Submit
unstrike

Bugcrowd MCP Server

Community unstrike
Updated

A high-performance MCP (Model Context Protocol) server that provides secure, tool-based access to the Bugcrowd API, allowing for natural language interaction through various AI agent platforms.

Bugcrowd MCP Server

CIcodecovCodeQLLicense: MITPython VersionCode style: ruff

A high-performance MCP (Model Context Protocol) server that provides secure, tool-based access to the Bugcrowd API, allowing for natural language interaction through various AI agent platforms.

Features

  • Broad API Coverage: Provides tools for interacting with Organizations, Programs, Submissions, Assets, and more.
  • Multi-Agent Support: Includes ready-to-use agents for OpenAI, Anthropic (Claude), Google (Gemini), and FastMCP.
  • Extensible & Customizable: Easily switch between AI providers, configure different models, and integrate with platform-specific CLIs.
  • Secure: Uses environment variables for API credentials and performs input validation.
  • Dynamic Help: Includes a help() tool that provides real-time documentation for all available tools.

Quick Start

This guide will get you up and running with the default agent (openai).

1. Prerequisites

  • Python 3.10+
  • uv for package installation.

2. Installation

Clone the repository, create a virtual environment, and install dependencies.

git clone https://github.com/unstrike/Bugcrowd_MCP_Server.git
cd Bugcrowd_MCP_Server

# Create and activate virtual environment
uv venv
source .venv/bin/activate

# Install dependencies
uv sync

3. Configuration

Export your Bugcrowd and OpenAI API credentials as environment variables.

export BUGCROWD_API_USERNAME="your-username"
export BUGCROWD_API_PASSWORD="your-password"
export OPENAI_API_KEY="your-openai-api-key"

4. Run the Agent

Start the interactive agent.

uv run python -m bugcrowd_agents.agent_orchestrator

You can now interact with the Bugcrowd API using natural language.

Example Prompts:

  • "Show me available bug bounty programs"
  • "What are the 5 most recent vulnerability submissions?"
  • "Use the help tool to see all available commands"

Advanced Usage

Switching Agents

The true power of this server lies in its flexibility. You can easily switch between supported AI platforms by setting the AGENT_PLATFORM environment variable.

  • Supported platforms: openai (default), claude, gemini, fastmcp.

Remember to set the appropriate API key for the agent you choose.

Example: Running the Gemini Agent

# 1. Set the API key for Google
export GOOGLE_AI_API_KEY="your-gemini-api-key"

# 2. Run the orchestrator with the AGENT_PLATFORM variable
AGENT_PLATFORM=gemini uv run python -m bugcrowd_agents.agent_orchestrator

Example: Running the Claude Agent

export ANTHROPIC_API_KEY="your-claude-api-key"
AGENT_PLATFORM=claude uv run python -m bugcrowd_agents.agent_orchestrator

Using the FastMCP Agent

The fastmcp agent is a versatile client that can use different LLM backends. Configure it by setting the FASTMCP_PROVIDER environment variable.

  • Supported providers: anthropic (default), google, openai.

Example: Running FastMCP with the Google (Gemini) Backend

# 1. Set the API key for the desired backend
export GOOGLE_AI_API_KEY="your-gemini-api-key"

# 2. Set the platform and provider, then run
AGENT_PLATFORM=fastmcp FASTMCP_PROVIDER=google uv run python -m bugcrowd_agents.agent_orchestrator

Customizing Agent Models

You can override the default models for each agent by setting environment variables:

  • Claude: CLAUDE_MAIN_MODEL, CLAUDE_SUMMARY_MODEL
  • Gemini: GEMINI_MAIN_MODEL, GEMINI_SUMMARY_MODEL
  • OpenAI: OPENAI_MODEL

Available Tools

The server provides the following tools. For detailed parameter information, run the agent and use the help() tool (e.g., help('get_submission')).

Category Tool Description
Organizations get_organizations List all accessible organizations
get_organization Get specific organization details
Programs get_programs List bug bounty programs
get_program Get specific program details
Submissions get_submissions List vulnerability submissions
get_submission Get specific submission details
create_submission Create a new vulnerability report
update_submission Update an existing submission
create_comment Add a comment to a submission
Teams get_teams List all teams in an organization
create_team Create a new team
delete_team Delete a team
Rewards get_monetary_rewards List bounty rewards
create_monetary_reward Create a new monetary reward
update_monetary_reward Update an existing monetary reward
Users get_users List users in an organization
get_user Get specific user details
Health server_health Check server and API connectivity
Help help Get detailed help for any tool

Direct Integration

For integration with platform-specific CLIs (bypassing the included agent handlers), use the provided configuration templates.

  • For OpenAI (codex): Use docs/config.toml.
  • For Gemini, Claude, etc.: Use docs/config.json.

Instructions:

  1. Copy the appropriate template file to your tool's configuration directory (e.g., ~/.codex/config.toml).
  2. In the copied file, update the cwd variable to the absolute path of the Bugcrowd_MCP_Server project directory.

Documentation

  • API Reference: A static reference for all tool and endpoint details.
  • Architecture Diagram: An overview of the system architecture.
  • Bugcrowd REST API: The official API documentation that this server is built upon.

For more detailed information on MCP server configuration, refer to the official documentation for your platform:

MCP Server · Populars

MCP Server · New