Provides tools for exploring JavaScript codebases, including literal and regex search, file navigation, and extraction of symbols such as functions and classes.
Supports symbol extraction and code exploration for Kotlin source files, allowing agents to understand project structure.
Utilizes Markdown for its task delegation protocol and agent instruction system, allowing agents to communicate and coordinate via structured task files.
Allows agents to explore Python source code, providing tools for searching code and extracting symbol outlines for classes and functions.
Enables symbol extraction and code exploration for Rust projects, allowing agents to identify functions and structures within the codebase.
Enables exploration of TypeScript projects with support for searching code patterns and extracting symbol outlines from .ts and .tsx files.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cross-Project MCP Serversearch for the implementation of the API client in the OSS project"
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.
Cross-Project MCP Server
A generic MCP (Model Context Protocol) server that allows AI agents to access code from another project. This enables agents working in one repository (e.g., your website) to reference implementation details from a source repository (e.g., your OSS tool).
Discovery & Instructions
The server exposes get_agent_instructions to help agents understand the target repository.
Best Practice: Agents should call
get_agent_instructionsfirst to read.agent/gemini.md(or similar) from the source repo. This provides context on when and how to delegate tasks.
Tools Reference
Code Exploration
Tool | Description |
| Read file contents with optional line ranges |
| Browse directory structure (recursive optional) |
| Search for patterns (regex or literal) across the codebase |
| Extract functions, classes, and symbols from source files |
| Find files by name pattern (glob matching) |
Agent Discovery & Delegation
Tool | Description |
| Read |
| Delegate work by creating a task file in |
| List tasks in the inbox, filterable by status (OPEN, IN_PROGRESS, DONE, BLOCKED) |
| Read the full content of a specific task file |
All operations are sandboxed to the configured source project path for security.
Installation
cd cross-project-mcp-server
npm install
npm run buildConfiguration for Antigravity
Add the server to your project's .gemini/mcp_settings.json:
{
"mcpServers": {
"oss-project": {
"command": "node",
"args": [
"/absolute/path/to/cross-project-mcp-server/dist/index.js",
"/absolute/path/to/your-oss-repo"
]
}
}
}Configuration Parameters
Parameter | Description |
| A descriptive name for your source project (can be anything) |
First arg | Path to this server's |
Second arg | Path to your OSS/source repository |
Example
If your OSS tool is at /Users/you/projects/my-oss-tool and this server is at /Users/you/tools/cross-project-mcp-server:
{
"mcpServers": {
"my-oss-tool": {
"command": "node",
"args": [
"/Users/you/tools/cross-project-mcp-server/dist/index.js",
"/Users/you/projects/my-oss-tool"
]
}
}
}Usage
Once configured, the MCP tools will be available to AI agents working in your project. The agent can:
Explore structure: List directories, find files by pattern
Read implementation: Read specific files or line ranges
Search code: Find usages of functions, types, or patterns
Understand symbols: Get outlines of classes and functions
Supported Languages for Outline
The get_file_outline tool supports extracting symbols from:
TypeScript/JavaScript (
.ts,.tsx,.js,.jsx)Python (
.py)Java/Kotlin (
.java,.kt)Go (
.go)Rust (
.rs)
Security
All file access is restricted to the configured source project directory
Common non-essential directories (node_modules, .git, etc.) are automatically excluded
Path traversal attempts are blocked
Task Delegation (Multi-Agent)
This server supports a Task Delegation Protocol allowing agents to request work from the repository owner.
submit_task: Write a structured task request (Markdown) to
.agent/tasks/list_tasks: Check the inbox for new requests
read_task: Read the full context of a request
Workflow
Agent A (Website) needs a change in Repo B (OSS).
Agent A calls
submit_taskon Repo B's MCP server.A file
task_[timestamp]_[title].mdis created in Repo B.Agent B (OSS) sees the task and implements it.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.