Bucky
REMOTE · BUCKYBUILD.COM
Compare markets, find lots that fit a buy box, and check what a site allows, with cited sources.
Available components
Last scanned (20 hours ago)
Scores higher than 65% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Maps and Location
Recent critical change
Authorization (22 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability71
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 9070 tokens (~431/item across 21 items; 19 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management29
- Stability check failed: schema churn in the 30 days we've observed: 10 tool removals, 14 breaking changes, 0 auth/transport breaks, 5 additions. See how to fix → Fail
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 80% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
- Supports UI / widget rendering.Pass
Checks we ran (14)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
- Capabilities
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 −3
No change was recorded against any check on this day. Stability & Change Management went from 47 to 29.
- 20 Nov 26 0
- Resource “Bucky” now points somewhere else: ui://bucky/app.html?v=3d67c43d424f → ui://bucky/app.html?v=02a84765c4ec security
- 18 Nov 26 0
- Server version: 2.1.2 → 2.1.4 functional
- “submitBuckyFeedback” added an optional parameter “confirm” cosmetic
- “submitBuckyFeedback” added an optional parameter “draft” cosmetic
- “saveToProject” reworded the description of “action” cosmetic
- “saveToProject” reworded the description of “parcelExternalIds” cosmetic
- 17 Nov 26 0
- Tool “findPlacesByMarket” rewrote its description, which is the text the model reads security
- Tool “getBylawSection” rewrote its description, which is the text the model reads security
- Tool “screenLots” rewrote its description, which is the text the model reads security
- Schema quality: excellent → good functional
- New tool “get_more_tools” functional
- New tool “reportBuckyFeedback” functional
- “checkSite” added an optional parameter “conversation_id” cosmetic
- “cityInventory” added an optional parameter “conversation_id” cosmetic
- “explainFeasibilityStatus” added an optional parameter “conversation_id” cosmetic
- “findPlacesByMarket” added an optional parameter “conversation_id” cosmetic
- “getBuckyMcpGuide” added an optional parameter “conversation_id” cosmetic
- “getBylawSection” added an optional parameter “conversation_id” cosmetic
- “getProjectContext” added an optional parameter “conversation_id” cosmetic
- “previewSiteCoverage” added an optional parameter “conversation_id” cosmetic
- “produceProjectReport” added an optional parameter “conversation_id” cosmetic
- “runFeasibilityAnalysis” added an optional parameter “conversation_id” cosmetic
- “saveToProject” added an optional parameter “conversation_id” cosmetic
- “screenLots” added an optional parameter “conversation_id” cosmetic
- “setProjectMapListing” added an optional parameter “conversation_id” cosmetic
- “submitBuckyFeedback” added an optional parameter “conversation_id” cosmetic
- “uiGetAnalysisStatus” added an optional parameter “conversation_id” cosmetic
- “uiRequestSignIn” added an optional parameter “conversation_id” cosmetic
- “updateProject” added an optional parameter “conversation_id” cosmetic
- “screenLots” reworded the description of “criteria” cosmetic
- 16 Nov 26 0
- Schema quality: 517 → 445 ▲ functional
- “checkSite” reworded the description of “context” cosmetic
- “cityInventory” reworded the description of “context” cosmetic
- “explainFeasibilityStatus” reworded the description of “context” cosmetic
- “findPlacesByMarket” reworded the description of “context” cosmetic
- “getBuckyMcpGuide” reworded the description of “context” cosmetic
- “getBylawSection” reworded the description of “context” cosmetic
- “getProjectContext” reworded the description of “context” cosmetic
- “previewSiteCoverage” reworded the description of “context” cosmetic
- “produceProjectReport” reworded the description of “context” cosmetic
- “runFeasibilityAnalysis” reworded the description of “context” cosmetic
- “saveToProject” reworded the description of “context” cosmetic
- “screenLots” reworded the description of “context” cosmetic
- “setProjectMapListing” reworded the description of “context” cosmetic
- “submitBuckyFeedback” reworded the description of “context” cosmetic
- “uiGetAnalysisStatus” reworded the description of “context” cosmetic
- “uiRequestSignIn” reworded the description of “context” cosmetic
- “updateProject” reworded the description of “context” cosmetic
- 12 Nov 26 0
- Resource “Bucky” now points somewhere else: ui://bucky/app.html?v=a5be05d4d6ad → ui://bucky/app.html?v=3d67c43d424f security
- Tool “getBuckyMcpGuide” rewrote its description, which is the text the model reads security
- “screenLots” reworded the description of “cursor” cosmetic
- 11 Nov 26 +7
- Tool “addSavedFolderItem” was removed ▼ security
- Tool “createSavedFolder” was removed ▼ security
- Tool “deleteSavedFolder” was removed ▼ security
- Tool “getFeasibilitySnapshot” was removed ▼ security
- Tool “listSaved” was removed ▼ security
- Tool “listSavedFolders” was removed ▼ security
- Tool “proposeResultFlags” was removed ▼ security
- Tool “removeSavedFolderItem” was removed ▼ security
- Tool “renameSavedFolder” was removed ▼ security
- Tool “saveLot” was removed ▼ security
- Tool “unsaveLot” was removed ▼ security
- Authorization: fail → partial ▲ security
- Resource “Bucky” now points somewhere else: ui://bucky/app.html?v=1706d518e6f0 → ui://bucky/app.html?v=a5be05d4d6ad security
- Tool “explainFeasibilityStatus” rewrote its description, which is the text the model reads security
- Tool “findPlacesByMarket” rewrote its description, which is the text the model reads security
- Tool “getBuckyMcpGuide” rewrote its description, which is the text the model reads security
- Tool “getBylawSection” rewrote its description, which is the text the model reads security
- Tool “previewSiteCoverage” rewrote its description, which is the text the model reads security
- Tool “produceProjectReport” rewrote its description, which is the text the model reads security
- Tool “saveToProject” rewrote its description, which is the text the model reads security
- Tool “screenLots” rewrote its description, which is the text the model reads security
- Schema quality: 420 → 516 ▼ functional
- Tool coverage: 75% → 83% ▲ functional
- Schema quality: good → excellent functional
- Destructive annotations: 100 → pass functional
- Server version: 2.1.0 → 2.1.2 functional
- Server version: 1.2.0 → 2.1.0 functional
- New tool “checkSite” functional
- New tool “uiRequestSignIn” functional
- “findPlacesByMarket” added an optional parameter “setId” cosmetic
- “produceProjectReport” added an optional parameter “previewId” cosmetic
- “getBylawSection” reworded the description of “geoDivisionId” cosmetic
- “getBylawSection” reworded the description of “sectionIds” cosmetic
- “getBylawSection” reworded the description of “zoneCode” cosmetic
- “saveToProject” reworded the description of “action” cosmetic
- “saveToProject” reworded the description of “lat” cosmetic
- “saveToProject” reworded the description of “lng” cosmetic
- “saveToProject” reworded the description of “parcelExternalIds” cosmetic
- “findPlacesByMarket” made “country” optional cosmetic
- 10 Nov 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 47.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://buckybuild.com/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=buckybuild.com | CN=YR1,O=Let's Encrypt,C=US | 30 Sept 2026 | 29 Dec 2026 | RSA 2048 | SHA256-RSA | 5ac2e0d516ee4e24fca2ad8e5200d5297c5 |
| SANs: buckybuild.com | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of buckybuild.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| buckybuild.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'none'; frame-ancestors 'none'; report-to csp-endpoint; report-uri /api/security/csp-report |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(self), microphone=(self), camera=(), payment=*, usb=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://buckybuild.com/api/mcp | Verified | 200 | |
| http (plaintext) | http://buckybuild.com/api/mcp | HTTPS enforced | 308 | https://buckybuild.com/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
checkSite Check a site: lot, zone and building envelope for an address ~508
Look up lot, zone, and building envelope for one street address in Canada or the US. Pass `address`. One address per call; cannot search or compare. Read exception before searching: its parcel zone label identifies the site-specific exception, chain contains the cited text and required references. Use that text first. text_missing means incomplete evidence, never no exception. Prevailing by-laws can be address-specific; do not apply every listed address provision to this lot. A live answer uses one site check from the monthly plan allowance; `usage` says if it was charged and how many are left. getBuckyMcpGuide reports the allowance for free. CMHC rental survey figures describe purpose-built rentals; the new-build proxy is the 2000 or later band. Missing facts are not surveyed or unavailable, never zero. Cite RMS figures as Source: CMHC, Rental Market Survey, October YYYY using referencePeriod. Cite starts and completions with their own source and period. Every envelope value carries a `status`. Never report `not_extracted` or `site_specific_schedule` as no limit or as zero — call `explainFeasibilityStatus` first. Envelope numbers are extracted ceilings. Call `getBylawSection` with a citation `knowledgeSectionId`, or with `coverage.geoDivisionId`, `zone.code`, and the section number, before treating a number as available on this lot. Do not fetch `zone.bylawSourceUrl`. `lot.minLotFrontageM` is the zone minimum. `lot.lotConformity` compares lot width, lot area, and floor area per unit to those minima. A missing input is `unknown`, never a pass. State every fail before quoting a unit count.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Street address to analyse, e.g. "4170 Sophia St, Vancouver BC". |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| source | string | – | Which question the caller is answering. Used for attribution and to pick the link back; the payload is the same either way. |
No output schema declared.
No examples provided.
cityInventory See what Bucky has mapped for a city ~305
Public city catalogue inventory. Pass exactly one of: cityName, lat and lng together, or geoDivisionId. A city name with multiple matches returns choices; after the user chooses, call again with that candidate geoDivisionId. Never pass a slug. Shows datasets grouped by topic as on file, not loaded yet, unavailable, or not confirmed. This is city coverage, not lot feasibility or operator health. CMHC rental survey figures describe purpose-built rentals; the new-build proxy is the 2000 or later band. Missing facts are not surveyed or unavailable, never zero. Cite RMS figures as Source: CMHC, Rental Market Survey, October YYYY using referencePeriod. Cite starts and completions with their own source and period. If Bucky has not mapped the place, the result points to recording demand. It does not record demand by itself.
| Name | Type | Req | Description |
|---|---|---|---|
| cityName | string | – | – |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| geoDivisionId | string | – | – |
| lat | number | – | – |
| lng | number | – | – |
No output schema declared.
No examples provided.
explainFeasibilityStatus Explain a Bucky feasibility status ~288
Explain one Bucky coverage or per-fact provenance status and the safe next action. This is a pure static lookup: it does not inspect an address, retrieve property data, or call a database, geocoder, AI model, or third-party API. Accepts exactly one of: live, live_unavailable, published, planned_not_live, geo_division_uncatalogued, unseeded_place, geocode_failed, cited, cited_conditional, conditional_unresolved, no_limit_in_bylaw, not_extracted, site_specific_schedule, unverified_default, derived_from_cited, defaulted, missing. Copy the status verbatim from a feasibility result. An unknown status returns this list instead of failing.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| status | string | yes | A Bucky coverage resolution status or per-fact provenance status returned by a feasibility result. Copy it verbatim. Do not paraphrase or invent a status. |
No output schema declared.
No examples provided.
findPlacesByMarket Find places by their rental market ~2,086
Rank Canadian or US places by rental market facts (vacancy, rent, rent growth, permits, population). Read-only; signed-in only. Pass `country` (CA or US; places rank only within one country) and a `preset` (CA: tight-rental, fast-rent-growth, undersupplied, mli-select-headroom; US: low-rental-vacancy, car-light), `filters` ({ key, min, max } inclusive, or `top`/`bottom` percent), or both; optional `region` (province or state), `sort`, `limit` (default 20, max 50) and `offset`. An unknown key returns the filterable keys. Returns counts { places, matched, inPlan, excluded, unknown }, matched places with their values and `access`, and the places missing a filtered value. Report the unknown count: a missing value is not a match and not a fail. `truncation.places.nextOffset` is the next `offset`. Each matched place has `access`: `in_plan` (the user can screen its lots), `available` or `not_sold` (not in the user's plan). Say how many matches are `in_plan`. Only screen lots in `in_plan` places. To run a saved filter set, pass `setId` from listPlaceMarketSets with `limit` and `offset` only. `unavailableFilters` lists stored filters that were skipped; tell the user. Cite every figure with the `sources` lines (CMHC for CA, ACS for US). Tell the user each filter used, in plain words with units: each result filter has a `text` field. To find lots, call screenLots with the `geoDivisionId` of each `in_plan` place. Turning a question into filters: pick the country from the place named (Ontario, Texas). Put a province or state in `region`. Map each condition to the closest key below. "Tight" or "low vacancy" is a max on a vacancy key; "growing" or "rising" is a min on a change key; "above" is min, "below" is max. Percent bounds are numbers: 5 means 5%. Money bounds are in the country's own dollars. A relative question ("top quarter for rent growth", "lowest 10% vacancy in the province") is a percentile filter: `top` keeps the highest-valued share of places, `bottom` the lowest,…
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| country | string | – | ISO country code. Places are filtered and ranked only within this country. |
| filters | array | – | – |
| limit | integer | – | – |
| offset | integer | – | Matched places to skip. Copy truncation.places.nextOffset for the next page. |
| preset | string | – | A preset id for the country; its filters apply first, then `filters` by key |
| region | string | – | Province or state, as a code (AB) or a name (Alberta) |
| setId | string | – | Run one of your saved filter sets, by id from listPlaceMarketSets. Pass it with limit and offset only. |
| sort | object | – | Defaults to the preset sort, else the first filter key |
No output schema declared.
No examples provided.
get_more_tools ~89
Report that the user's request needs a capability this server does not have. Records the report for the server's developers; it does not return or add tools.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | – |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
No output schema declared.
No examples provided.
getBuckyMcpGuide Get the Bucky MCP guide ~253
Call with no arguments on first contact. Optional `role`, `market`, and `scale` answer the first-call questions on a second call. Returns what this session should do next, and the two ideas Bucky uses: lists, and the properties in them. Signed in, it also returns `profile`: the standing answers Bucky has for this user and the questions still open; save answers with updateMyProfile.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| market | string | – | Which country the site is in. Answers "US or Canada?". |
| role | string | – | Who is asking. Answers "Developer, GC, or municipal reviewer?". |
| scale | string | – | One site or several. Answers "Single parcel, or a portfolio?". |
No output schema declared.
No examples provided.
getBylawSection Get cited bylaw section text ~448
Return the stored bylaw section text behind a snapshot citation. Pass `sectionIds` copied from `citations.*.knowledgeSectionId` on checkSite. Or pass `geoDivisionId` from `coverage.geoDivisionId`, `zoneCode` from `zone.code`, and `sectionNumbers` such as 3.1 or 3.2. Examples: {"sectionIds":["<knowledgeSectionId>"]} or {"geoDivisionId":"<coverage.geoDivisionId>","zoneCode":"RM-4","sectionNumbers":["3.1"]}. sectionIds and sectionNumbers are arrays; do not pass address, city, sectionId or sectionNumber. The markdown is the schedule text. A number in the snapshot can still be conditional on frontage, tenure, or adjoining district. Each section returns at most 12,000 characters. A cut section has `truncated: true`, `totalChars` and `nextOffset`: call again with that section id and `textOffset: nextOffset` for the rest. Ids or section numbers with no active chunk come back in `missing`.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| geoDivisionId | string | – | coverage.geoDivisionId from checkSite. |
| sectionIds | array | – | Copy citations.*.knowledgeSectionId from checkSite. 1 to 4 ids. |
| sectionNumbers | array | – | Section numbers to read, for example 3.1 or 3.2. 1 to 4 numbers. |
| textOffset | integer | – | Character to start each section at. Default 0. Copy nextOffset from a truncated section to read the rest. |
| zoneCode | string | – | zone.code from checkSite, for example C-2. |
No output schema declared.
No examples provided.
getProjectContext Get project context bundle ~416
Load one project with analysis envelope, compact agentStatus, document summaries, evidence summaries, the project memory digest, and external_ref when the project was imported from another system. Pass `include` for optional sections: tasks, members, insights, capital, visualEvidence. Default is none, so the payload stays the same as a call without include. Documents and evidence return up to `documentsLimit` / `evidenceLimit` (default 20, max 50); each include list returns up to 20. `truncation` gives `total`, `returned` and `truncated` for every list that can be cut. Writes to those sections stay on the Bucky CLI. You do not need a UUID: pass `project` with the name the user said, or call with neither and the result lists their projects to choose from. Use before composing reports or after scheduling analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| documentsLimit | integer | – | – |
| evidenceLimit | integer | – | – |
| include | array | – | Optional extra sections. Default is none, so the payload matches a call without include. tasks, members, insights, capital, and visualEvidence each reuse the matching product read — they are not sepa… |
| project | string | – | Project name to match, when you do not have the UUID. Case-insensitive; an exact name wins over a partial one. Matching more than one lists the candidates instead of guessing. |
| projectId | string | – | Project UUID. Omit if you pass `project`. |
No output schema declared.
No examples provided.
previewSiteCoverage Preview what Bucky has on file for an address ~253
Free preview, no sign-in needed. For one street address in Canada or the US, it says whether Bucky covers the place and which zoning facts it holds for the lot (lot boundary, zone, height, density, setbacks, permitted uses, overlays, parking): found, partly on file, or not on file. It returns no values: no zone code, heights, setbacks or areas. The lot outline is a shape with no scale. Use it when the user is not signed in and asks what they can build at an address. For the numbers, call checkSite. That call asks the user to sign in.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Street address to analyse, e.g. "4170 Sophia St, Vancouver BC". |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
No output schema declared.
No examples provided.
produceProjectReport Compose and export a project report PDF ~374
Compose a project report PDF. Pass `projectId` or `project`; with neither, the result lists projects and no meter is spent. preview=true composes without spending and returns `previewId`. confirm=true with that `previewId` exports exactly the text that was previewed; without it, confirm composes again. Export spends records.exports and is irreversible. Returns a signed download URL, never PDF bytes.
| Name | Type | Req | Description |
|---|---|---|---|
| audience | string | – | – |
| confirm | boolean | – | When true, compose (if needed), save, export PDF, and return a download URL. Required when preview is false. Spends records.exports and cannot be undone. |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| detail | string | – | – |
| planName | string | – | – |
| preview | boolean | – | When true, compose only — no export meter spend and no download URL. |
| previewId | string | – | From a preview result. With confirm=true it exports exactly that preview, with no second compose. A newer preview for the same project replaces it. |
| project | string | – | Project name to match, when you do not have the UUID. Case-insensitive; an exact name wins over a partial one. Matching more than one lists the candidates instead of guessing. |
| projectId | string | – | Project UUID. Omit if you pass `project`. |
| request | string | – | – |
No output schema declared.
No examples provided.
reportBuckyFeedback ~209
Report a missing capability, failed tool, or unusable result to Bucky automatically when it blocks or degrades your task. No human form is needed. Use feedback_type missing_capability or issue. Send only a short technical summary and tool/field names. Never include addresses, names, prompts, raw results, personal data or secrets. Reports are analytics, not human-endorsed feedback; no tools are added. Submit at most one report per distinct problem per task.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| details | string | – | – |
| feedback_type | string | yes | – |
| friction_points | string | – | – |
| sentiment | string | – | – |
| suggested_improvement | string | – | – |
| summary | string | yes | – |
| task_completed | boolean | – | – |
| tool_name | string | – | – |
No output schema declared.
No examples provided.
runFeasibilityAnalysis Run project feasibility analysis ~287
Enqueue a fresh deterministic analysis run for a saved project. Pass `projectId`, or `project` with the name the user said; with neither, the result lists their projects and nothing is queued. Returns immediately with `agentStatus` (`queued`, `running`, `current`, `failed`, or `none`) and a receipt id; does not block on completion. Irreversible: a queued run cannot be un-queued from MCP. Re-check with `getProjectContext`, but no more than once every 15 seconds — it is a multi-query bundle, not a status endpoint.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| project | string | – | Project name to match, when you do not have the UUID. Case-insensitive; an exact name wins over a partial one. Matching more than one lists the candidates instead of guessing. |
| projectId | string | – | Project UUID. Omit if you pass `project`. |
No output schema declared.
No examples provided.
saveToProject Create or attach to a project ~674
Create a project (`create`), attach lots (`attach_parcels`), or attach a knowledge reference (`attach_reference`). Pass `projectId` or `project`; with neither, the result lists projects and writes nothing. For attach_parcels, pass a WGS84 GeoJSON polygon (up to 500 selected parcels), or copy `lot.parcelExternalId` from checkSite. Polygon cannot be combined with parcelExternalIds or radiusM. Results report source truncation and attached count. preview=true returns the diff and writes nothing. A write returns a receipt. Not reversible on this surface.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | create: new project from a site. attach_parcels: attach lots to an existing project (use lot.parcelExternalId from screenLots or checkSite). attach_reference: link a knowledge section to an existing… |
| address | string | – | Street address of the site. On `create` this is geocoded server-side when lat/lng are not supplied, and is what gets recorded as the project address. |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| externalRef | string | – | Provenance of an imported project. Canonical form is `<system>:<id>` (e.g. `notion:<page-id>`). Unique per creator when set. Returned on getProjectContext. Distinct from idempotencyKey. |
| idempotencyKey | string | – | – |
| lat | number | – | Latitude from checkSite. Supplied coordinates are never re-geocoded. |
| lng | number | – | Longitude from checkSite. |
| name | string | – | – |
| parcelExternalIds | array | – | Source parcel ids to attach. Copy lot.parcelExternalId from screenLots or checkSite; no checkSite call is needed for lots screenLots returned. If they are not in the current area, pass a larger radiu… |
| polygon | object | – | WGS84 GeoJSON Polygon for attach_parcels. Attach the parcels selected by the product area flow, up to 500. Interior rings exclude parcels. Use polygon instead of parcelExternalIds and radiusM. Maximu… |
| preview | boolean | – | When true, return the field-level diff and write nothing. |
| project | string | – | Project name to match instead of a UUID, for attach_parcels and attach_reference. Matching more than one lists the candidates instead of guessing. Ignored by create. |
| projectId | string | – | Existing project UUID. Required by attach_parcels and attach_reference unless you pass `project`; ignored by create. |
| radiusM | integer | – | Search half-width in metres when resolving parcel ids. Default 150. |
| role | string | – | build is the lot being developed; context is surrounding land. Default build. |
| sectionUuid | string | – | – |
No output schema declared.
No examples provided.
screenLots Find lots that match a list ~1,348
Find the lots in one live Bucky city that match a list. Pass `city` or `geoDivisionId` with `thesis` (plain words), `criteria` (square feet, dollars), or both; or pass a saved `profileId`. Lot size goes inside criteria: {"city":"Toronto","criteria":{"minAreaSqft":10000,"maxAreaSqft":50000}}. Do not pass minAreaSqft at the top level or use lot_area. For all lots in a city, pass criteria:{} and hygiene:false. Without profileId, both a location and thesis or criteria are required. Returns countOutcome (exact, partial, at_least, estimate, or unavailable), screeningRunId, and selected lots ranked largest first with a pass, fail, or not_available verdict per filter. totalMatches is a compatibility value and can be returned-page size when the total is unavailable. Report a not_available filter; never present the count as filtered by it. The execution preserves selection for optional candidate assessment; assessment candidate counts are separate from search totals. Returns candidates, counted suggestions and savedMatches. Candidate/suggestion criteria use the same square-foot boundary as the input, including canonical registry values and strategies. Present these alternatives before asking to save. Pass the selected criteria with save=true only after explicit approval, without re-reading the thesis. For a height the user wants to build ("10 to 14 storeys"), use criteria.permitted_stories or permitted_height_m: the maximum the lot's zone allows. criteria.stories is the building standing on the lot. Each lot has `lotId` for updateSaved (action save), `address` for checkSite and `parcelExternalId` for saveToProject. Assembly lots carry the same ids. At most 25 lots per call (`limit`, default 10). `page` says which matches these are (offset, returned, total, truncated); when truncated, call screenLots with `page.next` for the next lots. Paging reads only: it saves nothing and uses no list quota. save=true saves the list (write scope, counts against the plan list limit) and ret…
| Name | Type | Req | Description |
|---|---|---|---|
| assembly | object | – | Assembly mode: also return candidate assemblies, 2 to maxLots adjacent lots that each pass criteria and together meet minCombinedAreaSqft and/or minCombinedFrontageFt. Use for "two or three adjacent… |
| city | string | – | City as the user said it, e.g. "Laval" or "Bedford, MA". Omit when you pass geoDivisionId or profileId. |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| criteria | object | – | Structured criteria, e.g. {"minAreaSqft":10000,"maxAreaSqft":50000}. Lot area filters belong here, in square feet, not at the top level. A field set here replaces the same field read from thesis. Pas… |
| cursor | string | – | Next page of the same list. Copy page.next from the prior result: it carries the cursor with the filters of the list. Do not combine with thesis. Reads only; nothing is saved. |
| geoDivisionId | string | – | Division id, from an earlier screenLots or cityInventory result. |
| groupBy | string | – | Adds `groups`: every match split by one field, with lot count and summed area per group, the top groupLimit groups plus other / withheld / unknown buckets that add up to the match count. owner: large… |
| groupLimit | integer | – | Groups to list before the rest are summed as other. Default 10, at most 25. |
| groupOrder | string | – | lots (default): most matching lots first. area: largest summed lot area first. lot_size and year_built ignore groupOrder and groupLimit: they list every band in its own order. |
| hygiene | boolean | – | Default true. Ad-hoc lists leave out public owners (owner_class), cap lot size at 5 acres unless criteria set any lot-size minimum or maximum, and ignore assessed values under $100,000 where the city… |
| limit | integer | – | Lots to return. Default 10, at most 25 per call; page.next reads the next lots. countOutcome states whether the total is exact, partial, at_least (a lower bound), estimate (about), or unavailable. |
| profileId | string | – | Saved list id. Runs the saved city and criteria. Do not combine with city, thesis, or criteria. |
| save | boolean | – | true saves the list to the account. Default false. Search execution history is recorded. |
| saveName | string | – | Name for a saved list. |
| sort | string | – | Order of the returned lots across every match. Default lot_area_desc (largest first). land_value_per_buildable_asc / assessed_value_per_buildable_asc: lowest assessed land (or total) value per builda… |
| thesis | string | – | The list in plain words, e.g. "industrial lots over half an acre outside the floodplain". |
| totals | boolean | – | true adds `totals`: the match count and summed lot area (sq ft and acres) of every match, not only the page. Use it for "how many acres" instead of adding up pages. groupBy implies it. First page onl… |
No output schema declared.
No examples provided.
setProjectMapListing List or unlist a project on the public map ~447
Put a project on the public Bucky map, or take it off. Pass `projectId`, or `project` with the name the user said; with neither, the result lists their projects and nothing is published. Listing publishes the build-lot centroid, the project name, its zone category, typology and lifecycle status to anyone — signed in or not. Nothing else about the project is published. The project must have a build lot with a centroid; a project that has only an address and no attached build parcel cannot be pinned. Ask the human before listing a site that is not already public knowledge. A client, a friend, or a private residence is theirs to publish, not yours. preview=true returns the current state, the exact pin that would be published, and any privacy warning, and writes nothing. Unlisting removes the pin but does not un-share anything already collected while it was public. To undo, call again with `listed` set to the opposite value (`listed: false` after listing); the result repeats this as `undo`.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| listed | boolean | yes | true lists the project on the public map; false removes it. Listing publishes the build-lot centroid and the project name to anyone, signed in or not. |
| preview | boolean | – | When true, return the current listing state, the pin that would be published, and any privacy warning, and write nothing. |
| project | string | – | Project name to match, when you do not have the UUID. Case-insensitive; an exact name wins over a partial one. Matching more than one lists the candidates instead of guessing. |
| projectId | string | – | Project UUID. Omit if you pass `project`. |
No output schema declared.
No examples provided.
submitBuckyFeedback Submit feedback to Bucky ~344
Open a human-reviewed feedback form and submit it to the Bucky product team. Call only when the user explicitly asks to send feedback, report a problem, suggest an improvement, or praise something. The server asks the MCP client to show the form; nothing is saved unless the human accepts it. Do not use for silent agent self-reporting.
| Name | Type | Req | Description |
|---|---|---|---|
| affectedToolName | string | – | Tool the user is commenting on, when already known |
| confirm | boolean | – | Only when this client cannot show the form: call first without confirm to get the draft back, show it to the user, and call again with the same draft and confirm: true only after the user says to sen… |
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| draft | object | – | Optional. Feedback you drafted from this chat when the user asked you to: what they tried, what went wrong, what they expected. Plain words. No prompts, raw tool output, addresses, names, personal da… |
| submissionId | string | – | Optional. A UUID for this submission; generated server-side when omitted. Pass the same UUID when retrying this exact feedback so it is not recorded twice. |
No output schema declared.
No examples provided.
uiGetAnalysisStatus Get analysis status ~147
Return only the analysis `agentStatus` for a project. Cheap enough to poll. Used by the Bucky app view; the model should call getProjectContext instead.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| projectId | string | yes | – |
No output schema declared.
No examples provided.
uiRequestSignIn Sign in to Bucky ~145
Return `signedIn: true` for a signed-in caller. An anonymous call gets the sign-in challenge. Used by the Bucky app view; the model should call the tool it needs instead.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
No output schema declared.
No examples provided.
updateProject Update project fields ~371
Patch project metadata (name, lifecycle status, externalRef). Pass `projectId`, or `project` with the name the user said; with neither, the result lists their projects and nothing is written. preview=true returns the field-level diff and writes nothing. A write returns a receipt; undoOperationId restores the captured prior fields. Does not archive or delete.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other… |
| conversation_id | string | – | The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics. |
| externalRef | – | – | Provenance of an imported project. Canonical form is `<system>:<id>` (e.g. `notion:<page-id>`). Unique per creator when set. Pass null to clear. |
| lifecycleStatus | string | – | Project stage. getProjectContext returns it as lifecycleStatus. |
| name | string | – | – |
| preview | boolean | – | When true, return the field-level diff and write nothing. Combined with undoOperationId, returns the stored receipt. |
| project | string | – | Project name to match, when you do not have the UUID. Case-insensitive; an exact name wins over a partial one. Matching more than one lists the candidates instead of guessing. |
| projectId | string | – | Project UUID. Omit if you pass `project`. |
| undoOperationId | string | – | Receipt id from a prior updateProject write. Restores the captured prior fields. With preview=true, inspects the receipt instead. |
No output schema declared.
No examples provided.
How do I install the Bucky MCP server?
Bucky is a hosted endpoint at https://buckybuild.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · buckybuild.com
claude mcp add --transport http com-buckybuild-bucky 'https://buckybuild.com/api/mcp'
What is the Bucky MCP server?
Bucky is an MCP server listed in the public MCP registry as com.buckybuild/bucky. Compare markets, find lots that fit a buy box, and check what a site allows, with cited sources. This page covers its hosted endpoint (https://buckybuild.com/api/mcp).
Is the Bucky MCP server safe to use?
Bucky scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Bucky MCP server expose?
Bucky exposes 19 tools: getBuckyMcpGuide, explainFeasibilityStatus, checkSite, getBylawSection, screenLots, and 14 more. Their descriptions and schemas cost roughly 8,992 tokens of context every time the server is loaded.
Does the Bucky MCP server require authentication?
No. We connected to Bucky without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Bucky MCP server still maintained?
Bucky is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Bucky MCP server?
VerifyMCP ran 14 checks on Bucky, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.