyword constructor arguments passed to deployContract.
`rpcUrl`	No	Custom GenLayer RPC endpoint.
`chain`	No	GenLayer chain used when creating the SDK client.	localnet
`cwd`	No	Base directory for resolving contractPath. Defaults to MCP server cwd.
`leaderOnly`	No
`consensusMaxRotations`	No
`initializeConsensus`	No
`autoFundLocalnet`	No	Call localnet sim_fundAccount before deploy. Only works on localnet.
`fundAmount`	No
`waitForReceipt`	No
`receiptStatus`	No		ACCEPTED
`receiptRetries`	No
`receiptIntervalMs`	No
`timeoutMs`	No
`exposePrivateKey`	No	Return the generated/used private key in output. Defaults false to avoid leaking secrets.

TDQS

B3.2/5.0

Behavior2/5

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

In the absence of annotations, the description bears full responsibility for disclosing behavioral traits. It mentions the key generation fallback for privateKey but fails to disclose other significant behaviors such as error handling, side effects, or return value structure. This is insufficient for an 18-parameter tool.

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?

The description is extremely concise: two short sentences that front-load the core purpose and immediately add an important behavioral note. Every word earns its place.

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 the tool's complexity (18 optional parameters, one required), the description is far from complete. It lacks information about error handling, output structure, behavior of optional parameters, or any post-deployment steps. An output schema would help, but it is absent.

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 50%, so the baseline is 3. The description adds value by explaining the privateKey fallback behavior beyond the schema. However, it does not compensate for the remaining 50% of parameters that lack schema descriptions, resulting in only marginal improvement.

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 it deploys a GenLayer Intelligent Contract using genlayer-js, which is a specific verb-resource combination. It distinguishes itself from sibling tools like check_tools, genlayer, and genvm_lint, which serve different purposes.

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?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or context for usage. It only describes the action without any contextual usage advice.

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

genvm_lintC

Run genvm-lint for GenVM contract linting, validation, schema extraction, typechecking, setup, or downloads.

ParametersJSON Schema

Name	Required	Description
`args`	No	Arguments passed to the command.
`cwd`	No	Working directory for the command. Defaults to the MCP server cwd.
`timeoutMs`	No	Timeout in milliseconds. Defaults to 120000.
`env`	No	Extra environment variables merged over the MCP server environment.

TDQS

C2.5/5.0

Behavior2/5

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

No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits like side effects (e.g., file modifications, network requests), error handling, or required permissions. The description does not elaborate on what the tool does beyond running a command.

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

Conciseness3/5

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

The description is a single sentence, which is concise but lacks structure and prioritization. It lists multiple functions without highlighting the primary use case. It could be more efficiently organized.

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?

For a tool that runs a command, it is critical to mention that it returns stdout/stderr or exit code. No output schema is provided, and the description does not explain what the tool returns. Important behavioral context is missing, making it incomplete for an AI agent.

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?

The input schema has 100% description coverage, so the schema already documents the parameters (args, cwd, timeoutMs, env). The description adds no extra meaning beyond what the schema provides. Baseline score of 3 is appropriate.

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

Purpose3/5

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

The description states that the tool runs genvm-lint for various tasks like linting, validation, schema extraction, etc., but it lists multiple purposes without a clear single focus. The verb 'Run' is generic and does not distinguish this tool from sibling tools like 'genlayer' or 'genlayer_deploy'.

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 is provided on when to use this tool versus alternatives, such as 'check_tools' or 'genlayer'. There is no mention of prerequisites, limitations, or context in which this tool is appropriate.

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. Dates show when Glama detected each change.

4 tool updatesv0.1.0May 3, 2026
- First observedcheck_tools
- First observedgenlayer
- First observedgenlayer_deploy
- First observedgenvm_lint

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.3/5.0

Disambiguation5/5

Each tool targets a clearly distinct function: checking environment availability, running arbitrary CLI commands, deploying contracts, and linting. No overlap in purpose.

Naming Consistency3/5

Tool names are inconsistent: 'check_tools' uses verb_noun, 'genlayer' is a single word, 'genlayer_deploy' and 'genvm_lint' use prefix_verb pattern. Mixed conventions reduce predictability.

Tool Count4/5

Four tools is reasonable for a CLI wrapper server, covering core operations without being too few or excessive.

Completeness4/5

The set covers essential actions: environment check, CLI execution, deployment, and linting. Missing other possible genlayer commands, but core workflow is covered.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

microservices.sh
sh.microservices
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Cloud Platforms Agent Orchestration Developer Tools
21
mcp-serverOAuth
com.niftypm
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Project Management Communication File Systems
2
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
agentwork-mcp A
io.github.ferm-ai
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Agent Orchestration Autonomous Agents App Automation
2

Related MCP Servers

OpenZeppelin Contracts MCPofficial
Blockchain Code Execution Autonomous Agents
OpenZeppelin
A
license
A
quality
A
maintenance
A Model Context Protocol (MCP) server that allows AI agents to generate smart contracts using OpenZeppelin Contracts libraries.
Updated 2 days ago (2026-09-04 18:02 UTC)
33
465
294
AGPL 3.0
MCP Plus
Developer Tools Autonomous Agents Code Analysis
David3u
F
license
Not graded
quality
D
maintenance
A lightweight MCP server that enhances AI agents with tools for codebase analysis, task delegation to sub-agents, multi-agent coordination through chatrooms, and project todo management.
Updated 8 months ago (2026-01-14 03:05 UTC)
-
GenLayer MCP Server
Blockchain Web3 & Decentralized Tech AI & Machine Learning
albert-mr
A
license
A
quality
C
maintenance
A comprehensive MCP server for generating sophisticated GenLayer Intelligent Contracts with AI-native blockchain capabilities.
Updated 8 months ago (2025-12-30 10:34 UTC)
16
17
7
MIT
genskill-mcp
Blockchain Web3 & Decentralized Tech Developer Tools
Jr-kenny
A
license
A
quality
C
maintenance
An MCP server that lets AI agents build on GenLayer by searching documentation, inspecting contracts and transactions over RPC, and scaffolding, linting, and testing Intelligent Contracts.
Updated a month ago (2026-07-29 11:38 UTC)
46
20
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/ngh1105/genlayer-cli-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

GenLayer CLI MCP

Requirements

MCP Config

Local Development

Tools

check_tools

genlayer

genvm_lint

genlayer_deploy

Agent Setup Examples

Codex

Antigravity

Claude Code

Security

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

OpenZeppelin Contracts MCPofficial

Latest Blog Posts

MCP directory API

`check_tools`

`genlayer`

`genvm_lint`

`genlayer_deploy`