Vai al contenuto principale
Public AI connector guide

Connect your AI assistant to Kernion safely

Use Hermes, Claude Code, or any MCP-compatible client to inspect, draft, QA, and operate Site Studio through scoped connector presets — without handing an agent a platform-admin session.

Sign in to connect See how it works

Agency partners issue from their agency Integrations page. Platform support issues tenant-limited support connectors from the agency cockpit.

Quickstart

Three safe steps, no public secrets

Use native browser approval for one assistant installation or profile, then choose site coverage at consent. No static key or model helper is needed. A local server name does not select a site.

1

Choose an assistant

Use native browser approval for one assistant installation or profile, then choose site coverage at consent. No static key or model helper is needed. A local server name does not select a site.

2

Site coverage

Approve an assistant installation for the sites and permissions shown below. Access is checked against the current role on each site on every call. Revoke it from account connections at any time.

3

Check recorded activity

Return to Connected AI assistants after approval. Authorization is separate from verified use; only a successful recorded tool action proves activity.

Presets

Use presets instead of hand-picking dangerous checkboxes

Authenticated screens still show advanced capability details. The normal path is preset-first: draft-only by default, explicit publish power only when needed.

Read + QA

Inspect selected sites, schemas, and QA findings without editing drafts.

Risk posture

Safest posture for audits, support triage, and tool discovery.

Capabilities

  • studio.read
  • studio.schema.read
  • studio.qa.run

Draft editor

Recommended first

Create and repair Site Studio drafts while keeping visitor-visible publishing off.

Risk posture

Recommended default. Humans still review and publish live changes.

Capabilities

  • studio.read
  • studio.schema.read
  • studio.draft.blocks.write
  • studio.draft.content.write
  • studio.qa.run

Designer

Draft content plus theme, media, and navigation changes for selected sites.

Risk posture

Can reshape the visitor journey. Review carefully before publishing.

Capabilities

  • studio.read
  • studio.schema.read
  • studio.draft.blocks.write
  • studio.draft.content.write
  • studio.qa.run
  • studio.theme.write
  • studio.media.write
  • studio.navigation.write

Publisher

Draft editing plus explicit permission to publish public Site Studio changes.

Risk posture

Visitor-visible. Use short TTLs, one operator per credential, and audit every key.

Capabilities

  • studio.read
  • studio.schema.read
  • studio.draft.blocks.write
  • studio.draft.content.write
  • studio.qa.run
  • studio.publish

Agency operator

Agency workspace operations such as client, app, and readiness management.

Risk posture

Can affect client onboarding and readiness workflows. Keep tenant allowlists tight.

Capabilities

  • studio.read
  • studio.schema.read
  • studio.draft.blocks.write
  • studio.draft.content.write
  • studio.qa.run
  • apps.read
  • apps.manage
  • readiness.read
  • readiness.manage
  • clients.view
  • clients.manage
Publisher rule: Publishing changes what visitors see. Do not grant Publisher unless the operator explicitly owns public launch responsibility for that site.

1. Connect site tools

Use native browser approval for one assistant installation or profile, then choose site coverage at consent. No static key or model helper is needed. A local server name does not select a site.

Hermes Desktop

Open in Hermes Desktop needs the hermes:// link handler that Hermes Desktop registers when it is installed on this computer. If nothing opens — or the wrong app opens — update Hermes Desktop with its normal updater, or copy the setup instructions below. This site cannot detect, install or register that handler.

This link registers this site's MCP address in the Hermes app under the local name kernion. Hermes asks for its own confirmation, and this site cannot install or open software silently.

Open in Hermes Desktop

Install link

hermes://mcp/install?name=kernion&config=eyJ1cmwiOiJodHRwczovL2FnZW5jeS5rZXJuaW9uLmlvL21jcCIsImF1dGgiOiJvYXV0aCJ9

Run in a terminal on the computer where this assistant is installed.

hermes mcp add kernion --url 'https://agency.kernion.io/mcp' --auth oauth
hermes mcp login kernion

After sign-in, verify the connection

hermes mcp test kernion

Account connections

Use native browser approval for one assistant installation or profile, then choose site coverage at consent. No static key or model helper is needed. A local server name does not select a site.

Sign in to connect
Sign in to connect
Other clients and manual setup
Choose an assistant

Merge this entry into the selected client's user configuration, keeping existing entries. Then run the login command in that same client profile.

Hermes: config.yaml in the active Hermes profile.

Merge this entry into the selected client's user configuration, keeping existing entries. Then run the login command in that same client profile.

mcp_servers:
  kernion:
    url: "https://agency.kernion.io/mcp"
    auth: oauth

Run in a terminal on the computer where this assistant is installed.

hermes mcp add kernion --url 'https://agency.kernion.io/mcp' --auth oauth
hermes mcp login kernion
Advanced: static keys and manual setup

Client setup

Use the live domain and an environment variable

After issuing a credential, store the bearer value as AGENCY_CONNECTOR_MCP_BEARER. These examples deliberately show only the variable reference.

Add this under mcp_servers. Store the bearer value in the process environment or an env file loaded by Hermes.

# ~/.hermes/config.yaml
mcp_servers:
  kernion_site:
    transport: http
    url: https://agency.kernion.io/mcp
    headers:
      Authorization: "Bearer ${AGENCY_CONNECTOR_MCP_BEARER}"

Security model

  • No keys are issued on this public page. It teaches the flow only.
  • Raw bearer keys are shown only once on authenticated issuance screens.
  • Capabilities are stored with the credential and re-checked against the live role on every call.
  • Draft writes stay private until someone with explicit publish power publishes them.
  • Every tool call is rate-limited, audited, and tied to the credential that made it.

Troubleshooting

Common connector failures are intentional guardrails

Most setup failures are scope, credential, or transport mismatches. Fix the boundary rather than broadening the connector blindly.

401

Invalid, missing, revoked, or expired token

Re-copy the environment variable from your secret store, rotate the connector if the raw key was lost, and confirm the Authorization header uses Bearer plus the variable value.

403

Capability or tenant scope denied

Use a higher preset only when the operator truly needs it, or add the exact tenant site to the credential allowlist.

405

Wrong transport method

The MCP endpoint is Streamable HTTP over POST. GET is intentionally not a server-sent event stream.

Ready to connect an agent?

Return to Connected AI assistants after approval. Authorization is separate from verified use; only a successful recorded tool action proves activity.

Sign in See plans