Skip to main content

Overview

The bloom-mcp package wraps any MCP (Model Context Protocol) server with Bloom’s security layer. This provides:
  • Authentication for every tool call
  • Tool-level permissions (allow/block specific tools)
  • Audit logging of all MCP interactions
  • Kill switch support

Quick Start

1. Install

2. Configure Environment

3. Wrap Your MCP Server

How It Works

Claude Desktop Configuration

Add to your claude_desktop_config.json:

Tool-Level Permissions

Control which MCP tools your agent can use.

Dashboard Configuration

  1. Go to Scopes
  2. Create or edit a scope
  3. Set Scope Type to “MCP”
  4. Configure:
    • Allowed Tools: ["*"] for all, or ["create_issue", "list_repos"]
    • Blocked Tools: ["delete_repo", "force_push"]

API Configuration

Permission Logic

Monitoring MCP Calls

Dashboard

Go to Activity > MCP Tools tab to see:
  • All tool calls with timestamps
  • Allow/block status for each call
  • Agent and tool name
  • Latency metrics

Webhooks

Subscribe to MCP events:
Webhook Payload:

Supported MCP Servers

Works with any stdio-based MCP server:

CLI Commands

Environment Variables

Troubleshooting

  1. Check the agent has an MCP-type scope assigned
  2. Verify the tool is in allowed_tools (or allowed_tools is ["*"])
  3. Verify the tool is NOT in blocked_tools
  4. Check Activity > MCP Tools for the denial reason
  • Verify BLOOM_API_KEY and BLOOM_AGENT_ID are set correctly
  • Check the agent exists and is active in the dashboard
  • Ensure the API key hasn’t been revoked
  • Check the underlying MCP server command works without bloom-mcp
  • Verify all required environment variables for the MCP server are set
  • Check for port conflicts if running multiple servers

Example: Secure GitHub Agent

Complete setup for a GitHub-enabled Claude agent:
Now your agent can only use the allowed GitHub tools, and all calls are logged.