MCP Server Scf README

The full upstream README, mirrored for reference. Install config, tool schemas, adoption signals and our own overview live on the MCP Server Scf listing page.

SCF Controls Platform β€” MCP server for security compliance, frameworks, and risk management for AI agents. Maintained by ComplianceGenie.io.

mcp-server-scf

CI Security OpenSSF Scorecard Socket.dev

npm version npm downloads install size License: MIT MCP

MCP Registry

TypeScript Node.js

Security compliance controls, frameworks, and risk management for AI agents.

Give your AI assistant access to 1,451 SCF security controls, 354+ framework mappings (NIST 800-53, ISO 27001, SOC 2, FedRAMP, GDPR), evidence tracking, risk registers, and vendor risk management β€” all through the Model Context Protocol.

Built for the SCF Controls Platform. Maintained by ComplianceGenie.io.

πŸ†• The platform is now open-source, self-hosted software. The SCF Controls Platform β€” SCF-native GRC tooling for the free Secure Controls Framework content β€” is published under AGPL-3.0 at scf-controls-platform-oss. Companies download and host it themselves via Docker Compose.

Having trouble? β†’ docs/troubleshooting.md Β· API key setup β†’ docs/authentication.md Β· How it works β†’ docs/architecture.md


Overview

mcp-server-scf connects AI assistants to the SCF Controls Platform via MCP, enabling natural language interaction with your compliance program. Your AI can browse the full SCF control catalog, track implementation progress, manage evidence collection, assess risks, and monitor third-party vendors β€” all without leaving your editor or chat.

42 tools over 225 platform operations, in 16 groups. Each tool is one noun and direction β€” scf_vendor_read, scf_vendor_write β€” and its method argument picks the operation; the method description explains each one. Read tools are readOnlyHint: true, so a client can allow them all at once.

Only the core groups are in the tool list at startup (26 tools, about 27k tokens of schema instead of 71k). Call scf_load_tools with the groups you need β€” or all β€” and the rest appear; the server sends notifications/tools/list_changed. A client that ignores that notification can set SCF_LOAD_ALL_TOOLS=true to get everything up front. Per-group docs list every method with its parameters; docs/migration-consolidation.md maps each pre-v4 tool name to its tool and method.

GroupLoadedOperationsTools
catalogcore8scf_catalog_read
controlscore15scf_control_read, scf_control_write
evidencecore25scf_evidence_read, scf_evidence_write, scf_evidence_file_read, scf_evidence_file_write, scf_list_evidence_tasks, scf_evidence_task_write
assessmentscore17scf_assessment_read, scf_assessment_write
riskcore19scf_risk_read, scf_risk_write, scf_custom_risk_read, scf_custom_risk_write
vendorscore23scf_vendor_read, scf_vendor_write, scf_vendor_record_write
systemscore19scf_system_read, scf_system_write, scf_capability_theme_read
organizationcore12scf_org_read, scf_update_org_settings, scf_user_read, scf_mark_notifications_read
teamson demand11scf_team_read, scf_team_write
collaborationon demand7scf_collaboration_read, scf_collaboration_write
documentson demand15scf_document_read, scf_document_write
engagementson demand16scf_engagement_read, scf_engagement_write
assuranceon demand19scf_assurance_read, scf_assurance_write
catalog-reconciliationon demand9scf_catalog_reconciliation_read, scf_catalog_reconciliation_write
webhookson demand6scf_webhook_read, scf_webhook_write
journeyon demand4scf_journey_read, scf_journey_write

Try it with MCP Inspector

Kick the tires without adding the server to a client β€” MCP Inspector launches a local UI that introspects every tool, its schema, and its description:

Terminal
npx @modelcontextprotocol/inspector npx -y mcp-server-scf

Inspector opens on http://localhost:6274 and connects to mcp-server-scf over stdio. You'll see the 26 core tools (set SCF_LOAD_ALL_TOOLS=true for all 42), each with a method picker and its Zod schema rendered as a live form.

Live tool calls need your instance's URL and an API key β€” export SCF_API_URL and SCF_API_KEY in the same shell before launching Inspector, or set them under the "Environment Variables" tab inside the Inspector UI. Without them, you can still browse schemas and descriptions; tool calls return a configuration error.


Quick Start

1. Self-host the platform & get an API key

The SCF Controls Platform is open-source software you host yourself β€” there is no sign-up. Deploy it from scf-controls-platform-oss (a Docker Compose stack with bundled PostgreSQL, Redis, and MinIO), then:

  1. Set an API_KEY in the platform's .env (generate one with openssl rand -hex 32), or create a key in Settings β†’ API Keys once the app is running.
  2. Note your instance's API URL β€” http://localhost:8000 by default, or your deployed host.

Use that key as SCF_API_KEY and the instance URL as SCF_API_URL (see Configuration).

2. Install β€” one-click

Pick the route for your client.

Claude Desktop β€” the one-click path is the signed .mcpb Desktop Extension below. Claude Desktop does not register a custom URL scheme, so there is no clickable deeplink; instead you drag the .mcpb onto Settings β†’ Extensions and paste your API key once. See anthropics/claude-code#26952 for the upstream tracking issue.

Cursor β€” click the badge below. Cursor registers the cursor:// scheme, so the deeplink opens the IDE with the server config pre-filled:

Install in Cursor

After install, edit the pre-filled SCF_API_URL to point at your instance β€” there is no hosted default.

Prefer to edit config by hand, or on a client without a deeplink (Windsurf, Docker)? See 3. Manual config below.

Claude Desktop Extension (.mcpb)

For Claude Desktop β‰₯ 0.11.0, the easiest install is a signed .mcpb bundle β€” no JSON editing, no npx runtime, no Node required on the host:

  1. Download mcp-server-scf-<version>.mcpb from the latest GitHub release.
  2. Double-click the file (or drag it onto Claude Desktop β†’ Settings β†’ Extensions).
  3. When prompted, paste your scf_… API key. It's stored in your OS keychain, not in a config file.
  4. Claude Desktop restarts the server and the core tools are available; ask for more with scf_load_tools.

To uninstall or update the API key later: Settings β†’ Extensions β†’ SCF Controls Platform β†’ Configure.

3. Manual config

Claude Desktop β€” edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

config.json
{
  "mcpServers": {
    "scf": {
      "command": "npx",
      "args": ["-y", "mcp-server-scf"],
      "env": {
        "SCF_API_KEY": "your_api_key_here",
        "SCF_API_URL": "http://localhost:8000"
      }
    }
  }
}

Claude Code:

Terminal
claude mcp add scf -- npx -y mcp-server-scf
export SCF_API_KEY="your_api_key_here"
export SCF_API_URL="http://localhost:8000"

Cursor / Windsurf β€” same JSON shape as Claude Desktop in .cursor/mcp.json (or the equivalent Windsurf path).

Docker:

config.json
{
  "mcpServers": {
    "scf": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "SCF_API_KEY", "-e", "SCF_API_URL", "markac007/mcp-server-scf"],
      "env": {
        "SCF_API_KEY": "scf_your_api_key_here",
        "SCF_API_URL": "https://scf.your-domain.example"
      }
    }
  }
}

Configuration

VariableRequiredDefaultDescription
SCF_API_KEYYesβ€”API key from your self-hosted platform instance
SCF_API_URLYesβ€”Base URL of your self-hosted platform (e.g. http://localhost:8000). The former hosted default is decommissioned.

SCF_LOAD_ALL_TOOLS=true lists every tool at startup instead of the core groups β€” for a client that does not act on notifications/tools/list_changed after scf_load_tools.

Remote (Streamable HTTP): mcp-server-scf-http serves the same tools by URL for a hosted, multi-user deployment. No server-side key: each caller sends their own Authorization: Bearer scf_…, forwarded to the one platform in SCF_API_URL. Connect with claude mcp add --transport http scf https://<host>/mcp --header "Authorization: Bearer scf_…". Details and a hardened Compose example in docs/authentication.md.

Example Prompts

Once connected, try asking your AI assistant:

  • "What NIST 800-53 controls apply to access control?"
  • "Show me my organization's control implementation progress."
  • "List all critical vendors and their risk scores."
  • "Create a risk assessment for our cloud migration."
  • "What evidence do I need to collect for SOC 2 audit?"
  • "Show the 5x5 risk matrix for my organization."
  • "Run a DPSIA on our cloud provider vendor."

More examples live in each per-domain doc under docs/tools/.


Documentation


Security

  • API keys are never logged or included in error messages.
  • Keys are SHA-256 hashed server-side. Use HTTPS for any instance reachable beyond localhost.
  • Rate limiting: 100 req/min read, 20 req/min write.
  • Multi-tenant β€” all operations scoped to your organization.
  • npm package published with provenance attestation via OIDC trusted publishing.
  • CI includes Gitleaks secret detection, CodeQL analysis, and Semgrep SAST.

See SECURITY.md to report a vulnerability.


Privacy Policy

mcp-server-scf is a stateless connector β€” it stores no user data itself. All data flows directly between your MCP client and your own SCF Controls Platform instance, authenticated with your API key; nothing is sent to, or retained by, any third party. See the full privacy policy for details.


Development

bash
git clone https://github.com/MarkAC007/mcp-server-scf.git
cd mcp-server-scf
npm install
npm run build
npm run dev        # Watch mode
npm run lint       # ESLint
npm test           # Vitest

Testing with MCP Inspector

bash
SCF_API_KEY=scf_your_key npx @modelcontextprotocol/inspector node build/index.js

Contributing

Contributions welcome! Please read CONTRIBUTING.md before submitting PRs.

This project follows the Contributor Covenant β€” see CODE_OF_CONDUCT.md. By participating, you are expected to uphold this code.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

MIT β€” see LICENSE.


Links