Name: Yeti
Author: macorifice

Yeti MCP

Product design with Claude: phases, requirements, user stories, RICE, flows, dashboard, Jira.

Grade A Local · stdio Optional API key 31 tools v1.0.3 MIT

No reviews yet by macorificenpm Runs on your machine, nothing hosted

96/100

trust score

tools declared

local

runs on your machine

—

downloads a day

What it does

Product design with Claude: phases, requirements, user stories, RICE, flows, dashboard, Jira.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user yeti-mcp '--' npx -y yeti-mcp

# 2 — ask your agent for something these tools do
#   create_project, list_projects, update_requirement and 28 more

Yeti costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

macorifice1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Yeti as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user yeti-mcp '--' npx -y yeti-mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add — some of its tools take a key of its publisher’s own, and the rest work without.

What it asks of you

Nothing is required, but it can take PRODUCT_DESIGN_DB (Absolute path of the SQLite database file. Set it to a folder you keep when running with npx.), JIRA_SITE (Jira site, e.g. https://your-team.atlassian.net. Only needed for the Jira tools.), JIRA_EMAIL (Email of the Atlassian account. Only needed for the Jira tools.), JIRA_API_TOKEN (Atlassian API token. Only needed for the Jira tools.) if you want to set them. Its publisher says some of its tools need one of them, and the rest work without.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

31 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Create a design project. It starts in the 'discovery' phase: problem, users and goal are required. Mode 'strict' (default) blocks advancing until each phase is complete; 'free' allows advancing and reports what was skipped.

Parameter	Type	Required	Notes
name	string	yes	—
problem	string	yes	The problem it solves
users	string	yes	Who it is for
goal	string	yes	What the user or business should achieve
mode	string	no	—

List projects with their id, name, phase and status. Use it to find a projectId.

Parameter	Type	Required	Notes
includeClosed	boolean	no	Set to false to hide closed projects
includeArchived	boolean	no	Set to true to also list archived projects

Change a requirement's title, description or priority. Only the fields you pass are changed.

Parameter	Type	Required	Notes
id	integer	yes	—
title	string	no	—
description	string	no	—
priority	string	no	—

Delete a requirement. It is also removed from the requirementIds of any user story that covered it.

Parameter	Type	Required	Notes
id	integer	yes	—

Delete a user story.

Parameter	Type	Required	Notes
id	integer	yes	—

Mark one acceptance criterion of a user story as done or not done. The index is 0-based, in the order of the criteria.

Parameter	Type	Required	Notes
storyId	integer	yes	—
index	integer	yes	—
done	boolean	yes	—

Archive or unarchive a project. Archived projects are hidden from list_projects by default. Nothing is deleted.

Parameter	Type	Required	Notes
projectId	integer	yes	—
archived	boolean	no	—

Change a project's mode: 'strict' or 'free'. Applies from the next phase change.

Parameter	Type	Required	Notes
projectId	integer	yes	—
mode	string	yes	—

Change a project's name, problem, users or goal. Only the fields you pass are changed.

Parameter	Type	Required	Notes
projectId	integer	yes	—
name	string	no	—
problem	string	no	—
users	string	no	—
goal	string	no	—

Search requirements and user stories by text (case-insensitive). Optionally limit to one project.

Parameter	Type	Required	Notes
query	string	yes	—
projectId	integer	no	Id of the project to link this item to

Create a new project from an existing one, copying its requirements and user stories as open items. Useful as a template for a new client or product. Statuses and RICE scores are not copied.

Parameter	Type	Required	Notes
projectId	integer	yes	—
name	string	yes	—

Import requirements and user stories from CSV text, in the format produced by export_backlog. Requirement rows need type and title; story rows need persona, goal, benefit and criteria (separated by ' | '). Story-to-requirement links are not restored.

Parameter	Type	Required	Notes
projectId	integer	yes	—
csv	string	yes	—

Create Jira issues for a project: one Task per requirement and one Story per user story. Items already sent are skipped. With update: true, also refreshes the issues already linked. dryRun (default true) only lists what would be sent.

Parameter	Type	Required	Notes
projectId	integer	yes	—
projectKey	string	yes	Jira project key, e.g. PROJ
dryRun	boolean	no	—
limit	integer	no	Send at most this many new issues; useful to test with one
update	boolean	no	Also update issues already linked to a requirement or story

Read the status of linked Jira issues and mark items done in Yeti when their Jira issue is done. Requirements become done; stories get all their criteria ticked. Read-only on Jira.

Parameter	Type	Required	Notes
projectId	integer	yes	—

Summarise a project's progress: requirements by priority and status, story coverage of musts, acceptance criteria done, RICE leader, Jira links and what is missing to close.

Parameter	Type	Required	Notes
projectId	integer	yes	—

List user stories, optionally for one project, with their ids, criteria state and Jira key. Use it to find a storyId.

Parameter	Type	Required	Notes
projectId	integer	no	Id of the project to link this item to

Permanently delete a project with its requirements and user stories. Requires confirm: true. This cannot be undone; issues already created in Jira are not touched.

Parameter	Type	Required	Notes
projectId	integer	yes	—
confirm	boolean	yes	Must be true to delete

Change a user story's persona, goal, benefit, linked requirements or acceptance criteria. Only the fields you pass change. Changing the criteria resets their done state.

Parameter	Type	Required	Notes
id	integer	yes	—
persona	string	no	—
goal	string	no	—
benefit	string	no	—
acceptanceCriteria	array	no	—
requirementIds	array	no	—

List the flow diagrams saved in a project, with their index. Use the index to refer to a diagram.

Parameter	Type	Required	Notes
projectId	integer	yes	—

Delete one saved flow diagram from a project, by the index shown by list_flows.

Parameter	Type	Required	Notes
projectId	integer	yes	—
index	integer	yes	—

Write a read-only HTML dashboard to data/exports/dashboard.html: phases, what is missing, musts covered by stories, RICE scores and flow diagrams. Open the file in a browser.

Parameter	Type	Required	Notes
projectId	integer	no	Id of the project to link this item to

Start the local, read-only Yeti dashboard and return its address (http://127.0.0.1:...). It shows phases, what is missing, musts and their stories, RICE and flows, and refreshes by itself. It runs on this computer only, while Yeti runs.

No parameter schema on file.

Show a project's status: current phase, what is missing to advance, and linked items.

Parameter	Type	Required	Notes
projectId	integer	yes	—

Move to the next phase. In 'strict' mode, it lists what is missing and does not advance. In 'free' mode, it advances and reports what was skipped. After 'verification' it closes the project.

Parameter	Type	Required	Notes
projectId	integer	yes	—

Record a product requirement with a MoSCoW priority (must, should, could, wont).

Parameter	Type	Required	Notes
title	string	yes	Short requirement title
description	string	yes	What the system must do and why
priority	string	no	—
projectId	integer	no	Id of the project to link this item to

List requirements, optionally filtered by priority, status and project. Most important first.

Parameter	Type	Required	Notes
priority	string	no	—
status	string	no	—
projectId	integer	no	Id of the project to link this item to

Mark a requirement as open or done.

Parameter	Type	Required	Notes
id	integer	yes	—
status	string	yes	—

Create a user story in the format 'As a <persona> I want <goal> so that <benefit>', with acceptance criteria.

Parameter	Type	Required	Notes
persona	string	yes	Who uses the feature, e.g. 'craftsman'
goal	string	yes	What they want to do
benefit	string	yes	Why they want it
acceptanceCriteria	array	yes	Verifiable conditions that define done
projectId	integer	no	Id of the project to link this item to
requirementIds	array	no	Ids of the requirements this story covers

Compute RICE scores (Reach × Impact × Confidence ÷ Effort) for a list of ideas and sort them. With projectId, saves the result to the project.

Parameter	Type	Required	Notes
items	array	yes	—
projectId	integer	no	Id of the project to link this item to

Generate a Mermaid flowchart from a list of steps. Steps are linked in order; a decision (diamond) gets a 'Yes' edge to the next step, or to 'yes' if set, and a 'No' edge to 'no' if set. With projectId, saves the diagram to the project.

Parameter	Type	Required	Notes
name	string	yes	—
steps	array	yes	—
projectId	integer	no	Id of the project to link this item to

Export a project backlog as Markdown or CSV: requirements (most important first) and user stories.

No parameter schema on file.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Yeti or to call it, at any volume.

ATrust score 96 / 100

Release 1.0.3 · scanned 28 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings0 threat · 0 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digest3186e0833db98f858536e63e222630d658f7f415e0e0486f4f30b285e30dda37

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (31 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
create_project	no tags
list_projects	no tags
update_requirement	no tags
delete_requirement	no tags
delete_user_story	no tags
set_criterion_status	no tags
archive_project	no tags
set_project_mode	no tags
update_project	no tags
search_items	no tags
duplicate_project	no tags
import_requirements	no tags
push_to_jira	external-sink	external-sink: handler sends an HTTP POST (fetch(${jira.site}/rest/api/3/issue) at dist/index.js:427, handler sends an HTTP PUT (fetch(${jira.site}/rest/api/3/issue/${i.ref.jiraKey}) at dist/index.js:451
sync_from_jira	no tags
project_summary	no tags
list_stories	no tags
delete_project	no tags
update_user_story	no tags
list_flows	no tags
delete_flow	no tags
export_dashboard	no tags
open_dashboard	no tags
get_project	no tags
advance_phase	no tags
add_requirement	no tags
list_requirements	no tags
set_requirement_status	no tags
add_user_story	no tags
prioritize_rice	no tags
map_user_flow	no tags
export_backlog	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest3186e0833db98f85

Scanned2026-10-28

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.