On a contested topic, your assistant gets posts that are trusted across the disagreement in your network, not only on your side of it, each with a title and a link. It is meant for topics where people genuinely disagree. An empty answer says why, such as no posts on the topic or none that bridge.
Ask it like this
- “What would actually persuade the skeptics on nuclear power?”
- “What can I cite on phones in schools that the other side will not dismiss?”
When another tool fits better
- Whose judgment do the people I trust rely on for this topic?
You want who is trusted on a topic, regardless of disagreement. - Why do I see things the way I do?
You want to know which communities shape your view. - What holds up across divides, seen from another perspective?
You want what bridges as a named outside perspective sees it.
Before you use it
- It needs the Read your trust signal permission, which UpTrust asks you to approve when you connect.
- It only reads. It changes nothing on UpTrust.
- In Claude, connect
https://mcp.uptrusting.com/mcp. In ChatGPT, connecthttps://mcp.uptrusting.com/chatgpt. How to connect. - It can also answer from another trust graph than yours, such as one built from academic papers; see which communities it can answer from.
What your assistant is told
Your assistant decides when to use this tool from the title and description UpTrust’s server gives it. Here they are exactly as the server sends them.
- Tool name
bridges_for_principal- Title
- What holds up with people who disagree with you?
- Description
Use this when the user asks what, on a contested topic, holds up with people who disagree with them: "what would actually persuade the skeptics?", "what can I cite that the other camp won't dismiss?", "what holds up on both sides of this?". It returns up to 25 posts trusted ACROSS the disagreement ("bridge" content), for when the user's usual sources would be waved away by the other side. Works best on genuinely contested topics. Use top_trusted_for_principal instead for who is trusted on a topic regardless of disagreement, and field_for_principal to explain which communities shape the user's own view. Each item carries a title and URL, plus author and snippet when the issuer has them. Depending on the issuer, the response also reports how many items bridged, the resolved tag and how many posts were considered. On an empty result an issuer may send `empty_reason` and a `note`; when present they say why and override any inference from the other fields, so an empty list distinguishes a missing topic from a topic with no bridging content.