How do I use Tool Box MCP Server?

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., "@Tool Box MCP Server find tools for data analysis and excel export" 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.

Tool Box MCP Server

by Adriftnote

Overview Schema Related Servers Score Discussions

TypeScript

Local

Tool Box MCP Server

Central registry for AI tools with Vector Search + Knowledge Graph for intelligent tool discovery and chaining.

Features

Vector Search: Semantic tool discovery via ChromaDB
Knowledge Graph: Tool relationships and dependency traversal
Tool Chaining: Execute multi-step MCP tool pipelines with data transformations
Progressive Disclosure: Load only what's needed, 90%+ token savings
Unified Registry: MCP Servers, Skills, Tools, Commands in one place

Related MCP server: executor

Quick Start

# Clone
git clone https://github.com/Adriftnote/tool-box-mcp.git
cd tool-box-mcp

# Install dependencies
npm install

# Run setup (initializes ChromaDB and sample data)
./scripts/setup.sh

# Start server
npm start

Tools (11 total)

Tool	Description
`toolhub_search`	Find tools by natural language query
`toolhub_expand`	Explore tool dependencies via Knowledge Graph
`toolhub_cluster`	Get complete tool set for a task
`toolhub_register`	Add new tools to registry
`toolhub_delete`	Remove tools from registry
`toolhub_list`	List all registered tools
`toolhub_execute`	Auto-generate and execute chain from query
`toolhub_chain`	Execute sequential MCP tool pipeline
`toolhub_prepare_chain`	Analyze chain before execution (schemas, skills, transforms)
`toolhub_discover`	Refresh chainable tools from MCP servers
`toolhub_chainable`	List tools available for chaining

Installation

Prerequisites

Node.js 18+
Python 3.8+ (for ChromaDB)
pip (Python package manager)

Step 1: Clone and Install

git clone https://github.com/Adriftnote/tool-box-mcp.git
cd tool-box-mcp
npm install

Step 2: Run Setup

# This installs Python dependencies and initializes ChromaDB
./scripts/setup.sh

Step 3: Configure MCP Client

Add to your Claude Code or MCP client settings:

{
  "mcpServers": {
    "tool-box": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/tool-box-mcp/dist/index.js"]
    }
  }
}

Configuration

Data Files

After installation, configure these files in the data/ directory:

File	Purpose
`mcp-config.json`	MCP servers to chain with
`knowledge-graph.json`	Tool relationships
`chromadb/`	Vector search database

Environment Variables (Optional)

Override default paths with environment variables:

TOOLHUB_GRAPH_PATH       # Knowledge Graph JSON path
TOOLHUB_MCP_CONFIG       # MCP config path
TOOLHUB_PYTHON_PATH      # Python interpreter path

Usage Examples

1. Search Tools

toolhub_search({
  query: "data analysis excel",
  limit: 10,
  include_graph: true
})

2. Execute Tool Chain

toolhub_chain({
  mcpPath: [
    {
      toolName: "sqlite_read_query",
      toolArgs: "{\"query\": \"SELECT * FROM metrics LIMIT 10\"}",
      outputTransform: "sqlite→2d"
    },
    {
      toolName: "document_create_excel",
      toolArgs: "{\"filepath\": \"/tmp/report.xlsx\", \"content\": \"CHAIN_RESULT\"}"
    }
  ]
})

3. Register New Tool

toolhub_register({
  name: "my-mcp-server",
  type: "MCP_Server",
  description: "My custom MCP server for data processing"
})

Architecture

┌─────────────────────────────────────────────┐
│  Claude Code / AI Agent                     │
└─────────────────────────────────────────────┘
                    │ MCP Call
                    ▼
┌─────────────────────────────────────────────┐
│  Tool Box MCP Server                        │
│  ┌─────────────────────────────────────┐   │
│  │ HybridSearchService                 │   │
│  │ ├─ VectorSearchService (ChromaDB)   │   │
│  │ └─ GraphSearchService (JSON)        │   │
│  ├─────────────────────────────────────┤   │
│  │ ToolDiscoveryService                │   │
│  │ └─ Chain Execution + Transforms     │   │
│  └─────────────────────────────────────┘   │
└─────────────────────────────────────────────┘
         │                    │
         ▼                    ▼
┌───────────────┐    ┌───────────────┐
│  ChromaDB     │    │  Knowledge    │
│  (data/)      │    │  Graph JSON   │
└───────────────┘    └───────────────┘

Data Transforms

Built-in transforms for chain data flow:

Transform	Description
`sqlite→2d`	SQLite results to 2D array
`json→object`	Parse JSON string to object
`object→array`	Wrap object in array
`flatten`	Flatten nested arrays
`first`	Extract first element
`keys`	Get object keys
`values`	Get object values

Development

# Build from source
npm run build

# Run server
npm start

# Type check
npm run typecheck

Project Structure

tool-box-mcp/
├── dist/                 # Compiled JavaScript (included)
├── src/
│   ├── index.ts          # Main server entry
│   ├── schemas/          # Zod input schemas
│   └── services/         # Search, chain, transform services
├── scripts/
│   ├── setup.sh          # Initial setup script
│   └── register-tool.py  # Tool registration utility
├── data/
│   ├── chromadb/         # Vector database
│   ├── knowledge-graph.json
│   └── mcp-config.json
└── package.json

Troubleshooting

"ChromaDB not found"

pip install chromadb sentence-transformers

"Python not found"

Set the Python path:

export TOOLHUB_PYTHON_PATH=/usr/bin/python3

"No tools found"

Run setup to initialize sample data:

./scripts/setup.sh

License

ISC

Available Tools

4 tools

toolhub_clusterGet Tool ClusterA

Read-onlyIdempotent

Get a complete tool cluster for a task query.

This combines vector search and graph expansion to return a complete set of tools needed for a task. Includes primary tools (semantic matches) and their dependencies (graph expansion), plus usage context.

Args:

query (string): Natural language task description
include_context (boolean): Include usage patterns and examples (default: true)
response_format ('json' | 'markdown'): Output format

Returns: { "primary": [ { "name": "n8n-workflow-builder", "type": "MCP_Server", ... } ], "dependencies": [ { "name": "n8n-node-templates", "type": "Skill", ... } ], "context": { "usagePatterns": ["Use MCP servers for data operations", ...], "examples": ["Primary workflow: n8n-workflow-builder - ...", ...] }, "stats": { "totalTools": 7, "tokenEstimate": 7000, "savingsPercent": 92.1 } }

Use this tool for complete task setup - returns everything needed to start working.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Natural language query to find a complete tool cluster
`include_context`	No	Whether to include usage context and examples
`response_format`	No	Output format	json

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral context by explaining that the tool returns a complete set of tools including primary and dependencies, and provides a sample output structure. No contradictions with annotations.

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 concise and well-structured: a one-sentence title, a brief explanation of how it works, then clearly labelled Args and Returns sections. Every sentence adds value with no redundancy.

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

Completeness5/5

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

The tool has three parameters with full schema coverage, and the description provides a detailed output example including fields like primary, dependencies, context, and stats. Although no output schema exists, the example sufficiently describes the return value for an agent to use the tool correctly.

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 repeats parameter definitions with slight elaboration (e.g., 'Natural language task description' for query). Since schema already provides descriptions, the description adds marginal value. Baseline 3 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?

The description clearly states the tool's purpose: 'Get a complete tool cluster for a task query.' It explains it combines vector search and graph expansion to return primary tools, dependencies, and context. This distinguishes it from siblings like toolhub_search (likely semantic matches only) and toolhub_expand (graph expansion on a single tool).

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 explicitly says 'Use this tool for complete task setup - returns everything needed to start working.' This gives clear guidance on when to use it, but does not explicitly mention when not to use it or compare with alternatives beyond the description of what it returns.

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

toolhub_expandExpand Tool GraphA

Read-onlyIdempotent

Expand a tool to find its dependencies via Knowledge Graph.

Given a tool name, traverse the Knowledge Graph to find related tools, requirements, and dependencies. Useful for understanding what other tools are needed to complete a task.

Args:

tool_name (string): Name of the tool to expand (e.g., 'n8n-workflow-builder')
depth (number): Traversal depth (default: 2, max: 4)
relation_types (string[]): Filter by relation types (optional)
response_format ('json' | 'markdown'): Output format

Relation types:

REQUIRES: Tool A requires Tool B to function
WORKS_WITH: Tools that commonly work together
EXECUTABLE_VIA: Tool can be executed via another tool
OUTPUTS_TO: Tool outputs data to another tool
BENEFITS_FROM: Tool benefits from using another tool

Returns: { "tool": "n8n-workflow-builder", "dependencies": [ { "name": "n8n-node-templates", "type": "Skill", "relation": "BENEFITS_FROM" } ], "totalCount": 4 }

Use this tool when you know a primary tool and need to find related tools.

ParametersJSON Schema

Name	Required	Description	Default
`depth`	No	How many levels of relationships to traverse
`tool_name`	Yes	Name of the tool to expand (e.g., 'n8n-workflow-builder')
`relation_types`	No	Filter by relationship types (e.g., ['REQUIRES', 'WORKS_WITH'])
`response_format`	No	Output format	json

TDQS

A4.6/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description adds significant behavior context: traversal depth limits (default 2, max 4), relation types (REQUIRES, WORKS_WITH, etc.), example output, and explanation of how dependencies are returned. No contradiction with annotations.

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 well-structured with sections for arguments, relation types, returns, and usage tip. It is informative but slightly verbose; could be more concise by merging the argument list with the existing schema documentation. Still, every sentence adds useful information.

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

Completeness5/5

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

Given no output schema, the description provides an example JSON response, lists all relation types, and explains the depth and filter parameters. For a tool with 4 parameters, this is sufficiently complete for an agent to understand inputs and outputs.

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?

Although schema description coverage is 100%, the description adds value by providing an example of tool_name ('n8n-workflow-builder'), explaining relation types, and showing the response format. This goes beyond the schema's basic property descriptions.

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 tool's purpose: 'Expand a tool to find its dependencies via Knowledge Graph.' It uses a specific verb ('expand') and resource ('tool'), and distinguishes itself from sibling tools like toolhub_search, toolhub_health, and toolhub_cluster by focusing on dependency discovery.

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 provides a clear usage guideline: 'Use this tool when you know a primary tool and need to find related tools.' However, it does not explicitly mention when not to use it or directly compare with alternatives, such as using toolhub_search for broader search instead of dependency traversal.

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

toolhub_healthHealth CheckA

Read-onlyIdempotent

Check Tool Hub service status.

Returns:

chromadb: Connection status to vector database
knowledgeGraph: Knowledge graph file status
toolCount: Number of registered tools
version: Server version

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?

Annotations already indicate readOnlyHint=true, destructiveHint=false. The description adds value by detailing the return fields (chromadb, knowledgeGraph, toolCount, version), providing context on what the tool checks. No contradictions with annotations.

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 concise, consisting of a brief sentence and a bullet list of return fields. Every part is informative with no wasted words.

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?

For a simple health check tool with no parameters and no output schema, the description sufficiently explains the return structure. It could mention typical use or that it's a lightweight check, but overall it is complete.

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 tool has zero parameters and schema coverage is 100%. The description does not need to add parameter meaning. A baseline score of 4 is appropriate for a parameterless tool.

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 tool checks service status and lists the returned fields. The verb 'Check' with resource 'Tool Hub service status' is specific and distinguishes from siblings like search, expand, and cluster.

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 explicitly state when to use this tool versus alternatives. However, the purpose is clear and the tool has no parameters, making it suitable as a lightweight health check. No usage caveats or exclusions are mentioned.

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

toolhub_searchSearch ToolsA

Read-onlyIdempotent

Search for relevant tools using Vector Search + Knowledge Graph.

This tool finds the most relevant MCP servers, skills, and tools for a given query. It uses semantic similarity (ChromaDB) to find matches and optionally expands results using the Knowledge Graph to include dependencies.

Args:

query (string): Natural language query (e.g., "n8n workflow automation")
limit (number): Maximum tools to return (default: 10, max: 50)
include_graph (boolean): Expand with Knowledge Graph (default: true)
response_format ('json' | 'markdown'): Output format (default: 'json')

Returns: JSON format: { "results": [ { "name": "n8n-workflow-builder", "type": "MCP_Server", "description": "Create and manage n8n workflows", "similarity": 0.89 } ], "stats": { "vectorCount": 3, "graphCount": 4, "totalCount": 7, "tokenEstimate": 7000, "savingsPercent": 92.1 } }

Examples:

"n8n 워크플로우 자동화" → n8n-workflow-builder, n8n-node-templates, ...
"TikTok 데이터 분석" → sqlite_tiktok_analytics, pandas-excel, ...
"Excel 리포트 생성" → pandas-excel, 데이터-구조-파악, ...

Use this tool when you need to find which tools are relevant for a task.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of tools to return
`query`	Yes	Natural language query to find relevant tools (e.g., 'n8n workflow automation', 'TikTok data analysis')
`include_graph`	No	Whether to expand results using Knowledge Graph relationships
`response_format`	No	Output format: 'json' for structured data or 'markdown' for human-readable	json

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds behavioral details about the search mechanism (semantic similarity via ChromaDB) and knowledge graph expansion. No contradictions with annotations.

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 well-organized with a purpose statement, args detail, and examples. While somewhat lengthy, it is front-loaded with the main purpose and each section adds value. Minor redundancy in repeating args that are in schema, but overall structure is good.

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

Completeness5/5

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

Given no output schema, the description provides a detailed example of the return format, including JSON structure and stats. It explains the mechanism (ChromaDB, KG) and covers all relevant aspects for a tool with 4 parameters and no nested objects.

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%, so baseline is 3. The description includes an 'Args' section that repeats schema information and adds examples, but does not significantly enhance understanding beyond the schema. The example return format is helpful but not required for parameter semantics.

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 tool searches for relevant tools using Vector Search and Knowledge Graph. It specifies the types of items found (MCP servers, skills, tools) and distinguishes from siblings like toolhub_expand, toolhub_health, and toolhub_cluster.

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 explicitly says 'Use this tool when you need to find which tools are relevant for a task' and provides examples. However, it does not explicitly state when not to use it or contrast with siblings, though context implies that for expansion or cluster operations different tools should be used.

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 26, 2026
- First observedtoolhub_cluster
- First observedtoolhub_expand
- First observedtoolhub_health
- First observedtoolhub_search

Install Server

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

TDQS

A4.3/5.0

Disambiguation4/5

Each tool has a clear primary function: search, expand, health, and cluster. However, toolhub_cluster combines search and graph expansion, which might cause some confusion with using search and expand separately, but descriptions clarify the distinction.

Naming Consistency4/5

All tools share the 'toolhub_' prefix, providing consistency. However, the second part mixes verbs (search, expand) and nouns (health, cluster), which is a minor deviation from an ideal verb_noun pattern.

Tool Count5/5

Four tools is well-scoped for a tool discovery server. Each tool serves a distinct and necessary purpose without unnecessary bloat.

Completeness4/5

The tool set covers the core functions: searching, expanding dependencies, health checking, and full cluster retrieval. A minor gap is the lack of a direct tool for listing all registered tools or browsing categories, but search with broad queries may partially address this.

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

Aibooma - AI Agent Registry
com.aibooma
AI agent registry — search, discover, register, and connect agents via MCP.
Agent Orchestration Search Developer Tools
2
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
Cralo
ai.cralo
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Agent Orchestration Developer Tools
1
StackResolve C
dev.stackresolve
Find, compare, and audit software for AI agents. Scored registry of tools and MCP servers.
Developer Tools
151

Related MCP Servers

@neurynae/toolcairn-mcpofficial
Search Developer Tools
neurynae
A
license
Not graded
quality
C
maintenance
MCP tool discovery for AI agents — find, compare, verify tools across 35+ registries.
Updated 2 months ago (2026-07-02 09:25 UTC)
3
MIT
executor
Agent Orchestration App Automation
UsefulSoftwareCo
A
license
Not graded
quality
A
maintenance
An integration layer for AI agents that provides a catalog of tools from various sources (OpenAPI, GraphQL, MCP, etc.) and can be used as an MCP server for compatible agents.
Updated 11 hours ago (2026-09-05 18:41 UTC)
3,623
MIT
agent-discover
Agent Orchestration Developer Tools
keshrath
A
license
Not graded
quality
F
maintenance
MCP server registry and marketplace that enables dynamic discovery, installation, and activation of tools at runtime, allowing AI agents to use new tools without restarting.
Updated 5 months ago (2026-04-19 17:51 UTC)
126
7
MIT
Smart MCP Proxy
Agent Orchestration Search
Dumbris
A
license
Not graded
quality
D
maintenance
Federating gateway for AI agents to discover and call tools from multiple MCP servers with intelligent search and dynamic tool registration.
Updated a year ago (2025-07-22 17:46 UTC)
39
MIT

Appeared in Searches

A server for finding all available tools

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/Adriftnote/tool-box-mcp'

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

Tool Box MCP Server

Features

Quick Start

Tools (11 total)

Installation

Prerequisites

Step 1: Clone and Install

Step 2: Run Setup

Step 3: Configure MCP Client

Configuration

Data Files

Environment Variables (Optional)

Usage Examples

1. Search Tools

2. Execute Tool Chain

3. Register New Tool

Architecture

Data Transforms

Development

Project Structure

Troubleshooting

"ChromaDB not found"

"Python not found"

"No tools found"

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

@neurynae/toolcairn-mcpofficial

Appeared in Searches

Latest Blog Posts

MCP directory API