Interact with Microsoft 365 and Office services through the Microsoft Graph API.
Nothing to run from here
Juggle is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
397
downloads a day
local
runs on your machine
20
tools declared
What it does
Juggle (whyjuggle.com) babysitting/petsitting for families: sits, sitters, messages (AI-built).
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user juggle-mcp '--' npx -y @chrischall/juggle-mcp
# 2 — ask your agent for something these tools do
# juggle_post_job, juggle_cancel_booking, juggle_send_message and 17 more
Juggle costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CHAll 84 servers
chrischall84 servers
14 categories
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 Juggle 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 juggle-mcp '--' npx -y @chrischall/juggle-mcpReconnect, 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.
What it asks of you
Nothing is required, but it can take JUGGLE_EMAIL (The email address you sign in to whyjuggle.com with (a family account). Needed by every tool except juggle_list_locations; the server starts without it.), JUGGLE_PASSWORD (Your whyjuggle.com password. Google/Facebook-only sign-ins are not supported. Needed by every tool except juggle_list_locations; the server starts without it.), JUGGLE_BASE_URL (Site origin override, for tests or a local stub only. Defaults to https://whyjuggle.com; must be https (loopback http allowed).), MCP_CONFIRM_MODE (Confirm-gated writes on clients without prompts: ask-user (default), auto, or refuse.), MCP_CONFIRM_ELICITATION (Set to off to skip the confirmation prompt even on clients that declare elicitation support.), MCP_CONFIRM_TTL_SECONDS (How long a write's confirmToken stays valid, in seconds (default 600).) if you want to set them.
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
20 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Post a one-time babysitting/petsitting/homeschool-help job (sit), optionally inviting a sitter (confirm-gated)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| service | string | yes | babysitting, petsitting or homeschool_help. |
| start_date | yes | Start date, YYYY-MM-DD. | |
| start_time | yes | Start time, HH:MM (24h, local). | |
| end_time | yes | End time, HH:MM (24h, local). At or before 05:00 = the next day unless end_date says otherwise. | |
| end_date | no | End date, YYYY-MM-DD (default: start_date, or the next day for an end at or before 05:00). | |
| address_id | no | Which of your addresses (id from juggle_get_profile). Default: your primary address. | |
| num_kids | integer | no | Number of kids (default: from your profile). Required ≥1 for babysitting / homeschool help. |
| num_pets | integer | no | Number of pets (default: from your profile). Required ≥1 for petsitting. |
| special_instructions | string | no | Notes for the sitter (bedtimes, allergies, where to park…). Sitters who apply can read this. |
| post_on_open_jobs | boolean | no | Also list it on the public Open Jobs board for all sitters (default true, as on the website). |
| sitter_account_id | no | Invite this sitter (accountId from juggle_list_sitters / juggle_list_favorites) to the job. |
Cancel a booking; late cancels only via the one-star-review penalty, never the fee (confirm-gated)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| booking_id | yes | The booking id (bookingId from juggle_list_bookings). | |
| reason | string | yes | Cancellation reason: its id or its label (e.g. "Plans changed"). |
| details | string | no | Additional information about why you are canceling (shared with Juggle / the sitter). |
| accept_one_star_review | boolean | no | Set true ONLY after the user agrees to take a one-star review as the late-cancellation penalty (needed within 12 hours of the start). |
Send a text message in one of your sitter conversations (confirm-gated)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | yes | The conversation id (conversationId from juggle_list_conversations). | |
| text | string | yes | The message text (plain text; line breaks are kept). |
Leave a 0-5 star (half-star) review of a sitter for a finished booking (confirm-gated)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| booking_id | yes | The finished booking (bookingId from juggle_list_bookings). | |
| sitter_account_id | yes | The booked sitter's accountId (from juggle_get_booking). | |
| rating | number | yes | Stars, 0–5 in steps of 0.5. |
| comments | string | no | Review text (optional; public). |
Show your Juggle (whyjuggle.com) family account profile: name, email, service area (city), membership/subscription status, unread message count, job stats (posted/completed/canceled, rating), saved addresses with their ids (needed to post a sit), pets, and the number of kids. Kids' names,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_kids | boolean | no | Also return each kid's name, birthday, gender, grade, hobbies, foods, allergies and notes (default false). |
| view | yes | — |
Show your Juggle payments overview: your city's hourly sitting rates and booking fee (babysitting by number of kids, petsitting by number of pets, multi-sitter), saved cards (brand, last 4, expiry, which is default), membership subscription, promo codes/credits remaining, and recent transactions…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| transactions_limit | yes | — | |
| view | yes | — |
List your Juggle babysitting / petsitting bookings (the sits or jobs you posted): status (open, booked, in progress, awaiting payment/review, completed, canceled…), service, start date/time, the booked sitter, and how many sitter applications are waiting. status "active" (default) = still in play,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Which bookings: "active" (default), "past" or "all". Ignored when statuses is given. |
| statuses | array | no | Exact booking statuses to include (overrides status). |
| service | string | no | Only this service. |
| order | string | no | By start time: "asc" soonest/oldest first (default) or "desc". |
| limit | yes | — | |
| offset | yes | — | |
| view | yes | — |
Get one Juggle booking (sit/job) in detail: status, service, dates and times, kids/pets and notes, address, the sitters who APPLIED (applicants — accountId, name, rating, jobs completed, favorite, hours until the application expires) and the sitters BOOKED (with their phone number for the sit),…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| booking_id | yes | The booking id (bookingId from juggle_list_bookings). | |
| view | yes | — |
List the cities Juggle serves (by state) with each city's published babysitting and petsitting hourly rates and support email, from Juggle's public Locations page. Needs no sign-in. Optional state filter (e.g. "North Carolina").
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | string | no | Only this US state (full name, case-insensitive). |
| view | yes | — |
List your Juggle message conversations (inbox / chats with sitters): who, the last message, when, and how many unread messages each has. Returns conversationId for juggle_get_conversation. unread_only keeps just the conversations with unread messages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| unread_only | boolean | no | Only conversations with unread messages (default false). |
| limit | yes | — | |
| offset | yes | — | |
| view | yes | — |
Read the messages in one Juggle conversation (chat with a sitter): sender, whether you sent it, time, and text — the most recent limit messages, oldest first; page further back with offset. conversation_id comes from juggle_list_conversations. Opening a conversation is what the website does to…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | yes | The conversation id (conversationId from juggle_list_conversations). | |
| limit | yes | — | |
| offset | yes | — | |
| view | yes | — |
Search the Juggle sitters (babysitters, petsitters, nannies — college-student 'Squad') in your city: name, location, rating, jobs completed, background check, whether they are a favorite and how many of your friends booked them. Optional filters: available on a date between start_time and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | no | Only sitters available on this date (YYYY-MM-DD). Needs start_time and end_time. | |
| start_time | no | Availability window start, HH:MM 24h (with date). | |
| end_time | no | Availability window end, HH:MM 24h (with date). | |
| services | array | no | Only sitters offering these services. |
| keywords | string | no | Keyword search over sitter profiles. |
| name | string | no | Search by sitter name. |
| limit | yes | — | |
| view | yes | — |
List the sitters you have marked as favorites on Juggle: name, location, rating, jobs completed, background check. Returns profileId (for juggle_get_sitter) and accountId (for reviews, unfavoriting and booking invites).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| view | yes | — |
Get one Juggle sitter's public profile: rating, jobs completed, 'mom approved' since, background check, services offered, childcare / special-needs experience, college and major, certifications, kid age range, pet experience, homework help, driver's license / car, bio, whether they are a favorite…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| profile_id | yes | The sitter's profileId (NOT accountId). | |
| view | yes | — |
Read the reviews other families left for a Juggle sitter (date, reviewer, star rating, text, whether the reviewer is your friend), newest as Juggle orders them, with the total count and average rating. account_id is the sitter's accountId (from juggle_list_sitters, juggle_get_sitter or a booking).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| account_id | yes | The sitter's accountId (NOT profileId). | |
| limit | yes | — | |
| offset | yes | — | |
| view | yes | — |
Check the Juggle sign-in is configured and accepted, and that an authenticated page read works
No parameter schema on file.
Accept (book) a sitter who applied to one of your jobs (confirm-gated)
No parameter schema on file.
Decline a sitter's application to one of your jobs (confirm-gated)
No parameter schema on file.
Add a sitter to your favorites (confirm-gated)
No parameter schema on file.
Remove a sitter from your favorites (confirm-gated)
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Juggle or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.2.0 · scanned 4 Nov 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 score100
Findings1 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest4db459c228031e4103e3913ba06253b6578473f0b8d35eeb6b4a2b3a0bbb9c5b
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 (11 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| juggle_get_profile | untrusted-input | untrusted-input: keyword "read_message" |
| juggle_get_payments_summary | no tags | |
| juggle_list_bookings | no tags | |
| juggle_get_booking | no tags | |
| juggle_list_locations | no tags | |
| juggle_list_conversations | untrusted-input | untrusted-input: keyword "read_message" |
| juggle_get_conversation | no tags | |
| juggle_list_sitters | no tags | |
| juggle_list_favorites | no tags | |
| juggle_get_sitter | no tags | |
| juggle_get_reviews | 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 digest4db459c228031e41
Scanned2026-11-04
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.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.0. Pin a release below and the command asks for exactly that one.
0.2.0
4 Nov 2026
latestNo release note was published with this version.
0.1.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Juggle can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.