"SAP" matching MCP servers:

Enables AI agents to securely read and write SAP ABAP development objects via the ADT REST API, enforcing policy-based guardrails such as package/namespace allow-lists, read-only mode, human approvals, and audit logging.

Connects Claude to SAP Cloud Platform Integration (CPI) to diagnose failed messages, review iFlows, deploy artifacts, and check credentials directly from your conversation.

Enables MCP clients to perform administrator-approved, read-only SAP WebGUI lookups of DDIC table fields, data elements, domains, and displayed source over BTP principal propagation. Live reads are disabled by default and require each exact object to be approved and each verified principal mapped to an expected SAP user.

An MCP server over Streamable HTTP that exposes two SAP help-desk operations to an AI agent: sap_reset_password and sap_unlock_users.

Enables conversational management of SAP BTP cloud infrastructure, security, and entitlements through natural language via AI agents.

Enables querying SAP Security Note metadata including Patch Day releases, CVSS scores, CVEs, affected components, and actively-exploited status via the Model Context Protocol.

Enables AI assistants to perform real-time SAP security audits and risk assessments by analyzing user roles, system parameters, and segregation of duties via RFC integration. It provides 17 specialized tools for monitoring security compliance and generating comprehensive audit reports directly from SAP systems.

Backend server that issues and validates alphanumeric software licenses tied to hardware IDs for SAP MCP servers (hana-b1, sap-btp, sap-cpi), storing products, licenses, and telemetry in PostgreSQL with online validation of expiry, revocation, and hardware matching.

Exposes 79 cybersecurity skills and 12 orchestrator agents over MCP, with a typed 11-field output contract, an enforced resolvable-evidence gate (no verdict without a resolvable source), and human-approval gating for every mutating action. Apache-2.0, stdlib-only.

Provides read-only access to manufacturing plant data from Excel or SAP S/4HANA, enabling natural-language queries for OEE, downtime Pareto, late work orders, scrap, and inventory alerts. It enforces data classification, masking, row limits, and audit logging for safe Claude/MCP client access.

Enables LLM clients to safely perform file operations such as create, read, edit, delete, move, copy, and more, with every path checked against an explicit permission database managed through a desktop GUI.

Enables LLM clients to read and modify MS-SQL, PostgreSQL, MySQL/MariaDB and SQLite databases through 38 MCP tools, with every table, view, function and procedure gated by explicit permission rules that deny by default. Ships with a desktop GUI for authoring rules, approving destructive operations and auditing what the model did.

Exposes SAP Cloud Integration OData APIs as MCP tools, letting AI assistants list, inspect, create, update, and delete integration packages, iFlows, message processing logs, message stores, log files, security artifacts, and partner directory entries through natural language. All tools are declared in a single JSON config and served by odata-mcp-proxy with OAuth2 authentication via the BTP Destination Service.

Integrates OWASP ZAP security testing with AI assistants through MCP, enabling automated vulnerability scanning and AI-powered security analysis during development. Supports multiple scan types including active, passive, and AJAX spider scans with real-time status updates.

Enables interaction with the Huntress SAT API to manage security awareness training, including learners, phishing campaigns, and training assignments. It supports OAuth2 authentication and optional role-based access control for secure organizational management.

MCP proxy server for SAP ABAP ADT that adds JWT authentication and forwards requests to target MCP servers.

Enables auditing an MCP server's declared capabilities, sealing them into a commit-able lock file, and verifying later versions for changes or escalated risk, without invoking any tools and with minimal environment exposure.

Exposes the SAI Verified Agent Protocol as MCP tools so clients acting in agent, verifier, or executor scopes can prepare and submit actions and proposals, submit attestations, and execute approved payments, with status and receipt lookups. Scope selection limits which tools are available per session.

Enables content inspection, sanitization, containment, and quarantine for LLM security, preventing prompt injection and credential leaks.

Local governance layer for AI-assisted development, providing human authorization gates, policy enforcement, change approval workflow, and rollback capabilities through a universal MCP server.