Explore

Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM prompt exchanges

Skill·Link only·★ 7

Zero-Trust Enterprise AI Security Gateway & Real-Time PII/PHI Masker for Atlassian Rovo Agents, Jira, Confluence, and IDEs (Cursor, Claude).

Skill·MIT·Few stars·No key

The control plane for your MCP servers - aggregate, route, and govern every MCP upstream from one self-hosted Go binary.

Go·MIT·★ 1·Few stars·No key

Salesforce sandbox seeding CLI + MCP server — SOQL-driven org-to-org copy with dependency-graph walking, FK remapping, deterministic PII masking, and a hard AI-never-sees-your-data boundary.

Node.js·Apache-2.0·Few stars·No key

Experimental configuration scanner for Model Context Protocol (MCP) configs. For demos, training, and learning secure MCP practices.

Go·MIT·★ 2·Few stars·No key

Comprehensive MCP memory plugin — AI coding memory, personal life memory (habits, experiences, knowledge, accounts), scheduled review, and cross-module linking

Python·MIT·Few stars·No key

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code chan

Python·MIT·★ 18·No key

Zero-dependency in-memory PII airgap & reversible masking proxy for Cloud LLMs (GDPR Art. 32 compliant MCP server)

Skill·Apache-2.0·★ 4·Few stars·No key

Enterprise Regulatory Compliance & Multi-Pattern PII Redaction Sentinel (inspired by Tencent Cloud Data Governance & GDPR/HIPAA Enterprise Policies). Detects and sanitizes personally identifiable info

Skill·MIT·★ 7·No key

Enterprise Regulatory Compliance & Multi-Pattern PII Redaction Sentinel (inspired by Tencent Cloud Data Governance & GDPR/HIPAA Enterprise Policies). Detects and sanitizes personally identifiable info

Skill·MIT·★ 7·No key

🛡️ A Model Context Protocol (MCP) server for AI security: detects prompt injection, masks sensitive data (PII), and audits insecure MCP configs.

Node.js·MIT·★ 3·Few stars·No key

Enterprise MCP (Model Context Protocol) Gateway — governance, auditing, and data protection for MCP traffic in regulated environments

Python·MIT·★ 1·Few stars·No key

Policy gateway for MCP: authenticate each agent, enforce least-privilege tools, mask and strip responses, and write a tamper-evident audit log.

Python·Apache-2.0·Few stars·No key

An open-source gateway for the Model Context Protocol. Register upstream MCP servers once, then curate their tools, resources and prompts into virtual MCP servers: one endpoint per agent or team, each

Skill·Apache-2.0·★ 2·Few stars·No key

A secure, production-grade Model Context Protocol (MCP) server providing read-only PostgreSQL query execution with automatic PII masking, session-based pseudonymization, and telemetry for LLM agents.

Node.js·MIT·Few stars·No key

Persistent, portable, shared memory for Massive Intelligence (IM) agents: pluggable stores, a deterministic identity seed stable across model swaps, masking and residency, and Ed25519-signed, SHA-256-

Node.js·Apache-2.0·★ 1·Few stars·No key

Read-only MCP server for Apache NiFi, ClickHouse and Kafka: OIDC or proxy auth, per-user audit, secret masking, two-lock read-only

Python·Apache-2.0·Few stars·No key

Zero-trust PostgreSQL/SQLite guard, live PII masking, zero-downtime migration checks

Python·MIT·Few stars·No key

A highly modular, pluggable RAG system and knowledge bridge built for the Model Context Protocol (MCP).

Skill·AGPL-3.0·★ 2·Few stars·No key

MCP server giving AI agents safe, audited access to a business database — SQL guardrails, PII masking, two-step writes. Zero native dependencies.

Node.js·MIT·Few stars·No key

MCP server giving AI agents a hardware constant-time, masking, and patch-completeness checker they cannot argue with

Python·Apache-2.0·Few stars·No key

Gatehouse: a read only MCP gateway that lets Claude query a business CRM safely. Per key scopes, field masking, rate limits, a full audit log and a live attack suite.

Python·MIT·Few stars·No key