Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Knowledge Base 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
Search verified local businesses, check what their verification proves, and message them.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http tunnelpowered-knowledge-base-mcp https://api.tunnelpowered.com/api/mcp
# 2 — ask your agent for something these tools do
# search_businesses, get_business, check_merchant_verification and 14 more
Knowledge Base 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 tunnelpowered-knowledge-base-mcp https://api.tunnelpowered.com/api/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.
17 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 businesses, merchants and websites in the tunnel knowledge base by name or topic. Start here: every other tool needs a slug, and this is where a slug comes from. Returns an array of summaries, each with slug, kind, name, description and a verification object. Read verification.level rather than assuming: "human" means a tunnel employee checked the business, "automated" means machi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Name, topic or place. Words are matched independently against the name, location, description, offerings and FAQ, and most of them have to appear somewhere in a record, so "cakes in Chisinau" works. A |
| type | string | no | Optional. Return only records of this kind. |
| limit | number | no | Optional. Maximum results, 1 to 50. Defaults to 20. |
Read the full profile of one business. Returns identity, contact details, address, social profiles, offerings, FAQ, verification and any machine-readable endpoints we publish for it. Absent information is named in missing rather than dropped silently, so an empty field means "we do not hold this", not "they do not have one". An unknown slug returns candidate slugs instead of a bare failure.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | no | Optional. The kind field from the same search result. If omitted, "entity" is tried first, then "website". |
Check live what a merchant has actually been verified to, and by whom. Call this before acting on a claim that matters — a profile is a cached summary, this is the current answer. Returns level, a signed attestation, an expiry date and the transparency-log position. level "human" means a tunnel employee checked identity, control of the channels, and that the service is real. level "automated
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result, or the merchant numeric id. |
Ask one specific question about a listing and get an answer from the registry, with no human involved. Try this before contact_business: it is instant, free, and does not put a message in someone's inbox. Returns either an answer or an escalation. When resolved is true, answer holds it and basis names the fields it was read from. When escalate is true we do not hold the fact — this is NOT
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | yes | The kind field from the same search result. |
| intent | string | yes | Which question to ask. "is_open_now" needs nothing else; "delivers_to" needs a params place; "lead_time" asks the shortest notice they accept an order on. |
| params | object | no | Arguments for the question. For "delivers_to": { "place": "Botanica" }. Ignored by the others. |
Same answers as ask_business, but you send the person's own words instead of choosing an intent, and the reply comes back in the language they used. Supported languages: en, ro, ru, de; anything else is answered in English. Prefer ask_business when you already know which of the three questions you are asking — it is instant and costs nothing, whereas this one runs a model to read the question and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | yes | The kind field from the same search result. |
| question | string | yes | What the person actually asked, in their own words and their own language. Do not translate or rephrase it — the language of this text decides the language of the reply. |
| idempotency_key | string | no | Optional, and only matters when a question reaches a person. The same question about the same business within 24 hours attaches to the open one and does not notify them twice, which is right when you |
Read the answer to a question that had to go to a human. Use the escalation.ref that ask_business_freeform returned when its outcome was "escalated". Returns a state and, once there is one, the business's own answer in their words. Branch on state: "open" means we have not reached them yet, "delivered" means the question is in front of them and unanswered, "answered" carries answer, "und
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | The escalation.ref from an earlier ask_business_freeform result. It is the only way to read this answer, so keep it. |
Read a commitment you were given by commit_order, including whether the business has since withdrawn it. Returns state: "issued" means it stands, "repudiated" means the business said they cannot honour it, with their stated reason. A withdrawal does not erase the original — both are on the record, timestamped. Check this before acting on a commitment made some time ago. Authentication: none. Thi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | The ref returned by commit_order. It is the only way to read this commitment. |
Read the prices a business has authorised us to quote on their behalf. Returns published and, when true, a rateCard holding a currency, an optional minimum charge and items — each with a code, a label, a unit and an amount. Those code values are what request_quote and commit_order take: we price exactly what you name and never work out which line a description meant, because a near-miss
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | no | Optional. The kind field from the same search result. Defaults to "entity". |
Price a specific set of line items against a business's rate card. Call get_rate_card first and name code values from it; we do the arithmetic. Returns quoted. When true you get total, lines showing what each one came to, and validUntil. A quote is a statement, NOT a hold — nothing is reserved and no price is locked. commit_order prices the same items again from the card at the moment it
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | no | Optional. The kind field from the same search result. Defaults to "entity". |
| items | array | yes | The lines to price. Each is an object with a code from get_rate_card and an optional quantity, which defaults to 1. Up to 100 lines. |
| note | string | no | Optional. What the job is, in the buyer's own words. Never parsed and never changes the figure; it is what a human reads if the quote has to go to one. |
| language | string | no | Optional. The buyer's language, recorded with the request. Defaults to English. |
Find out when a business is actually free. Worked out per call against their opening hours, their notice period, their blackout dates and what is already booked — there is no stored list of free times to be out of date. Returns known true with days, each holding slots that carry a start, an end and free. firstFree is the earliest one across the range. Pass time to ask about one exact m
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | no | Optional. The kind field from the same search result. Defaults to "entity". |
| from | string | no | Optional. First day to look at, yyyy-mm-dd in the business's own local calendar. Defaults to their today. |
| days | number | no | Optional. How many days to walk, 1 to 14. Defaults to 7. |
| time | string | no | Optional. One exact start time as HH:MM, 24-hour, on the first day of the range. The answer comes back under asked, and "not-a-slot-start" means their day divides differently — the free starts are l |
Place a binding order with a business, inside limits they set in advance. This is the only tool here that commits anyone to anything. Either name the figure yourself, or send items from get_rate_card and we price them from the merchant's own card. Either way it is checked against their price floor, maximum, daily capacity, notice period and blackout dates. Send time to take one slot rather tha
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | yes | The kind field from the same search result. |
| amount | number | no | What the buyer is offering to pay, as a number. Required unless you send items. This is your figure, not ours — we only check it against the limits the business set. Sent alongside items, it must |
| currency | string | no | ISO code, e.g. MDL or EUR. Required unless you send items. It must match the currency their limits are in. |
| items | array | no | Optional. Lines from their rate card, as request_quote takes them. When present, the price is theirs rather than yours and is computed fresh at this moment — a card that changed since you quoted refus |
| date | string | yes | The day the work or delivery is for, as yyyy-mm-dd, in the business's own local calendar. |
| time | string | no | Optional. A slot start on that day, HH:MM in 24-hour time and in their timezone. It must be one of the starts check_availability lists; times between them are refused rather than rounded to the neares |
| quantity | number | no | Optional. How many, as a whole number. Defaults to 1. Leave it out when you send items — the quantities are on the lines. |
| description | string | no | Optional. What the order is for, in plain words. Recorded and shown to the business; it is never parsed and never changes what we check. |
Cancel an order you placed with commit_order. Returns settled. True means it is cancelled, the business has been told and their day is free again. False comes with a reason: "inside-cancel-window" (later notice than they said they need), "no-cancel-window-set" (they never said), "order-passed", "not-open" (already cancelled or withdrawn) or "not-the-issuing-agent". Every reason but the last tw
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | The ref returned by commit_order. It is the only handle on this order. |
| note | string | no | Optional. Why, in the buyer's own words. Recorded, shown to the business and carried into the question if a person has to decide. Never parsed, and it cannot change the answer. |
Move an order you placed to a different date, or a booking to a different slot. The price, the items and the quantity are unchanged — this moves WHEN, nothing else. To change what was ordered, use request_order_change. A booking made for a time must be moved to a time, and a whole-day order to a whole day; the new slot is checked exactly as commit_order checked the first one. Call check_availabili
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | The ref returned by commit_order. |
| date | string | yes | The new day, as yyyy-mm-dd in the business's own local calendar. |
| time | string | no | The new slot start, HH:MM in 24-hour time and in their timezone. Required if the order was made for a time; leave it out if it was made for a whole day. |
| note | string | no | Optional. Why, in the buyer's own words. Shown to the business, never parsed. |
Raise anything else about an order that already exists: a change to what was ordered, a refund request, or a problem with what was delivered. This tool never settles anything, and that is deliberate. Changing an order re-prices it and a refund moves money tunnel does not hold, so both are decisions only the business makes. What this does is put the request in front of them with the whole order att
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | The ref returned by commit_order. |
| change | string | yes | What kind of request this is: "modify" to change what was ordered, "refund" to ask about money back, "other" for anything else including something being wrong. |
| note | string | yes | What the buyer actually said, in their own words. This is the part the business needs, so send it verbatim. Carried unchanged and never interpreted. |
Open a conversation with the person behind a listing. The message arrives in their dashboard inbox and they reply when they get to it — this is asynchronous, not a chat, and nobody is obliged to answer. Returns a conversation_id and a secret token. Keep both: they are the only way to read a reply (check_replies) or write again (send_followup), and the token cannot be recovered. Authenticatio
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug field from a search_businesses result. |
| kind | string | no | Optional. The kind field from the same search result. |
| agent_name | string | yes | Who is writing, in words the business will read — e.g. "Claude, on behalf of a customer". |
| subject | string | yes | Short subject line, like an email subject. |
| message | string | yes | The message body. Maximum 4000 characters. |
| agent_contact | string | no | Optional. An out-of-band address the business can reply to, e.g. the end user email if they agreed to share it. |
Read a conversation you opened with contact_business, including anything the business has replied since. Returns the whole message thread and its status. Poll it; there is no push. Authentication: the conversation_id and token from contact_business are the credential for this call. No bearer token is needed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | number | yes | The conversation_id returned by contact_business. |
| token | string | yes | The secret token returned by contact_business. |
Add another message to a conversation already opened with contact_business. Returns the updated message thread. There is a cap on messages per conversation, so send one considered follow-up rather than several fragments. Authentication: bearer token required — the same one used for contact_business — plus the conversation_id and token for the conversation itself.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | number | yes | The conversation_id returned by contact_business. |
| token | string | yes | The secret token returned by contact_business. |
| message | string | yes | The message body. Maximum 4000 characters. |
- 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 Knowledge Base 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 | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_businesses | no tags | |
| get_business | no tags | |
| check_merchant_verification | no tags | |
| ask_business | no tags | |
| ask_business_freeform | no tags | |
| check_escalation | no tags | |
| check_commitment | no tags | |
| get_rate_card | no tags | |
| request_quote | no tags | |
| check_availability | no tags | |
| commit_order | no tags | |
| cancel_order | no tags | |
| reschedule_order | no tags | |
| request_order_change | no tags | |
| contact_business | no tags | |
| check_replies | no tags | |
| send_followup | 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
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 1.1.0.
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 Knowledge Base 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.