Skyward MCP Server & Agent Skill

What is the Skyward API, and what can an agent read from it?

A OneRoster API for SMS 2.0 and Qmlativ, an LMS API for SMS 2.0 grade sync, and Qmlativ data available by both API and file import/export. Also supports Ed-Fi.

• API: Skyward OneRoster API; LMS API (SMS 2.0); Qmlativ APIs via the Partner Portal (Mixed)
• Access: Partner or license program
• Authentication: not published by Skyward

Districts contact their Skyward representative to obtain API access. Vendors not yet registered start in the Skyward Partner Portal (partners.skyward.com), which has how-to docs and a downloadable SDK.

Skyward does not publish its auth scheme. Its OneRoster API is certified at 1.1, and 1EdTech notes OneRoster 1.2 replaced 1.1's OAuth 1.0a with OAuth 2.0, so expect OAuth 1.0a; confirm with Skyward.

What can an agent read from Skyward?

• Class rosters — Orgs, users, classes and enrollments via the OneRoster 1.1 REST provider (certified for SMS 2.0 and Qmlativ).
• Gradebook data — OneRoster 1.1 Gradebook Pull (certified REST Data Provider role).
• Qmlativ records — Skyward states all Qmlativ data is available by API and by file import/export; details are in the Partner Portal.
• Scheduled file exports — Scheduled import/export exchanges, e.g. exporting grades to an LMS at set times.

What can an agent write to Skyward?

• Grade passback — OneRoster 1.1 Gradebook Push (certified): third-party apps sync assignments and scores into the Skyward gradebook. Confirm with the user first.
• LMS grade sync (SMS 2.0) — The LMS API lets platforms such as Canvas and Schoology sync grades and assignment details into SMS 2.0. Confirm with the user first.

Student education records protected by FERPA: demographics, schedules, enrollments and grades, plus state-reporting data.

How do I connect Skyward to an AI agent over MCP?

As of October 2026 we found no MCP server published by Skyward itself.

The practical path is to host a small MCP server that wraps the Skyward OneRoster API; LMS API (SMS 2.0); Qmlativ APIs via the Partner Portal, or to give the agent the calls directly with the SKILL.md below.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

1. Register the server — POST …/mcp-servers/ with its URL, a transport (sse, websocket or streamable_http) and an auth_type of none, token or oauth2.
2. Create a connection that holds the credential, scoped to the whole organization (platform), to a single agent, or to each user (user).
3. Enable it on the agent — mcp-tool in tool_slugs and the server id in mcp_servers. Both lists are replaced, not merged, so read the settings first.

For an API key or a service credential, one token connection at platform scope serves the whole organization; scope a connection to a single agent when that agent needs narrower access than the rest.

The field reference is in MCP server connections, and the /iblai-api-agent-mcp skill runs all three steps from a coding agent.

What does the Skyward agent skill do?

The Skyward skill is one SKILL.md file named iblai-connect-skyward. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

Download the Skyward SKILL.md

Save it as .claude/skills/iblai-connect-skyward/SKILL.md, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against Skyward's documentation on October 20, 2026. Test it against your own Skyward setup before you rely on it.

What can I ask a Skyward agent to do?

• “Pull the class rosters for every 5th-grade section from Skyward”
• “Sync this week's assignment scores from our LMS into the Skyward gradebook”
• “List students added to Period 2 Biology since Monday”
• “Export the course list for next term so we can build sections in our LMS”

How do I run a Skyward agent on ibl.ai?

Agentic OS is where the agent runs on ibl.ai: it holds the Skyward MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.

• AI agents for K-12 — what ibl.ai deploys in this sector

Which ibl.ai agents work with Skyward data?

• School Administrator — K-12
• Family Communicator — K-12

Which ibl.ai platform skills does a Skyward agent use?

• /iblai-api-agent-mcp — MCP connectors for ibl.ai agents, end to end
• /iblai-vibe-agent-mcp — Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth,…
• /iblai-api-agent-tool — Enable or disable an ibl.ai agent's tools via the platform API

What else should I know before connecting Skyward to an AI agent?

Which other data sources can an AI agent connect to alongside Skyward?

Which other K-12 systems have a connector?

• 1EdTech OneRoster — Rostering and gradebook data standard
• Blackboard Learn — Learning management system
• Canvas LMS — Learning management system
• ClassLink — Rostering and single sign-on platform
• Clever — Rostering and single sign-on platform
• D2L Brightspace — Learning management system
• Google Classroom — Learning management system
• Infinite Campus — Student information system
• Moodle LMS — Learning management system
• PowerSchool SIS — Student information system
• Schoology — Learning management system
• Seesaw — Elementary learning platform

Every connector, grouped by sector, is on the connectors hub.