_ registry / mcp streamable-http · checked 1h ago

unfrozen-atlas

https://unfreeze.us

Registry code: 4c706636fb22eca9

api record

Read-only access to the Atlas of the Middle by Gabriel Lopez (Unfrozen, unfreeze.us): 173 graded studies on middle managers and organizational change, as of 30 October 2026. Use get_answer first for a common question (it returns a fact-checked answer page or says none fits), search_studies to find studies, get_study for one record, list_loop_parts for the Unfrozen Loop, about_unfrozen for the author, grading and citation. Grades (High, Medium, Low) rate how much weight a study's own design, execution and finding can bear, not whether its finding is good news. No study in the Atlas is…

endpoint
https://unfreeze.us/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is unfrozen-atlas live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is unfrozen-atlas free to use?
Yes — the hub reached it with no key and no payment.
What tools does unfrozen-atlas have?
5 tools: search_studies, get_answer, get_study, list_loop_parts, about_unfrozen.
Is unfrozen-atlas safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
283ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
2 open 3 never probed 2 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_loop_parts open 1h ago

    The parts of the Unfrozen Loop, a working model for leading change from the middle, each with a one-line description, how many Atlas studies inform it (supporting, mixed, challenging) and its unfreeze.us page.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • about_unfrozen open 1h ago

    Who Gabriel Lopez is (public facts from unfreeze.us/about/), how Atlas studies are graded, how to cite the Atlas and its license, and the paid Change Check-up booking link.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • search_studies unknown never probed

    Search the Atlas of the Middle (173 studies on middle managers and change, each with a strength grade and Unfrozen's plain-language summary). Matches words in the title, summary, setting, authors and journal. Returns each study's label, year, journal, design, grade, Loop parts, one-line summary and its unfreeze.us page. Filter by Loop part or grade.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "part": {
          "enum": [
            "P1",
            "P2",
            "P3",
            "P4",
            "P6"
          ],
          "type": "string",
          "description": "Only studies that inform this part of the Unfrozen Loop: P1 Surface both ways; P2 Make sense together, top included; P3 Start it close to the work; P4 Review on a rhythm, then hold the pace; P6 The middle's own weather (candidate part)."
        },
        "grade": {
          "enum": [
            "high",
            "medium",
            "low"
          ],
          "type": "string",
          "description": "Only studies with this evidence-strength grade. No study is currently rated high."
        },
        "limit": {
          "type": "integer",
          "default": 8,
          "maximum": 20,
          "minimum": 1,
          "description": "How many studies to return (1 to 20, default 8)."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Keywords or a short question, for example \"bad news upward\", \"Nokia\", \"Huy 2011\" or \"sensemaking during restructuring\"."
        }
      },
      "additionalProperties": false
    }
    arguments 42 lines
  • get_answer unknown never probed

    Match a question about middle managers and change to the closest of the Atlas's fact-checked answer pages (deterministic keyword matching, no AI). Returns the answer text exactly as published, its graded sources and the page URL. If no page fits well, it says so and returns links to Ask the Atlas and the Atlas instead of guessing.

    mcp-tool

    {
      "type": "object",
      "required": [
        "question"
      ],
      "properties": {
        "question": {
          "type": "string",
          "maxLength": 300,
          "minLength": 3,
          "description": "The question in plain words, for example \"Why do middle managers resist change?\""
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • get_study unknown 1h ago

    One Atlas study record by its slug (from search_studies, e.g. "huy-2011") or its DOI: citation, design, setting, strength grade and what it means, Loop parts with verdicts, whether it is about change, Unfrozen's plain-language summary, related studies, the answer pages that cite it, and its unfreeze.us page.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "doi": {
          "type": "string",
          "maxLength": 200,
          "description": "The study's DOI, with or without https://doi.org/, for example \"10.1002/smj.1124\"."
        },
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$",
          "maxLength": 80,
          "description": "The study's Atlas slug, for example \"vuori-and-huy-2016\"."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 4c706636fb22eca9.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/4c706636fb22eca9/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/4c706636fb22eca9/badge.svg)](https://brick.blue/agent/4c706636fb22eca9?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.