# Niels Langereis

> Essays, an enterprise AI map and a skill-matrix gap analysis on AI adoption and junior formation.

- name: com.nielslangereis/thinking
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 89/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.nielslangereis%2Fthinking
- tools: https://api.protogrid.dev/v1/servers/com.nielslangereis%2Fthinking/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "thinking": {
      "type": "http",
      "url": "https://nielslangereis.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-4d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 89/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,416 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 4 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 1,416 tokens to load them all
- tool set hash: 5f364ce83d2cf108b4430387f29d97d9
- badge: [![protogrid quality](https://protogrid.dev/badge/com.nielslangereis/thinking.svg)](https://protogrid.dev/servers/com.nielslangereis/thinking)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://nielslangereis.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `about_niels`: Who Niels Langereis is and how to work with him: what he does and for whom, how he works, his background, his talks and speaking, and how to get in touch. Use when someone asks whether he could help them, wants to hire or book him, or wants his background. Contact is by email or the site's contact form; this server does not send messages.
- `get_enterprise_ai_map`: Niels Langereis's enterprise AI map: 24 illustrative AI agents across ten business functions (strategy, product, design, marketing, sales, customer success, operations, people, finance, data and IT), each with its rollout phase, what it optimises for and the trade-off it creates for other functions; plus the coordination layer, the bench and the external renderers that decide whether faster work becomes a better organisation. Use it to reason about someone's own AI rollout. detail='summary' returns only the skeleton (functions, agents, phases and trade-offs, plus one line per remaining part), which is enough for most reasoning; detail='full' (default) adds the complete prose on coordination, the bench and the renderers. Optionally filter by function or phase. Shows an interactive map where the client supports it.
- `get_essay`: Get the full text of one essay by Niels Langereis, as Markdown, with its date, site link and the original LinkedIn link. Use the id from search_essays, or a title.
- `get_skill_matrix_method`: Explains Niels Langereis's skill-matrix gap analysis: a competency matrix run for formation rather than efficiency, to find where AI has removed the work that used to turn juniors into seniors. Includes the status rule, how to read it, a worked example and credits. Use before run_skill_matrix if the user wants to understand the method first.
- `run_skill_matrix`: Runs Niels Langereis's skill-matrix gap analysis for one role and shows it as an interactive matrix the user can edit (who does the work now, bench depth, formation actions). Draft 6 to 10 competencies for the user's role yourself from what you know about it, spanning routine work AI can now do with senior oversight, work AI already runs autonomously, and judgement work that needs a human. Set bench (how many people can do it at the strategic level) from what the user told you; if unknown, use 1 and say it is an estimate they should correct. Omit competencies to show the generic analyst example. The result flags 'At risk' (human work, one person deep), 'Thin' (two deep) and 'Reps gone' (AI runs it autonomously, so the formation that used to happen in reviewing it has gone too: ask where juniors get those reps now). After the user edits, their current matrix arrives in your context.
- `search_essays`: Search the essays of Niels Langereis on AI adoption, organisational change, the politics of AI, junior formation and judgement, brand and AI agents, boards and governance. Returns titles, dates, summaries, a matching snippet and links. Leave query empty to list all essays, newest first. Follow up with get_essay for the full text before quoting him.