Cross-Project MCP Server

Enables AI agents to explore, search, and reference code across repositories.

README.md

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_instructions first 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 Read file contents with optional line ranges
list_directory Browse directory structure (recursive optional)
search_code Search for patterns (regex or literal) across the codebase
get_file_outline Extract functions, classes, and symbols from source files
find_files Find files by name pattern (glob matching)

Agent Discovery & Delegation

Tool Description
get_agent_instructions Read .agent/gemini.md to understand the repo's purpose and rules
submit_task Delegate work by creating a task file in .agent/tasks/
list_tasks List tasks in the inbox, filterable by status (OPEN, IN_PROGRESS, DONE, BLOCKED)
read_task 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 build

Configuration 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
"oss-project" A descriptive name for your source project (can be anything)
First arg Path to this server's dist/index.js
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:

  1. Explore structure: List directories, find files by pattern
  2. Read implementation: Read specific files or line ranges
  3. Search code: Find usages of functions, types, or patterns
  4. 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

  1. Agent A (Website) needs a change in Repo B (OSS).
  2. Agent A calls submit_task on Repo B's MCP server.
  3. A file task_[timestamp]_[title].md is created in Repo B.
  4. Agent B (OSS) sees the task and implements it.

Tools 9

read_fileRead file contents with optional line ranges
list_directoryBrowse directory structure (recursive optional)
search_codeSearch for patterns (regex or literal) across the codebase
get_file_outlineExtract functions, classes, and symbols from source files
find_filesFind files by name pattern (glob matching)
get_agent_instructionsRead .agent/gemini.md to understand the repo's purpose and rules
submit_taskDelegate work by creating a task file in .agent/tasks/
list_tasksList tasks in the inbox, filterable by status
read_taskRead the full content of a specific task file

Try it

Read the agent instructions for the target repository to understand how to contribute.
Search for all occurrences of the 'AuthService' class in the target repository.
List all files in the src directory and provide an outline of the main controller file.
Submit a new task to the target repository requesting a fix for the login bug.
List all open tasks in the target repository to see what work is currently pending.

Frequently Asked Questions

What are the key features of Cross-Project MCP Server?

Cross-repository code exploration and searching. Task delegation protocol for multi-agent workflows. Symbol extraction for multiple programming languages. Sandboxed file access with path traversal protection. Agent-specific instruction reading via .agent/gemini.md.

What can I use Cross-Project MCP Server for?

Referencing implementation details from an OSS library while working in a separate website project.. Delegating feature requests or bug fixes from a primary application repository to a secondary utility repository.. Automated discovery of project rules and contribution guidelines for AI agents.. Synchronizing development tasks across multiple related codebases..

How do I install Cross-Project MCP Server?

Install Cross-Project MCP Server by running: cd cross-project-mcp-server && npm install && npm run build

What MCP clients work with Cross-Project MCP Server?

Cross-Project MCP Server works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Cross-Project MCP Server docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Open Conare