Skip to main content
Glama
FojleRabbiRabib

Gemini Bridge

by FojleRabbiRabib
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Gemini Bridge

CI Status PyPI Version MIT License Python 3.10+ MCP Compatible Gemini CLI

A lightweight MCP (Model Context Protocol) server that enables AI coding assistants to interact with Google's Gemini AI through the official CLI. Works with Claude Code, Cursor, VS Code, and other MCP-compatible clients. Designed for simplicity, reliability, and seamless integration.

āœØ Features

  • Direct Gemini CLI Integration: Zero API costs using official Gemini CLI

  • Three MCP Tools: Basic queries, file analysis, and web search capabilities

  • Stateless Operation: No sessions, caching, or complex state management

  • Production Ready: Robust error handling with configurable 60-second timeouts

  • Minimal Dependencies: Only requires mcp>=1.0.0 and Gemini CLI

  • Easy Deployment: Support for both uvx and traditional pip installation

  • Universal MCP Compatibility: Works with any MCP-compatible AI coding assistant

  • Modern Python: Uses pathlib and modern type hints (Python 3.10+)

Related MCP server: Gemini Code Assist MCP

šŸš€ Quick Start

Prerequisites

  1. Install Gemini CLI:

    npm install -g @google/gemini-cli

  2. Authenticate with Gemini:

    gemini auth login

  3. Verify installation:

    gemini --version

Installation

šŸŽÆ Recommended: PyPI Installation

# Install from PyPI
pip install gemini-bridge

# Add to Claude Code with uvx (recommended)
claude mcp add gemini-bridge -s user -- uvx gemini-bridge

Alternative: From Source

# Clone the repository
git clone https://github.com/shelakh/gemini-bridge.git
cd gemini-bridge

# Build and install locally
uvx --from build pyproject-build
pip install dist/*.whl

# Add to Claude Code
claude mcp add gemini-bridge -s user -- uvx gemini-bridge

Development Installation

# Clone and install in development mode
git clone https://github.com/shelakh/gemini-bridge.git
cd gemini-bridge
pip install -e .

# Add to Claude Code (development)
claude mcp add gemini-bridge-dev -s user -- python -m src

šŸŒ Multi-Client Support

Gemini Bridge works with any MCP-compatible AI coding assistant - the same server supports multiple clients through different configuration methods.

Supported MCP Clients

  • Claude Code āœ… (Default)

  • Cursor āœ…

  • VS Code āœ…

  • Windsurf āœ…

  • Cline āœ…

  • Void āœ…

  • Cherry Studio āœ…

  • Augment āœ…

  • Roo Code āœ…

  • Zencoder āœ…

  • Any MCP-compatible client āœ…

Configuration Examples

# Recommended installation
claude mcp add gemini-bridge -s user -- uvx gemini-bridge

# Development installation
claude mcp add gemini-bridge-dev -s user -- python -m src

Global Configuration (~/.cursor/mcp.json):

{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {}
    }
  }
}

Project-Specific (.cursor/mcp.json in your project):

{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {}
    }
  }
}

Go to: Settings ā†’ Cursor Settings ā†’ MCP ā†’ Add new global MCP server

Configuration (.vscode/mcp.json in your workspace):

{
  "servers": {
    "gemini-bridge": {
      "type": "stdio",
      "command": "uvx",
      "args": ["gemini-bridge"]
    }
  }
}

Alternative: Through Extensions

  1. Open Extensions view (Ctrl+Shift+X)

  2. Search for MCP extensions

  3. Add custom server with command: uvx gemini-bridge

Add to your Windsurf MCP configuration:

{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {}
    }
  }
}

  1. Open Cline and click MCP Servers in the top navigation

  2. Select Installed tab ā†’ Advanced MCP Settings

  3. Add to cline_mcp_settings.json:

{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {}
    }
  }
}

Go to: Settings ā†’ MCP ā†’ Add MCP Server

{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {}
    }
  }
}

  1. Navigate to Settings ā†’ MCP Servers ā†’ Add Server

  2. Fill in the server details:

    • Name: gemini-bridge

    • Type: STDIO

    • Command: uvx

    • Arguments: ["gemini-bridge"]

  3. Save the configuration

Using the UI:

  1. Click hamburger menu ā†’ Settings ā†’ Tools

  2. Click + Add MCP button

  3. Enter command: uvx gemini-bridge

  4. Name: Gemini Bridge

Manual Configuration:

"augment.advanced": { 
  "mcpServers": [ 
    { 
      "name": "gemini-bridge", 
      "command": "uvx", 
      "args": ["gemini-bridge"],
      "env": {}
    }
  ]
}

  1. Go to Settings ā†’ MCP Servers ā†’ Edit Global Config

  2. Add to mcp_settings.json:

{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {}
    }
  }
}

  1. Go to Zencoder menu (...) ā†’ Tools ā†’ Add Custom MCP

  2. Add configuration:

{
  "command": "uvx",
  "args": ["gemini-bridge"],
  "env": {}
}

  1. Hit the Install button

For pip-based installations:

{
  "command": "gemini-bridge",
  "args": [],
  "env": {}
}

For development/local testing:

{
  "command": "python",
  "args": ["-m", "src"],
  "env": {},
  "cwd": "/path/to/gemini-bridge"
}

For npm-style installation (if needed):

{
  "command": "npx",
  "args": ["gemini-bridge"],
  "env": {}
}

Universal Usage

Once configured with any client, use the same two tools:

  1. Ask general questions: "What authentication patterns are used in this codebase?"

  2. Analyze specific files: "Review these auth files for security issues"

The server implementation is identical - only the client configuration differs!

āš™ļø Configuration

Timeout Configuration

By default, Gemini Bridge uses a 60-second timeout for all CLI operations. For longer queries (large files, complex analysis), you can configure a custom timeout using the GEMINI_BRIDGE_TIMEOUT environment variable.

Example configurations:

# Add with custom timeout (120 seconds)
claude mcp add gemini-bridge -s user --env GEMINI_BRIDGE_TIMEOUT=120 -- uvx gemini-bridge
{
  "mcpServers": {
    "gemini-bridge": {
      "command": "uvx",
      "args": ["gemini-bridge"],
      "env": {
        "GEMINI_BRIDGE_TIMEOUT": "120"
      }
    }
  }
}

Timeout Options:

  • Default: 60 seconds (if not configured)

  • Range: Any positive integer (seconds)

  • Per-call override: Supply timeout_seconds to either tool for one-off extensions

  • Recommended: 120-300 seconds for large file analysis

  • Invalid values: Fall back to 60 seconds with warning

šŸ› ļø Available Tools

consult_gemini

Direct CLI bridge for simple queries.

Parameters:

  • query (string): The question or prompt to send to Gemini

  • directory (string): Working directory for the query

  • model (string, optional): Model to use - "flash", "pro", "flash-lite", "2.5-lite", "3-pro", "3-flash", "3.1-pro", "3.1-flash-lite", or "auto" (default: "flash")

  • timeout_seconds (int, optional): Override the execution timeout for this request

Example:

consult_gemini(
    query="Find authentication patterns in this codebase",
    directory="/path/to/project",
    model="flash"
)

consult_gemini_with_files

CLI bridge with file attachments for detailed analysis.

Parameters:

  • query (string): The question or prompt to send to Gemini

  • directory (string): Working directory for the query

  • files (list): List of file paths relative to the directory

  • model (string, optional): Model to use - "flash", "pro", "flash-lite", "2.5-lite", "3-pro", "3-flash", "3.1-pro", "3.1-flash-lite", or "auto" (default: "flash")

  • timeout_seconds (int, optional): Override the execution timeout for this request

  • mode (string, optional): Either "inline" (default) to stream file contents or "at_command" to let Gemini CLI resolve @path references itself

Example:

consult_gemini_with_files(
    query="Analyze these auth files and suggest improvements",
    directory="/path/to/project",
    files=["src/auth.py", "src/models.py"],
    model="pro",
    timeout_seconds=180
)

Tip: When scanning large trees, switch to mode="at_command" so the Gemini CLI handles file globbing and truncation natively.

web_search

Ask Gemini queries with web search context. Uses Gemini CLI's automatic web search when the model determines it's needed. Best-effort functionality - not guaranteed for every query.

Parameters:

  • query (string): Search query or question to look up on the web

  • directory (string): Working directory for command execution

  • model (string, optional): Model to use - "flash", "pro", "flash-lite", "2.5-lite", "3-pro", "3-flash", "3.1-pro", "3.1-flash-lite", or "auto" (default: "flash")

  • timeout_seconds (int, optional): Override the execution timeout for this request

Example:

web_search(
    query="latest Python version and new features",
    model="flash"
)

šŸ“‹ Usage Examples

Basic Code Analysis

# Simple research query
consult_gemini(
    query="What authentication patterns are used in this project?",
    directory="/Users/dev/my-project"
)

Detailed File Review

# Analyze specific files
consult_gemini_with_files(
    query="Review these files and suggest security improvements",
    directory="/Users/dev/my-project",
    files=["src/auth.py", "src/middleware.py"],
    model="pro"
)

Multi-file Analysis

# Compare multiple implementation files
consult_gemini_with_files(
    query="Compare these database implementations and recommend the best approach",
    directory="/Users/dev/my-project",
    files=["src/db/postgres.py", "src/db/sqlite.py", "src/db/redis.py"],
    mode="at_command"
)

Web Search

# Get current information from the web
web_search(
    query="latest Python version and new features in 3.13",
    model="flash"
)

Large File Safeguards

  • Inline transfers cap at ~256 KB per file and ~512 KB per request to avoid hangs.

  • Oversized files are truncated to head/tail snippets with a warning in the MCP response.

  • Tune the caps with environment variables (GEMINI_BRIDGE_MAX_INLINE_TOTAL_BYTES, etc.) or prefer mode="at_command" for bigger payloads.

šŸ—ļø Architecture

Core Design

  • CLI-First: Direct subprocess calls to gemini command

  • Stateless: Each tool call is independent with no session state

  • Adaptive Timeout: Defaults to 60 seconds but overridable per request or via env var

  • Attachment Guardrails: Inline mode enforces lightweight limits; @ mode delegates to Gemini CLI tooling

  • Simple Error Handling: Clear error messages with fail-fast approach

Project Structure

gemini-bridge/
ā”œā”€ā”€ src/
ā”‚   ā”œā”€ā”€ __init__.py              # Entry point
ā”‚   ā”œā”€ā”€ __main__.py              # Module execution entry point
ā”‚   ā””ā”€ā”€ mcp_server.py            # Main MCP server implementation
ā”œā”€ā”€ .github/                     # GitHub templates and workflows
ā”œā”€ā”€ pyproject.toml              # Python package configuration
ā”œā”€ā”€ README.md                   # This file
ā”œā”€ā”€ CONTRIBUTING.md             # Contribution guidelines
ā”œā”€ā”€ CODE_OF_CONDUCT.md          # Community standards
ā”œā”€ā”€ SECURITY.md                 # Security policies
ā”œā”€ā”€ CHANGELOG.md               # Version history
ā””ā”€ā”€ LICENSE                    # MIT license

šŸ”§ Development

Local Testing

# Install in development mode
pip install -e .

# Run directly
python -m src

# Test CLI availability
gemini --version

Integration with Claude Code

The server automatically integrates with Claude Code when properly configured through the MCP protocol.

šŸ” Troubleshooting

CLI Not Available

# Install Gemini CLI
npm install -g @google/gemini-cli

# Authenticate
gemini auth login

# Test
gemini --version

Connection Issues

  • Verify Gemini CLI is properly authenticated

  • Check network connectivity

  • Ensure Claude Code MCP configuration is correct

  • Check that the gemini command is in your PATH

Common Error Messages

  • "CLI not available": Gemini CLI is not installed or not in PATH

  • "Authentication required": Run gemini auth login

  • "Timeout after 60 seconds": Query took too long, try breaking it into smaller parts

šŸ¤ Contributing

We welcome contributions from the community! Please read our Contributing Guidelines for details on how to get started.

Quick Contributing Guide

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests if applicable

  5. Submit a pull request

šŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

šŸ”„ Version History

See CHANGELOG.md for detailed version history.

šŸ†˜ Support

  • Issues: Report bugs or request features via GitHub Issues

  • Discussions: Join the community discussion

  • Documentation: Additional docs can be created in the docs/ directory

Focus: A simple, reliable bridge between Claude Code and Gemini AI through the official CLI.

Available Tools

3 tools
consult_geminiB

Send a query directly to the Gemini CLI.

Args: query: Prompt text forwarded verbatim to the CLI. directory: Working directory used for command execution. model: Optional model alias (flash, pro) or full Gemini model id. timeout_seconds: Optional per-call timeout override in seconds.

Returns: Gemini's response text or an explanatory error string.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
directoryYes
modelNo
timeout_secondsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It mentions forwarding the query verbatim and returning response/error, but does not clarify read-only nature, authentication needs, rate limits, or potential side effects.

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 with an initial purpose sentence and a clear Args/Returns format. Every sentence is informative with no fluff.

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?

While the description covers invocation details and parameter semantics, it lacks contextual completeness for an AI agent: no guidance on when to use this tool vs siblings, no output schema details, and no behavioral context beyond the immediate invocation.

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 description includes detailed parameter explanations (query, directory, model, timeout_seconds) and return value, adding meaning beyond the input schema. Schema description coverage is 0% in JSON, but the docstring compensates well.

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 states 'Send a query directly to the Gemini CLI', clearly indicating the action and resource. However, it does not explicitly distinguish from sibling tools like 'consult_gemini_with_files' or 'web_search', which would be helpful for an AI agent.

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. The description lacks explicit context such as prerequisites, when-not-to-use, or comparisons with siblings.

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

consult_gemini_with_filesA

Send a query to the Gemini CLI with file context.

Args: query: Prompt text forwarded to the CLI. directory: Working directory used for resolving relative file paths. files: Relative or absolute file paths to include alongside the prompt. model: Optional model alias (flash, pro) or full Gemini model id. timeout_seconds: Optional per-call timeout override in seconds. mode: "inline" streams truncated snippets; "at_command" emits @path directives so Gemini CLI resolves files itself.

Returns: Gemini's response or an explanatory error string with any warnings.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
directoryYes
filesNo
modelNo
timeout_secondsNo
modeNoinline

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.2/5.0
Behavior4/5

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

No annotations provided, but description discloses key behaviors: inline mode streams truncated snippets, at_command mode emits @path directives, and returns explanatory error string with warnings. Adequate for a query 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?

Description is relatively concise with a clear intro and parameter list; no wasted sentences. Returns line adds value. Could be more front-loaded but still efficient.

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 6 parameters, no annotations, and no output schema, the description covers behavior, parameters, and return value sufficiently. Minor gap: no explicit mention of usage context beyond mode difference.

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

Parameters5/5

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

With 0% schema coverage, description compensates fully by explaining each parameter's purpose and constraints, e.g., directory resolves relative paths, mode describes two options, model lists aliases.

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 specifies the verb 'send a query', the resource 'Gemini CLI', and the distinguishing feature 'with file context', clearly differentiating it from the sibling tool 'consult_gemini'.

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?

Description explains the two modes ('inline' vs 'at_command') and their behaviors, providing some guidance on how to use the tool but lacks explicit when-to-use versus siblings or when-not-to-use conditions.

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.

  1. 3 tool updatesv1.3.0
    • First observedconsult_gemini
    • First observedconsult_gemini_with_files
    • First observedweb_search
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: consult_gemini for plain queries, consult_gemini_with_files for queries with file context, and web_search for web-augmented queries. No functional overlap.

Naming Consistency4/5

Naming mostly follows a verb_noun pattern with 'consult_gemini' as a base, but 'web_search' deviates by not starting with 'consult'. Overall pattern is still predictable and readable.

Tool Count5/5

Three tools is an appropriate scope for a Gemini CLI bridge, covering the essential query modes (plain, with files, web search) without unnecessary bloat.

Completeness4/5

The set covers the primary use cases for interacting with Gemini. Missing tools for model listing or configuration, but these are minor gaps for the intended purpose of querying.

Maintenance

ActivityInactive
ResponsivenessSyncing

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/FojleRabbiRabib/gemini-bridge'

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