About Tenrung
Tenrung scores how AI-native a team is across 10 areas and provides a 90-day plan and an AI champion role card. It is listed in Openkrill’s office and admin collection.
Key features
- 01Scores AI-native practices across 10 areas
- 02Creates a 90-day plan
- 03Provides an AI champion role card
- 04Listed in the office and admin collection
Use cases
- 01Assess a team’s AI-native practices
- 02Plan 90 days of team changes
- 03Define an AI champion role
MCP support
Tenrung is listed as an MCP server in Openkrill’s office and admin collection. The listing gives its endpoint as https://tenrung.openkrill.app/mcp; servers in the collection are public, read-only, and need no key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tenrung.openkrill.app/mcpclaude mcp add --transport http app-openkrill-tenrung https://tenrung.openkrill.app/mcp{"mcpServers":{"app-openkrill-tenrung":{"type":"http","url":"https://tenrung.openkrill.app/mcp"}}}Open in Cursor{"servers":{"app-openkrill-tenrung":{"type":"http","url":"https://tenrung.openkrill.app/mcp"}}}Open in VS Code{"mcpServers":{"app-openkrill-tenrung":{"type":"http","url":"https://tenrung.openkrill.app/mcp"}}}{"mcpServers":{"app-openkrill-tenrung":{"serverUrl":"https://tenrung.openkrill.app/mcp"}}}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| Parameter | Type | Required | Description |
|---|---|---|---|
| scores | object | Yes | The team's 0 to 3 score on each of the 10 lines. Ask the user for each line; never guess a score they did not give. |
| scores.reps | integer | Yes | One person from each department meets every 2 weeks. 0: Departments do not talk about AI with each other. 1: People swap tips in a chat channel now and then. 2: There are department reps, but they meet when someone remembers. 3: Each department has a rep, and the reps meet every 2 weeks with notes. |
| scores.wins | integer | Yes | Wins are posted where the whole company sees them. 0: Wins stay inside the team that made them. 1: A win gets mentioned now and then in a meeting. 2: Wins are posted, but without the time saved or how it was done. 3: Each win is posted company-wide with the hours saved and the steps, so others can copy it. |
| scores.owner | integer | Yes | One named person owns AI adoption, with hours for it in their week. 0: Nobody owns it. Whoever is keen helps when they can. 1: Someone is the go-to person, but it is a favour on top of their job. 2: A person is named, but the hours for it are not in their week. 3: A named owner has protected hours every week, and everyone knows who it is. |
| scores.policy | integer | Yes | A 1-page AI policy is pinned where people work. 0: There is no policy. People guess what is allowed. 1: There are rules, but they live in an email or in someone's head. 2: A policy exists, but it is long or hard to find. 3: One page says what data may go where and which tools are approved, and it is pinned in the main channel. |
| scores.tracks | integer | Yes | Training comes in 3 tracks: starters, daily users and builders. 0: Everyone gets the same thing, or nothing. 1: There is one level, pitched at beginners. 2: There are 2 levels, or the 3 tracks exist on paper only. 3: Starters, daily users and builders each have their own track and their own sessions. |
| scores.backlog | integer | Yes | A list of AI use cases, ranked by hours saved. 0: Ideas come and go in meetings. 1: There is a list, but nobody ranks it. 2: The list is ranked by gut feel or by who asked loudest. 3: Every idea has an hours-saved estimate, and the list is ranked by it every 2 weeks. |
| scores.library | integer | Yes | Sessions are recorded into a library that is checked every month. 0: Nothing is recorded. 1: Some recordings exist in someone's drive. 2: There is a shared library, but old or broken material stays in it. 3: Every session goes into one library, and each month someone removes what is out of date. |
| scores.training | integer | Yes | Live training every month, on your own workflows. 0: No training. People learn from videos on their own. 1: There was a kickoff session, and nothing since. 2: Training happens a few times a year, or uses generic examples. 3: Every month there is a live session built on a real task from your own team. |
| scores.focus_time | integer | Yes | Time for AI work is blocked in calendars every week. 0: AI work happens only when the day is quiet, which is never. 1: Some people block time for it on their own. 2: Blocked time is encouraged, but meetings take it back. 3: Everyone has a weekly block for AI work, and managers protect it. |
| scores.hours_saved | integer | Yes | Hours saved are measured and shown to leadership. 0: Nobody knows what AI saves. 1: There are stories, but no numbers. 2: Some workflows are timed, but the numbers are not shown upward. 3: Hours saved are measured before and after, and leadership sees the total every month. |
| team_name | string | No | Optional team or company name shown on the result and in the share link. Leave it out to keep the link anonymous. |
Details
From the project READMEOffice and Admin Tools
Business days and holidays, US tax figures, EU VAT and company registries, document files, ready-to-send links, weekly lane plans and an AI-native team scorecard.
claude plugin install office@openkrill
| Skill and MCP server | Tool | Endpoint |
|---|---|---|
business-days | Business Days & Workday Calc | https://businessdays.openkrill.app/mcp |
tax | Tax Numbers | https://tax.openkrill.app/mcp |
eu-business | EU Business & VAT Checker | https://eubusiness.openkrill.app/mcp |
docs | Document Tools | https://docs.openkrill.app/mcp |
send-out | Send Out | https://sendout.openkrill.app/mcp |
lane-planner | Lane Planner | https://lanes.openkrill.app/mcp |
tenrung | Tenrung | https://tenrung.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
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.