The UOR Foundation MCP server

• Registry namefoundation.uor.hub/model-hubverified in the MCP registry

The registry name sits under uor.foundation. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-21
• Tools3
• Server calls itselfhologram-model-hub
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 411 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• Use5 GitHub stars
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer299 ms
• Space in an agent's context≈ 432 tokensthe definitions of all its tools (3), which an agent carries on every turn
• Tool definitionsC · 72 of 100
• Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 2 of 3
• Not saying whether it only reads or can destroy: 3 of 3

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search_models

  Find open models in the hub's index. Every result has all of its files addressed by SHA-256. Returns id, task, library, licence, parameters, weight size, downloads and where the bytes live.

• get_model

  The pinned revision of one model, its files with size and SHA-256, its GGUF quantisations if any, and its sources with their current health.

• resolve_file

  Where to download one file of a model right now, the SHA-256 it must have, how to check it, and the commands that hand it to an engine (hf, Ollama, llama.cpp). Give either a path or, for GGUF models, a quantisation such as Q4_K_M.