helio
Active·★ 14·Apache-2.0·Updated 2026-10-22
Helio is an open-source MCP proxy that provides governance for AI agents by enforcing policies on tool calls, managing spend, and routing approvals. It operates between agents and their tools, ensuring useful autonomy without unlimited authority across various platforms and frameworks.
#MCP Proxy#AI Agent Governance#Tool Call Policy#Spend Control#Audit Trail#Access Control#Approval Workflows#Security
01
Features
01Declarative Policy Engine: Define YAML rules for tool names, inputs, and state, with hot-reloading and dry-run mode.
02Cross-Tool Spend Budgets: Aggregate and cap spending across multiple tools and MCP servers with break-glass approvals.
03Approval Workflows: Route sensitive tool calls to Slack, webhooks, or the dashboard for human review and approval.
04Comprehensive Audit Trail: Record all tool calls, policy decisions, and responses for full traceability and searchability.
05Evidence Grounding: Require fresh, application-provided evidence to validate actions, preventing accidental skips.
02
Compatibility
Node.js
Runtime
Verified via docs
Python
SDK
Verified via docs
MCP (Model Context Protocol)
Protocol
Verified via docs
AI Agents (Claude, ChatGPT, LangChain, CrewAI, AutoGen)
Frameworks
Verified via docs
03
Quick start
1
$ npx @gethelio/proxy init
04
Use cases
↳Prevent unauthorized API calls and modifications to production records by AI agents.
↳Establish centralized governance for AI agents operating across multiple platforms like Claude, ChatGPT, and LangChain.
↳Implement human-in-the-loop approval workflows for sensitive or destructive agent operations.
↳Manage and cap cumulative spending by AI agents across various integrated tools and services.
05
Alternatives
platform★ 15
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard demo
HealthClawGuardrails★ 31
Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
scopegate★ 18
AI Access Proxy Layer — granular permission gateway for AI agents. Connect services, define scopes, get an MCP endpoint.
DashClaw★ 313
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
Comments
Log in to leave a comment
No comments yet. Be the first!