MCP Auth and Scopes

Every AutoCISO MCP call authenticates with a bearer token. This page is the canonical reference for creating MCP tokens, the mcp:read and mcp:write scopes, and how your org is bound to the token.

Create a token

1. Go to Settings → API Tokens.
2. Click New token.
3. Give it a name that identifies the client (e.g., mcp-claude-desktop).
4. Select the scopes you need:
   • mcp:read — read access to all 22 read tools.
   • mcp:write — adds the risk_create_draft tool. Write implies read.
5. Click Create and copy the token immediately — it’s only shown once.

Scopes

About mcp:write

mcp:write is required for the one write tool, risk_create_draft. A token without it — or an org with write disabled — returns NOT_PERMITTED when the tool is called. This is expected behavior, not an error in your code. See MCP Errors and Retries.

Org binding — no org_id from the client

Your organization is bound to the token on the server. You never pass an org identifier:

• There is no org_id argument on any tool and no X-Org-ID header for normal tokens.
• The SDK method signatures don’t accept an org parameter — there is no way to query another tenant.

This is least-privilege by design. Issue one token per client so you can revoke a single integration without affecting the others.

Using the token

Send the token in the Authorization header on every request:

curl -s \
-H "Authorization: Bearer $AUTOCISO_MCP_TOKEN" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \
"https://autociso.io/mcp"

Token lifecycle

• Revoke a token from Settings → API Tokens when a client is decommissioned.
• If a token leaks, revoke it immediately and issue a new one.
• Because each client uses its own token, revocation is surgical — only the leaked client loses access.