Seesaw MCP Server & Agent Skill

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

No public developer API was found. Rosters reach Seesaw from Clever or ClassLink (district product) or CSV import; sign-in uses Google, Microsoft or Okta SSO; Seesaw embeds in Canvas, Schoology and D2L through LTI.

• API: No public API documented; integration via Clever, ClassLink, CSV, SSO and LTI (Mixed)
• Access: No public API
• Authentication: SSO (Google, Microsoft, Okta); Rostering connection via Clever or ClassLink

Seesaw says it does not integrate directly with any SIS; districts automate rostering through Clever or ClassLink. To move data in, roster through those platforms or import CSV files.

No API credentials are issued to third parties. Users sign in via Google, Microsoft or Okta SSO; rostering runs through the district's Clever or ClassLink connection.

What can an agent read from Seesaw?

• Class rosters (via Clever/ClassLink) — Classes, teachers and students come from the district's Clever or ClassLink sync; read them at the source, not from Seesaw.
• CSV roster imports — Schools without Clever or ClassLink create classes by CSV roster import.
• LMS launches (LTI) — Seesaw content opens inside Canvas, Schoology and D2L via LTI admin setups.

What can an agent write to Seesaw?

This skill only reads Seesaw data; it documents no write calls, so an agent built on it cannot change a Seesaw record.

Student education records protected by FERPA, from young children (COPPA applies to under-13 users): student work samples, photos, voice and video recordings, and family contacts.

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

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

The practical path is an MCP server you host over the integration path Seesaw Learning supports — an export, a reporting database or a partner interface — or 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 Seesaw agent skill do?

The Seesaw skill is one SKILL.md file named iblai-connect-seesaw. 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 Seesaw SKILL.md

Save it as .claude/skills/iblai-connect-seesaw/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 Seesaw Learning's documentation on October 20, 2026. Test it against your own Seesaw setup before you rely on it.

What can I ask a Seesaw agent to do?

• “Check whether the Seesaw classes for 1st grade match our Clever sections this week”
• “List the students in Clever who are missing from our Seesaw class rosters”
• “Build a Seesaw CSV roster import file from this class list”
• “Explain how to set up Seesaw inside our Schoology courses”

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

Agentic OS is where the agent runs on ibl.ai: it holds the Seesaw 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 Seesaw data?

• Family Communicator — K-12
• Assessment Builder — K-12

Which ibl.ai platform skills does a Seesaw 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 Seesaw to an AI agent?

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

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
• Skyward — Student information system

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