shariqriazz/vertex-ai-mcp-server

4.1

ai_chatbot developer_tools research_and_data file_systems

vertex-ai-mcp-server is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.

If you are the rightful owner of vertex-ai-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This project implements a Model Context Protocol (MCP) server that provides a comprehensive suite of tools for interacting with Google Cloud's Vertex AI Gemini models, focusing on coding assistance and general query answering.

Try vertex-ai-mcp-server with chat:

answer_query_websearch

Answers a natural language query using the configured Vertex AI model (gemini-2.0-flash) enhanced with Google Search results for up-to-date information. Requires a 'query' string.

Try it

Result:

answer_query_direct

Answers a natural language query using only the internal knowledge of the configured Vertex AI model (gemini-2.0-flash). Does not use web search. Requires a 'query' string.

Try it

Result:

explain_topic_with_docs

Provides a detailed explanation for a query about a specific software topic by synthesizing information primarily from official documentation found via web search. Focuses on comprehensive answers, context, and adherence to documented details. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'topic' and 'query'.

Try it

Result:

get_doc_snippets

Provides precise, authoritative code snippets or concise answers for technical queries by searching official documentation. Focuses on delivering exact solutions without unnecessary explanation. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'topic' and 'query'.

Try it

Result:

generate_project_guidelines

Generates a structured project guidelines document (e.g., Markdown) based on a specified list of technologies and versions (tech stack). Uses web search to find the latest official documentation, style guides, and best practices for each component and synthesizes them into actionable rules and recommendations. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'tech_stack'.

Try it

Result:

read_file_content

Read the complete contents of one or more files from the workspace filesystem. Provide a single path string or an array of path strings. Handles various text encodings and provides detailed error messages if a file cannot be read. Failed reads for individual files in an array won't stop the entire operation when multiple paths are provided.

Try it

Result:

write_file_content

Create new files or completely overwrite existing files in the workspace filesystem. The 'writes' argument should be either a single object with 'path' and 'content', or an array of such objects to write multiple files. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding.

Try it

Result:

edit_file_content

Make line-based edits to a text file in the workspace filesystem. Each edit attempts to replace an exact match of 'oldText' with 'newText'. If no exact match is found, it attempts a line-by-line match ignoring leading/trailing whitespace. Indentation of the first line is preserved, and relative indentation of subsequent lines is attempted. Returns a git-style diff showing the changes made (or previewed if dryRun is true).

Try it

Result:

list_directory_contents

Get a detailed listing of all files and directories directly within a specified path in the workspace filesystem. Results clearly distinguish between files and directories with [FILE] and [DIR] prefixes. This tool is essential for understanding directory structure and finding specific files within a directory. Does not list recursively.

Try it

Result:

get_directory_tree

Get a recursive tree view of files and directories within the workspace filesystem as a JSON structure. Each entry includes 'name', 'type' (file/directory), and 'children' (an array) for directories. Files have no 'children' array. The output is formatted JSON text. Useful for understanding the complete structure of a project directory.

Try it

Result:

move_file_or_directory

Move or rename files and directories within the workspace filesystem. Can move items between directories and rename them in a single operation. If the destination path already exists, the operation will likely fail (OS-dependent).

Try it

Result:

search_filesystem

Recursively search for files and directories within the workspace filesystem matching a pattern in their name. Searches through all subdirectories from the starting path. The search is case-insensitive and matches partial names. Returns full paths (relative to workspace) to all matching items. Supports excluding paths using glob patterns.

Try it

Result:

get_filesystem_info

Retrieve detailed metadata about a file or directory within the workspace filesystem. Returns comprehensive information including size (bytes), creation time, last modified time, last accessed time, type (file/directory), and permissions (octal string). This tool is perfect for understanding file characteristics without reading the actual content.

Try it

Result:

execute_terminal_command

Execute a shell command on the server's operating system. Allows specifying the command, an optional working directory (cwd), and an optional timeout in seconds. Returns the combined stdout and stderr output of the command upon completion or termination.

Try it

Result:

save_generate_project_guidelines

Generates comprehensive project guidelines based on a tech stack using web search and saves the result to a specified file path. Uses the configured Vertex AI model (gemini-2.0-flash). Requires 'tech_stack' and 'output_path'.

Try it

Result:

save_doc_snippet

Provides precise code snippets or concise answers for technical queries by searching official documentation and saves the result to a file. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'topic', 'query', and 'output_path'.

Try it

Result:

save_topic_explanation

Provides a detailed explanation for a query about a specific software topic using official documentation found via web search and saves the result to a file. Uses the configured Vertex AI model (gemini-2.0-flash). Requires 'topic', 'query', and 'output_path'.

Try it

Result:

save_answer_query_direct

Answers a natural language query using only the internal knowledge of the configured Vertex AI model (gemini-2.0-flash), does not use web search, and saves the answer to a file. Requires 'query' and 'output_path'.

Try it

Result:

save_answer_query_websearch

Answers a natural language query using Google Search results and saves the answer to a file. Uses the configured Vertex AI model (gemini-2.0-flash). Requires 'query' and 'output_path'.

Try it

Result:

code_analysis_with_docs

Analyzes code snippets by comparing them with best practices from official documentation found via web search. Identifies potential bugs, performance issues, and security vulnerabilities. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'code', 'language', and 'analysis_focus'.

Try it

Result:

technical_comparison

Compares multiple technologies, frameworks, or libraries based on specific criteria. Provides detailed comparison tables with pros/cons and use cases. Includes version-specific information and compatibility considerations. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'technologies' and 'criteria'.

Try it

Result:

architecture_pattern_recommendation

Suggests architecture patterns for specific use cases based on industry best practices. Provides implementation examples and considerations for the recommended patterns. Includes diagrams and explanations of pattern benefits and tradeoffs. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'requirements' and 'tech_stack'.

Try it

requirements*

Requirements and constraints for the system.

description*

Description of the system to be built.

scale*

Expected scale of the system.

key_concerns*

Key architectural concerns (e.g., ['scalability', 'security', 'performance', 'maintainability']).

key_concerns

Key architectural concerns (e.g., ['scalability', 'security', 'performance', 'maintainability']).

No items yet. Use the button below to add some.

tech_stack*

Technologies to be used (e.g., ['Node.js', 'React', 'PostgreSQL']).

tech_stack

Technologies to be used (e.g., ['Node.js', 'React', 'PostgreSQL']).

No items yet. Use the button below to add some.

industry

Optional. Industry or domain context (e.g., 'healthcare', 'finance', 'e-commerce').

existing_architecture

Optional. Description of existing architecture if this is an evolution of an existing system.

Result:

dependency_vulnerability_scan

Analyzes project dependencies for known security vulnerabilities. Provides detailed information about each vulnerability with severity ratings. Suggests mitigation strategies and secure alternatives. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'dependencies' and 'ecosystem'.

Try it

Result:

database_schema_analyzer

Reviews database schemas for normalization, indexing, and performance issues. Suggests improvements based on database-specific best practices. Provides migration strategies for implementing suggested changes. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'schema' and 'database_type'.

Try it

schema*

Database schema definition (SQL CREATE statements, JSON schema, etc.).

database_type*

Database system (e.g., 'PostgreSQL', 'MySQL', 'MongoDB', 'DynamoDB').

database_version

Optional. Specific version of the database system.

focus_areas

Optional. Areas to focus the analysis on.

focus_areas

Optional. Areas to focus the analysis on.

focus_areas-1*

expected_scale

Optional. Information about the expected scale and usage patterns.

rows_per_table

Approximate number of rows expected in each table.

growth_rate

Expected growth rate of the database.

query_patterns

Common query patterns (e.g., ['frequent reads', 'batch updates']).

query_patterns

Common query patterns (e.g., ['frequent reads', 'batch updates']).

No items yet. Use the button below to add some.

Result:

security_best_practices_advisor

Provides security recommendations for specific technologies or scenarios. Includes code examples for implementing secure practices. References industry standards and security guidelines. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'technology' and 'security_context'.

Try it

Result:

testing_strategy_generator

Creates comprehensive testing strategies for applications or features. Suggests appropriate testing types (unit, integration, e2e) with coverage goals. Provides example test cases and testing frameworks. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'project_description' and 'tech_stack'.

Try it

project_description*

Description of the project or feature to be tested.

tech_stack*

Technologies used in the project (e.g., ['React', 'Node.js', 'PostgreSQL']).

tech_stack

Technologies used in the project (e.g., ['React', 'Node.js', 'PostgreSQL']).

No items yet. Use the button below to add some.

project_type*

Type of project being developed.

testing_priorities

Optional. Testing priorities for the project.

testing_priorities

Optional. Testing priorities for the project.

testing_priorities-1*

constraints

Optional. Constraints that might affect the testing strategy.

time

Time constraints for implementing testing.

resources

Resource constraints (team size, expertise, etc.).

environment

Environment constraints (CI/CD, deployment, etc.).

Result:

regulatory_compliance_advisor

Provides guidance on regulatory requirements for specific industries (GDPR, HIPAA, etc.). Suggests implementation approaches for compliance. Includes checklists and verification strategies. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'regulations' and 'context'.

Try it

regulations*

Regulations to address (e.g., ['GDPR', 'HIPAA', 'PCI DSS', 'CCPA']).

regulations

Regulations to address (e.g., ['GDPR', 'HIPAA', 'PCI DSS', 'CCPA']).

No items yet. Use the button below to add some.

context*

Context information for compliance analysis.

industry*

Industry context (e.g., 'healthcare', 'finance', 'e-commerce').

application_type*

Type of application (e.g., 'web app', 'mobile app', 'SaaS platform').

data_types*

Types of data being processed (e.g., ['PII', 'PHI', 'payment data']).

data_types

Types of data being processed (e.g., ['PII', 'PHI', 'payment data']).

No items yet. Use the button below to add some.

user_regions

Regions where users are located (e.g., ['EU', 'US', 'Canada']).

user_regions

Regions where users are located (e.g., ['EU', 'US', 'Canada']).

No items yet. Use the button below to add some.

tech_stack

Optional. Technologies used in the application.

tech_stack

Optional. Technologies used in the application.

No items yet. Use the button below to add some.

implementation_phase

Optional. Current phase of implementation.

output_format

Optional. Format of the compliance guidance.

Result:

microservice_design_assistant

Helps design microservice architectures for specific domains. Provides service boundary recommendations and communication patterns. Includes deployment and orchestration considerations. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'domain_description' and 'requirements'.

Try it

domain_description*

Description of the business domain for the microservice architecture.

requirements*

System requirements and constraints.

functional*

Key functional requirements for the system.

functional

Key functional requirements for the system.

No items yet. Use the button below to add some.

non_functional*

Non-functional requirements (scalability, availability, etc.).

non_functional

Non-functional requirements (scalability, availability, etc.).

No items yet. Use the button below to add some.

constraints

Technical or organizational constraints.

constraints

Technical or organizational constraints.

No items yet. Use the button below to add some.

tech_stack

Optional. Technology preferences for implementation.

preferred_languages

Preferred programming languages.

preferred_languages

Preferred programming languages.

No items yet. Use the button below to add some.

preferred_databases

Preferred database technologies.

preferred_databases

Preferred database technologies.

No items yet. Use the button below to add some.

deployment_platform

Target deployment platform (e.g., 'Kubernetes', 'AWS', 'Azure').

existing_systems

Optional. Description of existing systems that need to be integrated.

existing_systems

Optional. Description of existing systems that need to be integrated.

No items yet. Use the button below to add some.

team_structure

Optional. Description of the development team structure.

design_focus

Optional. Specific aspects to focus on in the design.

design_focus

Optional. Specific aspects to focus on in the design.

design_focus-1*

Result:

documentation_generator

Creates comprehensive documentation for code, APIs, or systems. Follows industry best practices for technical documentation. Includes examples, diagrams, and user guides. Uses the configured Vertex AI model (gemini-2.0-flash) with Google Search. Requires 'content_type' and 'content'.

Try it

content_type*

Type of documentation to generate.

content*

The code, API specification, or system description to document.

language

Programming language or API specification format (e.g., 'JavaScript', 'OpenAPI', 'GraphQL').

audience

Optional. Target audience for the documentation.

audience

Optional. Target audience for the documentation.

audience-1*

documentation_format

Optional. Output format for the documentation.

detail_level

Optional. Level of detail in the documentation.

include_sections

Optional. Specific sections to include in the documentation.

include_sections

Optional. Specific sections to include in the documentation.

include_sections-1*

Result:

Loading Tools

Connecting to MCP server and fetching available tools...

Author

shariqriazz

Claim Ownership

Verify you have write access to the repository

Repository

https://github.com/shariqriazz/vertex-ai-mcp-server

GitHub Stars

License

MIT License

Last publish date

2025-04-20

Last update date

2025-08-12

Server configs

in claude desktop

{
  "mcpServers": {
    "vertex-ai-mcp-server": {
      "command": "bunx",
      "args": [
        "-y",
        "@shariqriazz/vertex-ai-mcp-server"
      ],
      "env": {
        "AI_PROVIDER": "vertex",
        "GOOGLE_CLOUD_PROJECT": "YOUR_GCP_PROJECT_ID"
      }
    }
  }
}

in cline

{
  "mcpServers": {
    "vertex-ai-mcp-server": {
      "command": "node",
      "args": [
        "/full/path/to/your/vertex-ai-mcp-server/build/index.js"
      ],
      "env": {
        "AI_PROVIDER": "vertex",
        "GOOGLE_CLOUD_PROJECT": "YOUR_GCP_PROJECT_ID"
      },
      "disabled": false,
      "timeout": 3600
    }
  }
}

via npx in cline

{
  "mcpServers": {
    "vertex-ai-mcp-server": {
      "command": "bunx",
      "args": [
        "-y",
        "vertex-ai-mcp-server"
      ],
      "env": {
        "AI_PROVIDER": "vertex",
        "GOOGLE_CLOUD_PROJECT": "YOUR_GCP_PROJECT_ID"
      },
      "disabled": false,
      "timeout": 3600
    }
  }
}

Top Comments

Related MCP Servers

View all ai_chatbot servers →

Sequential Thinking

4.6

by modelcontextprotocol

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

research_and_data

mindsdb

4.6

by mindsdb

MindsDB is an open-source server that enables seamless interaction with large-scale federated data using the Model Context Protocol (MCP).

databases

elevenlabs-mcp

4.5

by elevenlabs

Official ElevenLabs Model Context Protocol (MCP) server for interaction with Text to Speech and audio processing APIs.

ai_chatbot

mcp-hfspace

4.5

by evalstate

mcp-hfspace MCP Server connects to Hugging Face Spaces with minimal setup, providing Image Generation capabilities to Claude Desktop.

ai_chatbot

paelladoc

4.4

by jlcases

PAELLADOC is an AI-First Development framework implementing the Model Context Protocol (MCP) to enhance LLM interactions with external tools and context.

ai_chatbot

mcp-server-calculator

4.4

by githejie

A Model Context Protocol server for calculating. This server enables LLMs to use calculator for precise numerical calculations.

developer_tools

f2c-mcp

4.3

by f2c-ai

A Model Context Protocol server for Figma Design to Code using F2C.

developer_tools

whois-mcp

4.3

by bharathvaj-ganesan

The Whois MCP server allows AI agents to perform WHOIS lookups to retrieve domain details.

research_and_data

HowToCook-mcp

4.3

by worryzyy

HowToCook-MCP Server is a Model Context Protocol server that transforms AI assistants into personal chefs, helping users plan meals and recommend recipes.

ai_chatbot

apktool-mcp-server

4.3

by zinja-coder

apktool-mcp-server is a fully automated MCP server built on top of apktool to analyze Android APKs using LLMs like Claude, providing live reverse engineering support.

security

exa-mcp-server

4.3

by exa-labs

A Model Context Protocol (MCP) server allows AI assistants to use the Exa AI Search API for real-time web searches in a secure manner.

research_and_data

jinni

4.2

by smat-dev

Jinni is a tool designed to efficiently provide Large Language Models (LLMs) with the context of your projects by consolidating relevant project files.

developer_tools

mcp-crawl4ai-rag

4.2

by coleam00

Crawl4AI RAG MCP Server is a powerful implementation of the Model Context Protocol (MCP) integrated with Crawl4AI and Supabase, providing AI agents and AI coding assistants with advanced web crawling and RAG capabilities.

browser_automation

google-docs-mcp

4.2

by a-bonus

The Ultimate Google Docs MCP Server connects Claude Desktop or other MCP clients to Google Docs, enabling advanced document manipulation through the Model Context Protocol (MCP) and the fastmcp library.

ai_chatbot

python-mcp-server-client

4.1

by GobinFan

MCP Server is a server implementing the Model Context Protocol (MCP) to provide a standardized interface for AI models, connecting external data sources and tools like file systems, databases, or APIs.

ai_chatbot

mem0-mcp

4.0

by pinkpixel-dev

A Model Context Protocol (MCP) server that integrates with Mem0.ai to provide persistent memory capabilities for LLMs.

ai_chatbot

gateway

4.0

by centralmind

CentralMind Gateway is a tool designed to expose databases to AI agents via MCP or OpenAPI protocols, providing secure, LLM-optimized APIs.

databases

google-search

3.9

by web-agent-master

A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches and extract results.

browser_automation

square-mcp-server

3.9

by square

The Square Model Context Protocol Server (Beta) allows AI assistants to interact with Square's connect API using the Model Context Protocol standard.

cloud_platforms

drawio-mcp-server

3.9

by lgazo

The Draw.io MCP server is a Model Context Protocol implementation that integrates Draw.io's diagramming capabilities with AI agentic systems.

ai_chatbot

chronulus-mcp

3.9

by ChronulusAI

MCP Server for Chronulus allows users to interact with Chronulus AI Forecasting & Prediction Agents using Claude.

ai_chatbot

rapidocr-mcp

3.9

by z4none

RapidOCR MCP Server is a Model Context Protocol server that provides an easy-to-use OCR interface.

ai_chatbot

claude-prompts-mcp

3.9

by minipuft

Claude Prompts MCP Server is a universal Model Context Protocol server designed to enhance AI workflows with advanced prompt engineering and orchestration capabilities.

ai_chatbot

mcp-tavily

3.8

by RamXX

Tavily MCP Server is a Model Context Protocol server that provides AI-powered web search capabilities using Tavily's search API.

research_and_data

tiktok-mcp

3.8

by Seym0n

The TikTok MCP integrates TikTok access into Claude AI and other apps via TikNeuron.

ai_chatbot

magic-mcp

3.8

by 21st-dev

Magic Component Platform (MCP) is a powerful AI-driven tool that helps developers create beautiful, modern UI components instantly through natural language descriptions.

developer_tools

ableton-mcp

3.8

by ahujasid

AbletonMCP connects Ableton Live to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Ableton Live.

ai_chatbot

shariqriazz/vertex-ai-mcp-server

Try vertex-ai-mcp-server with chat:

answer_query_websearch

Result:

answer_query_direct

Result:

explain_topic_with_docs

Result:

get_doc_snippets

Result:

generate_project_guidelines

tech_stack

Result:

read_file_content

Result:

write_file_content

Result:

edit_file_content

edits

Result:

list_directory_contents

Result:

get_directory_tree

Result:

move_file_or_directory

Result:

search_filesystem

excludePatterns

Result:

get_filesystem_info

Result:

execute_terminal_command

Result:

save_generate_project_guidelines

tech_stack

Result:

save_doc_snippet

Result:

save_topic_explanation

Result:

save_answer_query_direct

Result:

save_answer_query_websearch

Result:

code_analysis_with_docs

analysis_focus

Result:

technical_comparison

technologies

criteria

Result:

architecture_pattern_recommendation

key_concerns

tech_stack

Result:

dependency_vulnerability_scan

Result:

database_schema_analyzer

focus_areas

query_patterns

Result:

security_best_practices_advisor

compliance_frameworks

Result:

testing_strategy_generator

tech_stack

testing_priorities

Result:

regulatory_compliance_advisor

regulations

data_types

user_regions

tech_stack

Result:

microservice_design_assistant

functional

non_functional

constraints

preferred_languages

preferred_databases