Which integrations are available for this server?

Allows interaction with Ollama for running local LLM models, enabling AI agents to leverage locally-hosted language models.

How do I use Agent Factory 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., "@Agent Factory MCP Register ollama as a local LLM agent for local inference." 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.

Agent Factory MCP

by utenadev

Overview Schema Related Servers Score Discussions

TypeScript

Local

Agent Factory MCP

License: MIT Open Source

A universal Model Context Protocol (MCP) server that automatically discovers and registers CLI tools as MCP tools. Transform any CLI tool (Qwen, Ollama, Aider, etc.) into an AI-powered agent with persona configuration.

Features

Auto-Discovery: Automatically parse CLI --help output to generate tool metadata
Zero-Code Registration: Register tools via config file or command-line arguments
Persona Support: Configure system prompts to create specialized AI agents
Multi-Provider: Use multiple AI tools simultaneously (Qwen, Gemini, Aider, etc.)
Runtime Registration: Add new tools dynamically via MCP protocol

Related MCP server: AutoMCP

Architecture

graph TB
    subgraph "MCP Client"
        A[Claude Desktop / Claude Code]
    end

    subgraph "Agent Factory MCP Server"
        B[Server Entry Point]
        C[Config Loader]
        D[Tool Registry]
        E[Dynamic Tool Factory]

        subgraph "Providers"
            F[QwenProvider]
            G[GenericCliProvider]
        end

        subgraph "Parsers"
            H[HelpParser]
        end
    end

    subgraph "CLI Tools"
        I[qwen]
        J[gemini]
        K[aider]
        L[ollama]
        M[...any CLI tool]
    end

    A -->|stdio| B
    B --> C
    B -->|CLI args| G
    C -->|load config| D
    G -->|create| D
    D --> E
    E -->|generate| F
    F -->|execute| I
    F -->|execute| J
    F -->|execute| K
    G -->|parse --help| H
    H -->|metadata| G

State Transition

stateDiagram-v2
    [*] --> Initialization

    Initialization --> LoadConfig: Start
    Initialization --> ProcessCLIArgs: CLI args provided

    LoadConfig --> ProcessCLIArgs: Config loaded
    ProcessCLIArgs --> RegisterProviders

    RegisterProviders --> ProviderCreated: Tool available
    RegisterProviders --> ProviderSkipped: Tool not found

    ProviderCreated --> GenerateTools
    ProviderSkipped --> RegisterProviders: Next tool

    GenerateTools --> ToolRegistered
    ToolRegistered --> RegisterProviders: Next tool

    RegisterProviders --> ServerRunning: All tools processed
    ServerRunning --> [*]: Ready for MCP requests

    ServerRunning --> RuntimeRegistration: register_cli_tool called
    RuntimeRegistration --> ServerRunning: Tool added

    note right of LoadConfig
        Loads ai-tools.json
        or .qwencoderc.json
    end note

    note right of ProcessCLIArgs
        Parses CLI args like:
        npx agent-factory-mcp qwen gemini aider
    end note

Installation

# Install via npm
npm install -g agent-factory-mcp

# Or use with npx without installation
npx agent-factory-mcp

# Or use with bun
bunx agent-factory-mcp

Configuration

Method 1: Command-Line Arguments

npx agent-factory-mcp qwen gemini aider

Method 2: Configuration File

Create ai-tools.json in your project root:

{
  "$schema": "./schema.json",
  "version": "1.0",
  "tools": [
    {
      "command": "qwen",
      "alias": "code-reviewer",
      "description": "Code review expert focusing on security and performance",
      "systemPrompt": "You are a senior code reviewer. Focus on security vulnerabilities, performance issues, and maintainability."
    },
    {
      "command": "qwen",
      "alias": "doc-writer",
      "description": "Technical documentation specialist",
      "systemPrompt": "You write clear, concise technical documentation for developers."
    }
  ]
}

Method 3: Runtime Registration

Use the register_cli_tool MCP tool:

register_cli_tool({
  command: "ollama",
  alias: "local-llm",
  description: "Run local LLM models via Ollama",
  systemPrompt: "You are a helpful AI assistant running locally.",
  persist: true
})

MCP Client Setup

Claude Desktop

Add to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-factory": {
      "command": "npx",
      "args": ["agent-factory-mcp", "qwen", "gemini", "aider"]
    }
  }
}

Claude Code CLI

claude mcp add agent-factory -- npx agent-factory-mcp qwen gemini aider

Usage Examples

Using Specialized Agents

# Code review with security focus
"Use code-reviewer to analyze this file for security issues"

# Documentation generation
"Ask doc-writer to generate API docs for this module"

# General AI assistance
"Use ask-qwen to explain this code"

Multiple AI Tools

# Use different AIs for different tasks
"Use gemini-vision to analyze this screenshot"
"Use aider to refactor this function"
"Use qwen to review the changes"

Configuration Schema

See schema.json for the full configuration schema:

Field	Type	Required	Description
`command`	string	✅	CLI command to register (e.g., "qwen", "ollama")
`enabled`	boolean	❌	Whether the tool is enabled (default: true)
`alias`	string	❌	Custom tool name (default: "ask-{command}")
`description`	string	❌	Custom tool description
`systemPrompt`	string	❌	System prompt for AI persona
`providerType`	string	❌	Provider type: "cli-auto" or "custom"
`defaultArgs`	object	❌	Default argument values

Development

# Install dependencies
bun install

# Build
bun run build

# Run tests
bun test

# Type check
bun run type-check

# Lint
bun run lint

# Format
bun run format

Project Structure

agent-factory-mcp/
├── src/
│   ├── index.ts              # Server entry point
│   ├── constants.ts          # Constants
│   ├── providers/            # Provider implementations
│   │   ├── base-cli.provider.ts
│   │   ├── generic-cli.provider.ts
│   │   └── qwen.provider.ts
│   ├── tools/                # Tool registry and factory
│   │   ├── registry.ts
│   │   ├── dynamic-tool-factory.ts
│   │   └── simple-tools.ts
│   ├── parsers/              # CLI help parser
│   │   └── help-parser.ts
│   ├── types/                # TypeScript types
│   │   └── cli-metadata.ts
│   └── utils/                # Utilities
│       ├── configLoader.ts
│       ├── commandExecutor.ts
│       ├── logger.ts
│       └── progressManager.ts
├── test/                     # Test files
├── ai-tools.json.example     # Example configuration
├── schema.json               # JSON schema
└── Taskfile.yml              # Task runner configuration

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see LICENSE for details.

Available Tools

4 tools

ask-qwenA

Execute Qwen AI to get responses. Supports model selection.

ParametersJSON Schema

Name	Required	Description	Default
`model`	No	Optional model to use (e.g., 'qwen-max', 'qwen-long'). If not specified, uses the default model.
`prompt`	Yes	Analysis request. Use @ syntax to include files (e.g., '@largefile.js explain what this does') or ask general questions

TDQS

A3.6/5.0

Behavior2/5

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

No annotations are provided, so the description must fully convey behavioral traits. It only states 'get responses' and 'supports model selection,' lacking details on side effects, authentication, rate limits, or synchronous/asynchronous behavior.

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 short and to the point, with two sentences that waste no words. It is appropriately front-loaded.

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 (2 parameters, no nested objects, no output schema), the description is mostly complete. It could mention the return type, but the phrase 'get responses' gives adequate context.

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%, and the description merely restates that model selection is supported without adding new meaning. It does not clarify parameter usage beyond what the schema already provides.

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 that the tool executes Qwen AI to get responses, which is a specific verb-resource pair. It distinguishes well from sibling tools like Ping, Help, and register_cli_tool, 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 Guidelines3/5

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

The description does not provide explicit guidance on when to use this tool versus alternatives. Usage is implied by the name and description, but no when-not or context is given.

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

HelpA

Shows the QwenCode help text

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.8/5.0

Behavior4/5

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

The description discloses that the tool displays help text, which is a read-only, non-destructive operation. No annotations are provided, but the description is sufficient for such a simple tool, though it could mention that no modifications are made.

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, very concise with no wasted words. However, it could be slightly more descriptive about the content of the help text, earning a 5 only if it were more informative.

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 (no parameters, no output schema, no annotations), the description is adequately complete. It states the tool's purpose clearly, and no further details are necessary for an AI agent to use it correctly.

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?

The input schema has zero parameters, so schema coverage is 100%. The description adds no parameter information, which is acceptable since there are none. The baseline score of 4 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 clearly states that the tool shows the QwenCode help text, using a specific verb and resource. It does not provide additional context to differentiate from siblings, but the name 'Help' is self-explanatory and no sibling serves the same purpose.

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 is provided. The context is implied due to the tool's standard role, but the description lacks any mention of when-not-to-use or alternative tools.

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

PingB

A simple test tool that echoes back a message

ParametersJSON Schema

Name	Required	Description	Default
`message`	No	Optional message to echo back

TDQS

B3.2/5.0

Behavior2/5

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

No annotations exist, so the description must cover behavior. It states only 'echoes back a message' but does not clarify side effects (likely none), behavior when no message is provided, or response format. Minimal transparency.

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 with no wasted words. It is concise but could benefit from slight expansion without losing brevity.

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 one optional param and no output schema, the description is minimally adequate. It does not explain return values, which would improve completeness given no output schema.

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 covers the single optional parameter with 100% description coverage. The description adds no extra meaning beyond 'optional message to echo back', so baseline 3 applies.

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 the tool 'echoes back a message', indicating a test/echo function. It distinguishes from siblings like Help (likely documentation) and ask-qwen (Q&A) but does not explicitly contrast.

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 use as a connectivity test but provides no explicit guidance on when to use versus alternatives (e.g., Help for docs, register_cli_tool for registration). No when-not or context provided.

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

register_cli_toolA

Dynamically register a CLI tool as an MCP tool. The tool must be available in PATH.

ParametersJSON Schema

Name	Required	Description
`alias`	No	Optional alias for the tool (defaults to 'ask-{command}')
`command`	Yes	The CLI command to register (e.g., 'ollama', 'git')
`persist`	No	Whether to save to ai-tools.json (default: false)
`description`	No	Custom description for the tool
`systemPrompt`	No	System prompt for AI agent persona configuration

TDQS

A3.5/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It mentions dynamic registration but does not disclose side effects, permissions, or potential conflicts. The description is insufficient for a mutation tool.

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, concise sentence that efficiently conveys the core purpose and a key condition. It is front-loaded and contains no unnecessary words.

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?

With 5 parameters, no output schema, and no annotations, the description is too minimal. It does not explain what 'registering' entails, the effect on the environment, or what the tool returns, leaving significant gaps 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?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds no additional 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.

Purpose5/5

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

The description clearly states the action ('register') and the resource ('CLI tool as an MCP tool'), and includes a prerequisite. Sibling tools are distinctly different, so no confusion.

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

Usage Guidelines4/5

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

The description explains when to use the tool (to register a CLI tool) and notes a key requirement (must be in PATH). However, it does not provide explicit when-not-to-use scenarios or alternative tools, though siblings are unrelated.

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 updatesv1.0.0Jul 30, 2026
- First observedask-qwen
- First observedHelp
- First observedPing
- First observedregister_cli_tool

Install Server

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

TDQS

B3.4/5.0

Disambiguation5/5

Each tool serves a distinct purpose: Ping for connectivity testing, Help for documentation, register_cli_tool for dynamic tool registration, and ask-qwen for AI queries. No overlap exists.

Naming Consistency2/5

Tool names use inconsistent conventions: Ping and Help are capitalized and single words, register_cli_tool is lowercase snake_case, and ask-qwen uses a lowercase dash. No clear pattern.

Tool Count5/5

With only 4 tools, the set is well-scoped for a lightweight toolkit combining testing, help, registration, and AI query capabilities. Not excessive or insufficient.

Completeness2/5

Given the server name 'Agent Factory MCP', the tool surface is incomplete—missing basic agent management operations like list, delete, or update agents. The current tools do not form a coherent factory workflow.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

GitHub Repository

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

Anagent A
io.github.jaytahir
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Agent Orchestration Developer Tools
21
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
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
strata
ai.klavis
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Agent Orchestration Autonomous Agents Developer Tools
25,748

Related MCP Servers

mcp-cli-catalog
Shell Access
abcpro1
A
license
Not graded
quality
D
maintenance
An MCP server that publishes CLI tools on your machine for discoverability by LLMs
Updated 10 months ago (2025-11-16 20:50 UTC)
14
1
MIT
AutoMCP
Developer Tools Command Line Agent Orchestration
rh-rahulshetty
A
license
Not graded
quality
D
maintenance
Automatically converts CLI tools, APIs, and programs into MCP servers for LLM and agentic use, enabling rapid integration without manual server implementation.
Updated a year ago (2025-07-30 12:27 UTC)
1
MIT
Forage MCP Server
Autonomous Agents Developer Tools
isaac-levine
A
license
Not graded
quality
D
maintenance
An MCP server that enables AI agents to automatically discover, install, and learn to use new tools without manual configuration.
Updated 6 months ago (2026-02-21 23:02 UTC)
52
16
MIT
wrapmcp
Shell Access Command Line
SubZtep
A
license
Not graded
quality
C
maintenance
Universal MCP server that wraps any CLI tool, enabling AI assistants to run commands via natural language.
Updated 3 months ago (2026-06-08 02:02 UTC)
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/utenadev/qwencode-mcp-server'

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