CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
neuralegion avatar

Bright Security

neuralegion/mcp
authSSEregistry active
Summary

Connects your AI coding assistant directly to Bright's application security platform to run vulnerability scans without leaving your editor. You get tools to discover API endpoints from URLs or OpenAPI specs, launch security tests for SQL injection, XSS, and other vulnerabilities, then review findings by severity. It handles authentication configs, manages scan history across projects, and supports scanning local apps through repeaters. Runs as a remote SSE server at app.brightsec.com/mcp, so there's nothing to install locally. You just authenticate with a Bright API key and ask your assistant to scan a URL. Good fit if you're already using Bright and want security testing in your AI workflow instead of switching to their web dashboard.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →

Bright MCP Integration

Bright's Model Context Protocol (MCP) integration brings AI-powered application security testing directly into your development workflow. Your AI coding assistant can discover API endpoints, run security scans, and review vulnerabilities — all through natural language conversation.

Bright MCP is a remote, cloud-hosted MCP server. There is nothing to install locally — you simply point your MCP-compatible client at Bright's endpoint and authenticate with an API key.

Quick Start

1. Get a Bright API Key

Create a dedicated API key in your Bright account. This can be a personal, project, or organization-level key with the relevant scopes. See Personal API Key Scopes for details.

2. Configure Your Client

Add Bright as a remote MCP server in your IDE or tool of choice. The server URL is:

https://app.brightsec.com/mcp

Note: If your organization uses a dedicated Bright cluster, replace app.brightsec.com with your cluster's hostname.

See Client Configuration below for IDE-specific instructions.

3. Start Using It

Ask your AI assistant something like:

Scan https://my-app.example.com for security vulnerabilities

Your assistant will use the Bright MCP tools to list projects, discover entrypoints, run scans, and report findings.


Client Configuration

VS Code (GitHub Copilot)

Add the following to your MCP configuration (via Command Palette → "MCP: Add Server" → Global, or manually edit your mcp.json):

{
  "servers": {
    "brightsec.com": {
      "type": "sse",
      "url": "https://app.brightsec.com/mcp",
      "headers": {
        "Authorization": "Api-Key ${input:apiKey}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "apiKey",
      "description": "Enter your Bright API Key",
      "password": true
    }
  ]
}

Then go to the Extensions tab, right-click the brightsec.com MCP server, and choose Start Server. You'll be prompted to enter your API key.

Full guide: Configure Bright MCP in VS Code

Augment Code

  1. Open the Augment Code extension settings → Tools → MCP.
  2. Click + Add remote MCP.
  3. Fill in:
    • Connection Type: HTTP
    • Authentication Type: Header
    • Name: BrightSec
    • URL: https://app.brightsec.com/mcp
    • Header Name: Authorization
    • Header Value: Api-Key YOUR_API_KEY
  4. Click Save.

Full guide: Configure Bright MCP in Augment Code

Cursor

Add to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "brightsec": {
      "url": "https://app.brightsec.com/mcp",
      "headers": {
        "Authorization": "Api-Key YOUR_API_KEY"
      }
    }
  }
}

Windsurf

Add to your Windsurf MCP configuration (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "brightsec": {
      "serverUrl": "https://app.brightsec.com/mcp",
      "headers": {
        "Authorization": "Api-Key YOUR_API_KEY"
      }
    }
  }
}

Generic MCP Client

Any MCP-compatible client that supports remote HTTP/SSE servers can connect to Bright. Configure it with:

SettingValue
TransportSSE (Server-Sent Events) or HTTP
URLhttps://app.brightsec.com/mcp
Auth HeaderAuthorization: Api-Key YOUR_KEY

Available Tools

Bright MCP exposes the following tools to your AI assistant:

Project Management

ToolDescription
listProjectsList all projects accessible to your API key. Use this to find project IDs needed for other operations.

Endpoint Discovery

ToolDescription
runDiscoveryDiscover API endpoints using crawling (crawlerUrls) or API definitions (fileId from uploadApiDefinition). Before running, check if the project already has entrypoints with listEntrypoints. For private/local targets, specify a connected repeater via repeaters.
getDiscoveryStatusGet the current status of a discovery run.
listDiscoveriesList discovery history for a project. View past discovery runs or monitor ongoing endpoint discovery.
uploadApiDefinitionUpload an API definition file (OpenAPI/Swagger) by URL or content. Returns a file ID to reference in discovery runs.

Entrypoint Management

ToolDescription
listEntrypointsList discovered API endpoints/URLs for a project. Use this to select entrypoints for scans or evaluate attack surface coverage. Supports filtering by HTTP method, status, and text search.
getEntrypointGet detailed information about a specific entrypoint by ID, including headers, body, and configuration.
addEntrypointAdd a new entrypoint to a project. Entrypoints define HTTP requests (method, URL, headers, body) that can be used for security scanning.
editEntrypointUpdate an existing entrypoint. Modify the HTTP request definition, authentication, or repeater settings.

Security Scanning

ToolDescription
runScanStart a security scan against selected entrypoints. Supports targeting specific entrypoints by ID or by status (e.g., new, changed, vulnerable). Configure which tests to run or use a scan template. For private/local targets, specify a connected repeater.
getScanStatusGet the current status of a running scan.
listScansList scan history for a project. View past scan results or check the status of multiple ongoing scans.
listTestsList all available security tests (e.g., SQL injection, XSS, CSRF) that can be included in scans.

Vulnerability Management

ToolDescription
listIssuesList security vulnerabilities found for a project. Filter by severity (Low, Medium, High, Critical), status (new, recurring, resolved, ignored), or entrypoint.

Authentication Configuration

ToolDescription
listAuthsList authentication configurations for a project. Use before scanning protected endpoints that require authentication.
getAuthGet detailed information about a specific authentication configuration.
addAuthCreate a new authentication configuration. Supports multiple auth types: static headers, OAuth 2.0/OIDC, multi-step HTTP flows, NTLM, browser-based login, and recorded browser flows.
editAuthUpdate an existing authentication configuration.

Private/Local Target Access

ToolDescription
createRepeaterCreate a repeater for accessing private/local targets. After creation, run the Bright CLI to start the repeater and establish the connection.
listRepeatersList repeaters and their connection status. Verify a repeater is connected before scanning non-public applications.

Usage Examples

Scan a Public Application

"Scan https://my-app.example.com for security vulnerabilities"

The assistant will:

  1. List your projects to find the appropriate one
  2. Get all discovered entrypoints for the project
  3. Run a security scan against those entrypoints
  4. Monitor the scan status and report findings

Discover Endpoints from an OpenAPI Spec

"Discover API endpoints from the OpenAPI spec at https://my-app.example.com/openapi.json"

The assistant will:

  1. Upload the OpenAPI definition file
  2. Run file-based discovery
  3. Monitor the discovery status

Scan a Local/Private Application

"Scan my local application at http://localhost:3000"

The assistant will:

  1. Check if Bright CLI is installed for repeater connectivity
  2. List your projects to find the appropriate one
  3. Create a repeater if needed
  4. Run a security scan through the repeater
  5. Monitor the scan status and report findings

Check for Critical Vulnerabilities

"Show me all critical and high severity issues in my project"

The assistant will:

  1. List your projects
  2. Query issues filtered by Critical and High severity
  3. Present findings with details

Scan with Authentication

"Scan my API that requires Bearer token authentication"

The assistant will:

  1. Create or find an existing auth configuration
  2. Set up the proper headers/token flow
  3. Run the scan with authentication applied

See the examples/ directory for more detailed workflow examples.


How It Works

┌─────────────────────┐         ┌──────────────────────┐
│   AI Assistant       │  MCP    │   Bright Cloud       │
│   (VS Code, Cursor,  │◄──────►│   (app.brightsec.com)│
│    Windsurf, etc.)   │  SSE    │                      │
└─────────────────────┘         └──────────┬───────────┘
                                           │
                                           │ Scans
                                           ▼
                                ┌──────────────────────┐
                                │   Your Application   │
                                │   (public or via      │
                                │    repeater)          │
                                └──────────────────────┘
  1. Your AI assistant connects to Bright's MCP endpoint over SSE/HTTP.
  2. Bright's cloud platform receives tool calls and orchestrates security operations.
  3. Scans run against your application — either directly (public targets) or through a Repeater (private/local targets).

Repeaters (Private/Local Targets)

To scan applications that aren't publicly accessible, Bright uses Repeaters — lightweight agents that route scan traffic from Bright's cloud through your local network.

  1. Create a repeater via the MCP tool (createRepeater)
  2. Start the repeater using the Bright CLI:
    bright-cli repeater \
      --id <REPEATER_ID> \
      --hostname app.brightsec.com \
      --token <YOUR_API_KEY>
    
  3. Reference the repeater when running scans or discoveries

See the Bright CLI Installation Guide for setup instructions.


Resources

  • Bright Documentation
  • Bright MCP Tools Reference
  • VS Code Configuration Guide
  • Augment Code Configuration Guide
  • API Key Scopes
  • Bright CLI Installation
  • Model Context Protocol Specification

License

This repository contains configuration examples and documentation for Bright's MCP integration. Bright's security scanning platform is a commercial SaaS product — visit brightsec.com for more information.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
Security & Pentesting
Registryactive
TransportSSE
AuthRequired
UpdatedMar 12, 2026
View on GitHub

Related Security & Pentesting MCP Servers

View all →
nexus-api-lab avatar
Nexus Mcp

nexus-api-lab/nexus-mcp

Japanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.
node-man avatar
Dechonet Mcp

node-man/dechonet-mcp

13 security recon tools for AI agents — DNS, SSL, HTTP, email, ports, ASN. Health Score 0-100.
olane-labs avatar
Cosync Local

olane-labs/cosync-local

Local encryption and project setup plugin for CoSync. Keys never leave your machine.
olum289 avatar
Agentlock

olum289/agentlock

Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
pduggusa avatar
Dredd MCP

pduggusa/dredd-mcp

Pre-flight MCP security. Blocks compromised deps + tool drift. HMAC-signed. Dredd judges.
promptfax avatar
promptfax

promptfax/promptfax

PromptFax is a pay-per-use remote MCP server that lets an AI assistant send a real fax to a US fax number. Your assistant uploads a PDF or image, enters the destination, reviews a quote, opens Stripe Checkout, and queues the transmission. Pricing is $2.00 for the first 5 pages, then $0.10 per page after that, capped at $4.50 for up to 35 pages. Payment is captured only after the fax is recorded as delivered. There is no PromptFax account, no subscription, and no API key to manage. PromptFax uses OAuth and Streamable HTTP, so users install once and their assistant can start a fax workflow when needed. Inside ChatGPT, PromptFax opens a connector widget that handles document review, destination entry, Stripe Checkout, and the delivery report. Inside Claude or other MCP hosts, PromptFax falls back to an agent-friendly hosted session page that handles the same flow without requiring the host to pass files directly. Every real send requires a user-reviewed quote and Stripe authorization. The assistant cannot silently complete a fax. The `send_fax` and `cancel` tools are marked as destructive so well-behaved MCP hosts can surface confirmation steps. ## Capabilities - Send outbound faxes to US fax numbers - Attach a PDF or image from the host, widget, hosted session page, or HTTPS URL - Generate a pay-per-use quote before payment - Open Stripe Checkout for payment authorization - Queue a paid fax for transmission - Check workflow, payment, and delivery status - Retry eligible failed faxes - Cancel an active send while cancellation is still possible ## Tools - `start_session` — Create or resume a PromptFax MCP session. - `attach_document` — Bind a PromptFax document or HTTPS PDF URLs to an MCP session. - `get_quote` — Create a fax quote from a session, document, or HTTPS PDF URL. - `checkout` — Open Stripe Checkout after the user accepts a quote. - `send_fax` — Queue a paid fax for transmission. - `get_status` — Fetch workflow, payment, and transmission status. - `retry_failed_fax` — Prepare a retry flow after a retry-eligible failed fax. - `cancel` — Cancel the active send while cancellation is still possible. ## Common use cases - Sending a one-off medical record, referral, or intake form to a clinic's fax line. - Returning a signed contract to a small business or law office that still operates by fax. - Sending insurance claim forms, prior-authorization paperwork, or appeal letters. - Sending a benefits or HR form to a payroll vendor that requires fax submission. - Sending court filings or notarized documents to a filing office. ## Data handling PromptFax does not require an email address, does not provision a PromptFax account, and stores uploaded documents only as long as the fax workflow needs them. Server-side working copies are deleted after transmission. The browser-local delivery report persists for up to 24 hours unless cleared sooner. PromptFax is outbound-only and currently supports US fax numbers only. Payments are processed by Stripe for Cogint Labs LLC. ## Links - Homepage: https://promptfax.app/ - MCP endpoint: https://promptfax.app/mcp - Setup docs: https://promptfax.app/mcp-setup - Tool catalog: https://promptfax.app/mcp-tools - Demo: https://promptfax.app/mcp-demo - Pricing: https://promptfax.app/pricing - Privacy: https://promptfax.app/privacy - Terms: https://promptfax.app/terms