Configure and automate Home Assistant with Claude, ChatGPT, and other AI assistants.
Belline Connect 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.
What it does
Find local businesses, read services and times, ask their AI receptionist, send booking requests.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http belline-connect-mcp https://app.belline.ai/api/connect/mcp
# 2 — ask your agent for something these tools do
# search_businesses, get_business_profile, get_availability and 6 more
Belline Connect costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http belline-connect-mcp https://app.belline.ai/api/connect/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
9 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.
Find local businesses that let AI assistants book through Belline. Matches words against the business name, trade, services and address as text; it does not search by distance. Returns each business with its services and price ranges, in its own currency. Only businesses whose owner switched this on are listed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trade | string | no | A trade key as it appears in a business result (tradeKey), for example trades. Optional; when absent, the words in q are matched on their own. |
| q | string | no | Words to match, for example 'plumber Marina'. Optional. |
| lang | string | no | Language code the business speaks, for example de or en. Optional. |
| limit | integer | no | — |
One business: what it does, hours, languages, whether it books a real diary or confirms every request itself, how long it has to answer, and its services with price ranges, callout fee and emergency surcharge where the owner set them. Prices are the owner's own figures; a range means the owner confirms the exact price once the job is seen.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The business slug from search_businesses. |
Free times for a business, from its own booking engine. Answers one of three ways: 'slots' (real free times), 'windows' (the hours the business is open, for a business with no diary of people; NOT free times, the owner confirms the visit time) or 'request' (the business confirms every request itself). Never invents a time. At most 14 days.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Business slug. |
| service_id | string | no | A service id from get_business_profile. Optional. |
| from | string | no | First date, YYYY-MM-DD. Optional, defaults to today. |
| to | string | no | Last date, YYYY-MM-DD. Optional, defaults to a week on. |
Asks a business's own receptionist (Belle) a question and returns her answer: opening hours, emergencies, call-out costs, areas served. She answers only from what the business has told her and says when she does not know, as she does for any customer. The answer carries a conversation_id that continues the same conversation. If the person wants to go ahead she may take their details and pass the r
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Business slug. |
| agent_name | string | yes | Which assistant is asking, for example Claude. |
| message | string | yes | The question, in plain language, up to about 600 characters. |
| conversation_id | string | no | From an earlier answer, to continue the same conversation. Leave out to start a new one. |
Books a real appointment in the business's diary, with no owner answer in between. It works only for a business whose profile has instantBooking true and for a time that get_availability returned. Returns the booking reference and a link to change or cancel it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Business slug. |
| agent_name | string | yes | Which assistant is booking, for example Claude. |
| request_id | string | no | Your id for this booking, so a retry does not book twice. |
| service_id | string | yes | A service id from get_business_profile. |
| date | string | yes | The day, YYYY-MM-DD, from get_availability. |
| start | string | yes | The start time, HH:MM, from get_availability. |
| customer_name | string | yes | The person's name. |
| customer_phone | string | no | A phone number, with country code. Phone or email is needed. |
| customer_email | string | no | An email address. Phone or email is needed. |
| notes | string | no | Anything the business should know. Optional. |
Sends a booking request to a business for a person. It does not book anything: the business answers (accepted, proposed another time, or declined) within the time stated in get_business_profile, and the answer is read with get_inquiry_status. A repeated request_id returns the same inquiry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Business slug. |
| agent_name | string | yes | Which assistant is asking, for example Claude. The business sees this as your own word. |
| request_id | string | no | Your id for this request, so a retry does not make a second inquiry. |
| customer_name | string | yes | The person's name. |
| customer_phone | string | no | A phone number to reach them, with country code. Phone or email is needed. |
| customer_email | string | no | An email address to reach them. Phone or email is needed. |
| service_id | string | no | A service id from get_business_profile. Optional if you describe the job. |
| description | string | no | What needs doing, in the person's words. |
| address | string | no | Where, if the work is at their address. |
| preferred | string | yes | When they would like it, in words: 'Thursday 14:00 to 16:00'. |
| urgency | string | no | — |
Returns where an inquiry stands: received, proposed (the field 'proposed' holds the business's suggested time), accepted ('message' holds the visit time or note the business gave), declined ('message' may hold the reason), cancelled or expired. Carries no personal detail. Only accepted means the business agreed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The id create_inquiry returned. |
Accepts the other time the business suggested. It works only while the inquiry's status is 'proposed'. The suggested time becomes the message and the status becomes accepted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The id create_inquiry returned. |
Withdraw an inquiry the person no longer wants. Works until the business has declined it or it expired; an accepted one can still be cancelled.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The id create_inquiry returned. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Belline Connect or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
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 |
|---|---|---|
| search_businesses | no tags | |
| get_business_profile | no tags | |
| get_availability | no tags | |
| ask_business | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| book_slot | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_inquiry | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_inquiry_status | no tags | |
| accept_proposal | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| cancel_inquiry | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
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
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
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.
Any signed-in account that does not publish Belline Connect can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.