SOJO Planning Assistant (Victoria) API
The HTTP surface for Victoria, the SOJO Planning Assistant — a LangGraph-backed agent over Sojo's production and machine-telemetry data. Publishes a public OpenAPI 3.0.3 describing non-streaming orchestration, SSE streaming chat, conversation CRUD/export, image upload and health/readiness probes, and serves a Model Context Protocol streamable-HTTP endpoint at /mcp for Claude Desktop and ChatGPT clients. Authenticated routes take a Stytch session JWT.
This API exposes 10 operations across 8 paths, organized into 4 resource areas. It is described by OpenAPI 3.0.3, at version langgraph-production.
Requests are made against 2 base URLs: https://victoria-agent.sojoshield.com, https://victoria-agent.sojoshield.dev.
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 1
SOJO Planning Assistant (Victoria) API declares
1 security scheme
for authenticating requests.
It accepts HTTP bearer tokens (JWT) (BearerAuth).
BearerAuth— Stytch session JWT. Pass as 'Authorization: Bearer '.
Paths & Operations 10
Across 8 paths, the API surfaces 10 operations — 1 DELETE, 5 GET, 1 PATCH, 3 POST. They span 4 resource areas: Chat, Conversations, Files, Health. Each is listed below with its method, path, parameters, and response codes.
Orchestration / streaming chat
Chat-history list/read/rename/delete (requires AGENTPERSISTENCEENABLED; 404 when the feature is off)
Image upload (files are uploaded via Shield, then referenced by S3 key)
Health probe
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
This is an independent, third-party profile of SOJO Planning Assistant (Victoria) API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.