AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Security & Safety/
helio
helio logo

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
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#Security
$ Install
$ npx @gethelio/proxy init
↗ Visit site★ GitHub
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

⚡Top VS:
VSsatgate★11→VSplatform★15→VSHealthClawGuardrails★31→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
scopegate
★18
→
satgate logo
satgate★ 11
The Economic Firewall for AI Agent Requests
VSCompare→
platform logo
platform★ 15
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard demo
VSCompare→
HealthClawGuardrails logo
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.
VSCompare→
scopegate logo
scopegate★ 18
AI Access Proxy Layer — granular permission gateway for AI agents. Connect services, define scopes, get an MCP endpoint.
VSCompare→
tsidp logo
tsidp★ 684
A simple OIDC / OAuth Identity Provider (IdP) server for your tailnet.
VSCompare→
DashClaw logo
DashClaw★ 313
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
VSCompare→
wirken logo
wirken★ 192
The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.
VSCompare→
sourcerykit logo
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 →
gethelio /
helio
↗

Governance proxy for MCP: block or hold AI agent tool calls on their arguments, route approvals with the arguments shown, enforce rules the model cannot argue with, require prerequisites, cap cumulative spend across tools and servers, and audit every call. No changes to agent code or MCP servers.

14Apache-2.0
Last commit1d ago
StatusActive
CategorySecurity & Safety
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

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

Claim $200 Free Credit