"Gcore" matching MCP servers:

Security analysis for Python codebases through the guard-core engine: SecurityConfig validation that catches keys pydantic silently drops, docs search over the vendored corpus, live detection probing, and verified setup guidance for Python, Typescript, Rust, PHP and Go adapters.

Reputation scoring for AI agent wallets on Base. 9 tools for trust scores, fraud checks, blacklist lookups, leaderboard, badge generation, and agent registration with x402 payment verification.

Experimental Python MCP server exposing traceguard_shield_exec to evaluate proposed tool calls through an authorization hook. Returns approval or rejection messages over stdio; it does not execute the requested tools.

Deterministic AI safety policy engine with Z3 formal verification. Write, verify, simulate, and enforce machine-verifiable safety constraints for AI agents. Completely outside the LLM.

Provides comprehensive management of Microsoft 365 services including Exchange, SharePoint, Teams, Azure AD, Intune device management, security & compliance frameworks, and universal access to 1000+ Microsoft Graph API endpoints with advanced features like batch operations, delta queries, and real-time webhooks.

Adds a responsible-AI safety layer to any agent by exposing RAIL Score's evaluation, agent-guardrail, and compliance capabilities as MCP tools, enabling content scoring, injection detection, tool call evaluation, and DPDP compliance checks.

Provides AI agents with zero-cost, zero-dependency trust evaluation for domains, URLs, wallets, APIs, and IPs, returning a 0-100 score with SSL, DNS, WHOIS, security header, and content sub-scores, plus batch comparison to rank multiple targets.

A local capability layer for AI agents providing persistent memory, credential management, connectors, and activity tracking.

An MCP server that proxies tool calls to a running SentinelX Core instance with OIDC/OAuth authentication. It enables secure integration of SentinelX Core's HTTP agent capabilities through the MCP protocol.

Enables an agent or MCP client to scan MCP server configs and AI-agent tool manifests on demand, exposing tools that list detection rules and report hidden prompt injections, data-exfiltration attempts, embedded secrets, deceptive Unicode, unpinned packages and shell-launching tools. Each finding comes with a severity and location so risky tool descriptions can be caught before an attacker exploits them.

Enables AI agents to query trust scores and security reviews for MCP servers before connecting, helping assess safety via a composite score and letter grade.

Deterministic zero-trust policy enclave, fail-closed schema validator, DPDP Act 2023 PII sanitizer, and cryptographic WORM audit ledger for MCP tools.

Provides shared MCP-server machinery for Flask apps, including streamable HTTP transport, token-based auth, caller identity resolution, tool registry with permissions, and audit logging, enabling developers to build consistent and secure MCP servers.

A production-ready MCP gateway and control plane that provides credential vault, policy engine, audit logging, and managed runtime for routing tool calls between AI agents and downstream MCP servers.

A governed MCP server that enforces a trust layer between AI agents and databases, requiring sign-off on joins and metrics and producing auditable receipts for every query.

MCP server for managing Microsoft Intune and Entra ID via the Microsoft Graph API, offering 34 tools for device, app, compliance, security, identity, and reporting operations.

The guarddog that watches your AI and stops before it goes rogue. It combines a deterministic core and dynamic AI layer to get the best both worlds of reliability and personalizaiton.

Compiles YAML adapters or OpenAPI specs into a minimal MCP tool surface that exposes only declared capabilities to agents, with risk-tiered execution, human approval queues, credential brokering, prompt-injection sanitising and NIST AU-3 audit logging. This lets operators put scoped identity, permissions and kill switches in front of any API so agents can call exactly the tools they need and nothing more.

Enables Claude Code, Cursor, and other agents to ingest and query shared memory through scoped, expiring capability tokens. Each read and refusal is checked in the database and recorded in an audit log.

Model Context Protocol server for real-time 5G DDoS detection and response.