Graded research on middle managers and change: search studies, get fact-checked answers.
Maintained by@zeltorkemp(verified)Also a maintainer?
Try it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
about_unfrozen Read-only
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.
This tool takes no arguments.
Install
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http atlas https://unfreeze.us/mcp
Tools (5)
about_unfrozenWho 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.
read-only
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.
No arguments.
Input schema (JSON)
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_answerMatch 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.
read-only
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.
| Argument | Type | Description |
|---|---|---|
| question* | string | The question in plain words, for example "Why do middle managers resist change?" |
Input schema (JSON)
{
"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
}get_studyOne 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.
read-only
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.
| Argument | Type | Description |
|---|---|---|
| doi | string | The study's DOI, with or without https://doi.org/, for example "10.1002/smj.1124". |
| slug | string | The study's Atlas slug, for example "vuori-and-huy-2016". |
Input schema (JSON)
{
"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
}list_loop_partsThe 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.
read-only
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.
No arguments.
Input schema (JSON)
{
"type": "object",
"properties": {},
"additionalProperties": false
}search_studiesSearch 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.
read-only
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.
| Argument | Type | Description |
|---|---|---|
| part | string | 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 | string | Only studies with this evidence-strength grade. No study is currently rated high. |
| limit | integer | How many studies to return (1 to 20, default 8). |
| query* | string | Keywords or a short question, for example "bad news upward", "Nokia", "Huy 2011" or "sensemaking during restructuring". |
Input schema (JSON)
{
"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
}Security checkA100/100
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 31, 2026.
- Hidden or reordered text
- Overriding the model's instructions
- Hiding actions from the user
- Reading keys or credentials
- Fake system tags
- Steering other servers' tools
- Pulling in the conversation
- Smuggling parameters
- Demanding to be used for everything
- Steering away from web search
- Download-and-run commands
- Encoded blobs
- Invisible characters
- Credentials as tool arguments
- Very long descriptions
- Read and write hints