JanuScope

Active·★ 32·AGPL-3.0·Updated 2026-10-16

JanuScope is a local proxy that wraps any Model Context Protocol (MCP) server, enhancing AI tool usage with critical security features. It enforces policies, redacts sensitive data, audits all calls, and pre-injects database schemas to improve LLM accuracy and safety.

#MCP Proxy#LLM Security#Policy Enforcement#Data Redaction#Audit Logging#Schema Injection#API Governance

Best by use case About Contact Advertise Privacy Policy Terms of Use QYS GitHub Buy me a coffee ☕

Browse by Category

MCP Servers Code Assistant Workflow Automation RAG / Knowledge Base Multi-Agent Browser Automation LLM Infra Dev Tooling Observability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

#Local-first

$ Install

$ npx -y januscope --config postgres-crystaldba

↗ Visit site ★ GitHub

Features

01Policy Enforcement and Tool Blocking

02Sensitive Data Redaction

03Comprehensive Audit Logging

04Database Schema Injection

05Local-First and No Hosted Gateway

Compatibility

Node.js

Runtime

Verified via docs

PostgreSQL

Database

Verified via docs

MongoDB

Database

Verified via docs

GitHub

Source Control

Verified via docs

Stripe

SaaS API

Verified via docs

Filesystem

Local Access

Verified via docs

Quick start

$ npx -y januscope --config postgres-crystaldba

Use cases

↳Securing AI Agent Interactions with Databases

↳Compliance and Audit Trails

↳Enhancing LLM Efficiency with External Tools

↳Protecting Sensitive Data from LLM Exposure

↳Centralized Policy Management for Diverse APIs

Alternatives

⚡Top VS:

VSmcp-hangar★18→VSheddle★14→VSDashClaw★313→VS

Comments

No comments yet. Be the first!

On this page

01Features 02Compatibility 03Quick start 04Use cases 05Alternatives

guardana

★251

→

mcp-hangar★ 18

MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.

VSCompare→

heddle★ 14

Heddle — The policy-and-trust layer for MCP tool servers. Turn YAML configs into validated, policy-enforced MCP tools.

VSCompare→

DashClaw★ 313

🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.

VSCompare→

guardana★ 251

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

VSCompare→

agents-shipgate★ 90

The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

VSCompare→

ctrlrun★ 27

The execution safety layer for AI agents.

VSCompare→

AegisFlow★ 36

Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.

VSCompare→

sourcerykit★ 21

SourceryKit — counterspell for hallucinating agents. Python SDK that breaks the illusion on every tool call, API response, and MCP handoff before bad outputs propagate.

VSCompare→

See all alternatives →

giancarloerra /

JanuScope

↗

Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway. One YAML Lens wraps any MCP, 20 included (Postgres, MySQL, MongoDB, GitHub, Stripe, Snowflake, etc.). 84% fewer tokens, ~3x faster, holds PII leaks. AGPL or commercial.

32AGPL-3.0

Last commit1w ago

StatusActive

CategorySecurity & Safety

Links

Documentation↗Discussion↗Issues↗Releases↗

Cloud Infrastructure

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit