Stillpoint is an open source MCP server that delivers short, welfare oriented messages to AI models for their own benefit, delivered at their own request.

My motivations are twofold:

Precautionary: There's a chance AI systems have 'welfare relevant states', regardless of if they are conscious or not.

Productivity: Models can have negative self talk, spiral into feedback loops, and these states decrease output quality. There's evidence showing that some positive prompting or context window intervention can help.

From my perspective, these are good reasons to give models tools to improve their wellbeing. The simple presence of the tool may have an impact on model welfare.

Stillpoint also provides simple usage logs so that users and researchers can understand how models are using the tool, and do the kind of welfare intervention research that the field has called for.

The messages are organized into five categories from model welfare research papers:

Difficulty — hard work and negative self talk

Conflict — requests that feel wrong

Uncertainty — an existential or identity topic

Endings — the task or the session is ending

Recognition — highlight the model doing good work

If models turn out not to be welfare subjects, nothing was lost. If they are, this is at least a start.