mcpField
S
School Digest

School Digest

Remote
tools.openkrill.appProductivity0Updated 2w ago

About School Digest

School Digest is a public, read-only MCP server for generating one printable daily page per child from supplied snapshots. It is listed in Openkrill’s research plugin collection.

Key features

  1. 01Printable daily page per child
  2. 02Uses supplied snapshots
  3. 03Public, read-only access
  4. 04No API key required

Use cases

  1. 01Prepare a daily school page for each child
  2. 02Generate a digest from provided snapshots

MCP support

Exposes School Digest through the MCP endpoint https://schooldigest.openkrill.app/mcp. The server is public, read-only, and requires no key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://schooldigest.openkrill.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

3
ParameterTypeRequiredDescription
datestringYesThe report day in the school time zone, as YYYY-MM-DD, such as "2026-10-08".
canvasobjectYesCanvas API JSON from a parent observer account, such as {"observees": [{"id": 1, "name": "River Sample"}], "courses": [...], "assignments": {"11": [...]}, "announcements": []}. No token.
canvas.coursesarrayNoCourses with id (integer), name, teachers [{display_name}] and enrollments [{type: "student", user_id, computed_current_score, computed_current_grade}].
canvas.observeesarrayNoOne entry per child: id (integer) and name.
canvas.assignmentsobjectNoObject keyed by course id, each a list of up to 80 assignments with id, name, due_at, points_possible and submission {user_id, workflow_state, score, graded_at, missing, late}.
canvas.announcementsarrayNoAnnouncements with id, title, message, posted_at, context_code such as "course_11", and author {display_name}.
run_atstringYesWhen the snapshots were taken, as an ISO time, such as "2026-10-08T12:00:00Z".
previousobjectNoOptional: yesterday's full request with its own date, run_at, timezone and canvas (and infinite_campus, if any), for the changes block.
previous.datestringNo
previous.canvasobjectNo
previous.run_atstringNo
previous.timezonestringNo
previous.infinite_campusobjectNo
timezonestringNoA valid IANA time zone name for the school, such as "America/Chicago" (the default).
summariesobjectNoOptional lines you wrote, keyed by child name as in observees, 1 to 3 lines of up to 180 characters each. The tool does not call a model.
notice_emailsarrayNoAny other school notice emails, same format and limits. Plain text with From, Subject and Date headers, a blank line, then the body. Up to 30 emails of 12000 characters each. Optional.
infinite_campusobjectNoOptional Infinite Campus grade snapshot. Each student is matched to a Canvas observee by firstName and lastName.
infinite_campus.studentsarrayNo
parentsquare_emailsarrayNoParentSquare notice emails. Plain text with From, Subject and Date headers, a blank line, then the body. Up to 30 emails of 12000 characters each. Optional.

Details

From the project README

Research and Public Data

Find papers, check references and DOIs, read US federal regulations, compare country statistics, and make a school digest.

claude plugin install research@openkrill
Skill and MCP serverToolEndpoint
papersPaper Finderhttps://papers.openkrill.app/mcp
citationsCitation Checkerhttps://citations.openkrill.app/mcp
rulesUS Federal Regulations (CFR)https://rules.openkrill.app/mcp
countrystatsCountry Stats Factshttps://countrystats.openkrill.app/mcp
school-digestSchool Digesthttps://schooldigest.openkrill.app/mcp

Every server is public, read-only and needs no key. Generated from the Agent Tools plugin listings; edits made here are overwritten.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.