helio

<p align="center">
  <h1 align="center">Helio</h1>
  <p align="center">Open-source governance for MCP agents: useful autonomy without unlimited authority.</p>
</p>

<p align="center">
  <a href="https://github.com/gethelio/helio/actions/workflows/ci.yml"><img src="https://github.com/gethelio/helio/actions/workflows/ci.yml/badge.svg" alt="CI" /></a>
  <a href="https://github.com/gethelio/helio/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License" /></a>
  <a href="https://www.npmjs.com/package/@gethelio/proxy"><img src="https://img.shields.io/npm/v/@gethelio/proxy.svg" alt="npm version" /></a>
  <a href="https://mcpservers.org/servers/gethelio/helio"><img src="https://mcpservers.org/badge.svg" alt="Listed on mcpservers.org" /></a>
  <a href="https://glama.ai/mcp/servers/gethelio/helio"><img src="https://glama.ai/mcp/servers/gethelio/helio/badges/score.svg" alt="Helio MCP server on Glama" /></a>
  <a href="https://registry.modelcontextprotocol.io/v0.1/servers/so.helio%2Fhelio/versions/latest"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fregistry.modelcontextprotocol.io%2Fv0.1%2Fservers%2Fso.helio%252Fhelio%2Fversions%2Flatest&query=%24.server.version&label=MCP%20Registry&logo=modelcontextprotocol" alt="Helio on the MCP registry" /></a>
</p>

<p align="center">
  <a href="./docs/getting-started.md">Getting Started</a> · <a href="./docs/configuration.md">Docs</a> · <a href="./CONTRIBUTING.md">Contributing</a>
</p>

---

Helio is an MCP proxy that sits between your AI agents and the tools they use. Every tool call passes through Helio, which enforces policies, requires prerequisites, checks evidence, routes approvals, caps cumulative spend, and records everything - **without changing your agent code or your MCP servers.**

The `2026-07-28` MCP revision made the protocol itself stateless: no handshake, no
protocol-level sessions, cross-call state carried as handles the model passes between
tools. That pattern works for application state and fails for governance state,
because a budget key the model can see is a budget key the model can change. Helio
keeps session identity, budgets, and evidence in the proxy, outside the agent's
context, which is why those controls still mean something after the protocol
stopped tracking sessions. See
[stateless protocol, stateful governance](docs/policies.md#stateless-protocol-stateful-governance).

```bash
npx @gethelio/proxy init
```

`@gethelio/proxy` is the only Node package you install. It ships the proxy runtime and bundled dashboard UI assets together.

```
ALLOW      read_customer
APPROVE    refund > £50
DENY       production.delete
BUDGET     £500/day across matching paid tools
REQUIRE    order.lookup succeeded before refund
```

## Why Helio?

Your agent just called an API you didn't expect. It spent money you didn't authorize. It modified a production record you can't easily undo.

Model providers are building governance for their own platforms but your agents run across Claude, ChatGPT, LangChain, CrewAI, and custom frameworks. No single platform governs the full picture. And none of them govern what happens in downstream systems like Stripe, Salesforce, or GitHub.

Helio governs what agents **do to the rest of the world** across any MCP-compatible agent, any tool, any platform.

A rule in Helio cannot be forgotten and cannot be weakened silently. It is not in the model's context, so a long session cannot evict it and an injection cannot argue it away, and enforcement is in the path rather than in the prompt: a tool call routed through Helio is decided before it is forwarded, whatever the model has been told. Every attempt to reload the policy file, including one that removes a rule, is an audit record, and every record carries the hash of the config in force when it was written, so a change shows against the decisions made under it. The "cannot be weakened silently" claim has one condition, stated under [Enforcement grades](#enforcement-grades).

## How It Works

<p align="center">
  <img src="docs/images/how-it-works.svg" alt="MCP clients send tool calls through Helio — which applies its policy engine, evidence grounding, approval workflows, cross-tool spend budgets, rate and spend limits, audit trail, and self-repair feedback — before forwarding them to MCP servers. An optional thin Python SDK connects to Helio over a sideband." width="900" />
</p>

Two integration paths:

1. **Proxy only**: Point your MCP client at Helio instead of your MCP server. Zero code changes. Immediate governance.
2. **Proxy + SDK**: Add the thin Python SDK to annotate tool calls with evidence context and action dependencies. Richer governance, under 500 lines of code.

### Enforcement grades

Helio governs at the strongest grade each path physically allows, and records it per call:

- **Structural** (stdio MCP) — Helio owns the child process it spawned, so nothing on the MCP path routes around it; a co-located process that can run the same command line is outside this grade (see the note below).
- **Network** (HTTP MCP) — structural given you control the upstream's egress.
- **Host-enforced** (hook adapters via the [adapter API](docs/adapter-api.md), e.g. OpenClaw) — for frameworks that run tools in-process and expose hooks rather than an MCP transport. The framework's hook gate enforces; Helio decides. This is a cooperative, lower grade than the proxy path, and Helio labels it as such rather than overclaiming. Helio's decisions still cannot be evicted from the agent's context or prompt-injected, and any attempt to route around them is visible in the audit trail.

All three grades assume the proxy's config, secret, and audit store are outside the agent's reach. In the default local install they are not: the proxy runs as the same user as the agent. [SECURITY.md](SECURITY.md#process-and-filesystem-boundaries) states the boundary and the deployments that close it. That install is also the condition on "cannot be weakened silently": a same-user agent can restart the proxy without the config pin and can edit or delete the audit file, so the reload record and the hash on every record are durable only while the agent cannot write the audit file, and the event stream and stderr are the channels that leave the box before that. Run the proxy as its own user or in its own container, as the recipes there do, and the condition falls away.

## Quick Start (5 minutes)

### 1. Install

```bash
npx @gethelio/proxy init
```

This single package includes the built-in dashboard UI bundle.

Running your agent in a container? `npx @gethelio/proxy init --sandbox` writes the sidecar layout instead; see [Running Helio as a Sidecar](./docs/deployment-sidecar.md).

Nothing governed yet? `npx @gethelio/proxy init --demo` writes a directory of sample traffic so every surface can be tried before the first real call; see [Sample traffic](./docs/demo.md).

### 2. Configure

`npx @gethelio/proxy init` already created a `helio.yaml` in your project root. Open it (e.g. `nano helio.yaml`, or in your editor) and point `upstream.url` at your existing MCP server. The singular `upstream:` form stays fully supported; to govern more than one MCP server, declare a named `upstreams:` list in its place (set exactly one of the two). Tool sets are never merged: each named upstream is served at its own `/mcp/<name>` door. See the [Configuration Reference](./docs/configuration.md#upstreams).

Not sure what the server exposes? `npx @gethelio/proxy scan --upstream http://localhost:8080/mcp` prints every tool, whether the server marks it destructive or leaves the MCP default, and the arguments a rule could match, before you write a rule and without starting the proxy.

> **Heads up — Helio starts in audit-only mode.** `init` scaffolds the `policies` section **commented out**, so out of the box Helio runs with `default: allow` and **zero rules**: it records every tool call to the audit trail but **blocks nothing**. Uncomment and edit `policies` (or paste your own rules) to start enforcing. See the [Policy Guide](./docs/policies.md) for rule syntax.

The block below is an **illustrative target** — not the file `init` writes — showing policies, budgets, audit, and a dashboard secret:

```yaml
version: '1'

upstream:
  url: 'http://localhost:8080/mcp' # Your existing MCP server
  transport: streamable-http # streamable-http (default), sse, or stdio

listen:
  port: 3000 # Helio listens here

session:
  identity: # Ordered identity sources; first match wins
    - source: header
      name: x-helio-session-id # Agent harnesses set this once per run
    - source: legacy_header # Verbatim Mcp-Session-Id (deprecation window)
  on_unresolved: deny # deny | anonymous

policies:
  default: allow

  # These rules match on tool-name globs (deny / rate-limit / spend-limit):
  rules:
    # Block destructive operations
    - match:
        tool: 'delete_*'
      action: deny
      feedback:
        message: 'Destructive operations are disabled'

    # Rate limit expensive API calls
    - match:
        tool: 'search_*'
      action: rate_limit
      limits:
        max_calls: 100
        window: 1h
        key: tool

    # Spend limit on payment tools
    - match:
        tool: 'create_payment'
      action: spend_limit
      limits:
        max_spend:
          field: '$.amount'
          limit: 5000
          currency: 'GBP'
          window: 24h

budgets:
  # One depleting pot shared by every tool that spends.
  - name: agent-payments
    limit: 50
    currency: USD
    window: session
    key: session
    on_exceed: deny # or require_approval for a break-glass ticket
    contributors:
      - match:
          tool: 'stripe_*'
        field: '$.amount'
      - match:
          tool: 'paypal_*'
        field: '$.total'

audit:
  storage: sqlite
  retention: 90d
  include_responses: true

dashboard:
  enabled: true
  port: 3100
  api_secret: '${HELIO_DASHBOARD_SECRET}'
```

Omitted f