Skip to main content
Glama
mustafa-can

Node.js MCP Server

by mustafa-can
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

MAIN ASPECTS

The ai is not human, we should simplify it and we can make it understand the prompt clearly for some regular tasks. Managing human behavior is not easy. We should not let the ai to behave like a human and to make the prompt processing difficult. We should let the ai to do its job and to make it understand the prompt clearly in regular cases. We must reduce the token usage. Otherwise it will be expensive.

Node.js MCP Server

A specialized MCP server focused on 3 Core Jobs for agentic workflows.

The 3 Jobs

1. Context Management & Learning

The agent can manage the project's documentation and "learn" the entire context.

  • Tool: md

  • Actions:

    • read_all: Reads README.md from the specified path.

    • update_all: Overwrites/updates README.md with new content provided by the client.

    • Arguments:

      • path (string, optional) - Absolute path to project root.

      • content (string, required for update_all) - The new content for README.md.

2. Test Management

The agent can manage the project's tests in a unified workflow.

  • Tool: test

  • Action: test

  • Functionality:

    1. Writes the provided test code to test_path.

    2. Runs the project's test suite (npm test).

    3. Reports output and errors to test.md.

  • Arguments:

    • path (string, optional) - Absolute path to project root.

    • test_path (string, required) - Relative path to the test file (e.g., tests/api.test.js).

    • code (string, required) - Content of the test file.

3. Build & Run

  • Tool: deploy

  • Actions:

    • dev: Runs the project in development mode.

    • prod: Builds the project and runs it.

    • Arguments:

      • path (string, optional) - Absolute path to project root.

Related MCP server: MCP Playground Server

Installation & Usage

1. Build the Server

cd /home/mc/Desktop/mcpserver
npm install
npm run build

2. Configuration (Claude / Antigravity)

Add to your MCP configuration file:

Location: ~/.config/Claude/claude_desktop_config.json (Linux)

{
  "mcpServers": {
    "job-server": {
      "command": "node",
      "args": ["path/to/mcpserver/dist/index.js"]
    }
  }
}
{
  "mcpServers": {
    "my-job-server": {
      "command": "node",
      "args": ["path/to/mcpserver/dist/index.js"]
    }
  }
}

3. Usage Examples

Manage Tests

To create a test, update it, or simply run existing tests (by re-submitting the code), use the test tool.

{
  "name": "test",
  "arguments": {
    "action": "test",
    "path": "path/to/ServiceApp",
    "test_path": "tests/login.test.js",
    "code": "describe('Login', () => { ... });"
  }
}

The server will:

  1. Save tests/login.test.js.

  2. Run npm test.

  3. Report full results to test.md.

Troubleshooting

  • Path Issues: Always provide the path argument.

  • npm test: The test action requires a valid test script in the project's package.json.

Available Tools

2 tools
calculateD
ParametersJSON Schema
NameRequiredDescriptionDefault
operationYesThe operation to perform
aYesThe first number
bYesThe second number

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

get_system_infoD
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

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

TDQS

D1.5/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: 'calculate' likely performs mathematical or computational operations, while 'get_system_info' retrieves system-related data. There is no overlap or ambiguity between these functions, making them easy for an agent to differentiate.

Naming Consistency2/5

The naming is inconsistent: 'calculate' uses a bare verb with no noun, while 'get_system_info' follows a verb_noun pattern. This mixing of conventions lacks a predictable pattern, though the names are still readable.

Tool Count2/5

With only 2 tools, this server feels too thin for a general-purpose Node.js domain, which typically involves many operations like file handling, networking, or process management. The count is insufficient to cover the implied scope effectively.

Completeness1/5

The tool surface is severely incomplete for a Node.js server, lacking basic operations such as file I/O, module management, or process control. The two tools provided do not offer meaningful coverage, leaving significant gaps that will cause agent failures.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

Related MCP Servers

Latest Blog Posts

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/mustafa-can/mcpserver'

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