Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Bahá’í 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.
96/100
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Search Bahá’í texts and read passages in context with source links. Independent, read-only access.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http baha-i-mcp https://mcp.bahaigpt.com/mcp
# 2 — ask your agent for something these tools do
# library_info, search_passages, lookup_work and 4 more
Bahá’í costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DEAll 1 server
devmomo1 server
1 category
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. 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.
Claude Codedeclared by this listing
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 baha-i-mcp https://mcp.bahaigpt.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
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.
What you approve
7 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.
Return the library’s snapshot identity, document and passage counts, coverage and tool limits.
No parameter schema on file.
Search individual passage text lexically. All query terms must occur within one passage. Matching normalizes case, punctuation and diacritics. Filters apply before duplicate quotation grouping.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Words to find in passage text. Accepts 1–64 searchable terms. Example: justice unity. |
| limit | integer | no | Maximum results per page, from 1 to 50. |
| cursor | no | Continue from a returned next_cursor, keeping all other arguments unchanged. | |
| author | no | Filter by recorded passage author. Accepts a name, recognized alias or contributor ID. Name matching normalizes case, punctuation and diacritics; Bahaullah matches Bahá’u’lláh. Only scoped author role | |
| issuer | no | Filter by recorded publication issuer. Accepts a name, recognized alias or contributor ID. Name matching normalizes case, punctuation and diacritics; Bahaullah matches Bahá’u’lláh. | |
| language | no | Strict exact passage language from the versioned evidence projection when installed, otherwise source-recorded language. Unknown/conflicting values are excluded; hints and website locale are not text | |
| language_hint | no | Filter by the language hint recorded in the source markup. | |
| document_id | no | Restrict results to one document ID. | |
| document_type | no | Filter by the exact recorded document type. | |
| phrase | boolean | no | Match the query words as one adjacent phrase after normalization. |
| context | integer | no | Include up to this many adjacent passage positions on each side of each result, from 0 to 3. |
| group_duplicates | boolean | no | Group matching occurrences of the same quotation. Set to false to return occurrences individually. |
Look up a catalogued work by reviewed title alias, passage ID or work ID. Works may appear separately or inside larger publications. Return available languages and recorded source versions, including coverage and availability. Supply exactly one lookup parameter.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | no | A reviewed title alias. Matching normalizes case, punctuation and diacritics. Example: Tablet of Ahmad. | |
| passage_id | no | Find work mappings associated with this passage occurrence. | |
| work_id | no | Retrieve the catalogue entry for this work ID. |
Search complete source-defined Q&A pairs, numbered selections and extracts. Terms may occur in different component passages—for example, one in a question and another in its answer. Results return the individually cited components. Coverage: The Kitáb-i-Aqdas Q&A, The Hidden Words selections, and extracts in To Set the World in Order: Building and Preserving Strong Marriages. Additional reviewed c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Words to find across a source unit. Accepts 1–64 searchable terms. Example: sick permissible can match terms divided between a question and its answer. |
| document_id | no | Restrict results to units from one document ID. | |
| document_type | no | Filter by the exact recorded document type. | |
| author | no | Keep units where every component passage has this recorded author. Accepts a name, recognized alias or contributor ID. Name matching normalizes case, punctuation and diacritics; Bahaullah matches Bahá | |
| responsibility | no | Filter by a publication contributor in any recorded role, such as author, issuer, compiler or translator. Accepts a name, recognized alias or contributor ID. Name matching normalizes case, punctuation | |
| language | no | Strict exact passage language from the versioned evidence projection when installed, otherwise source-recorded language. Unknown/conflicting values are excluded; hints and website locale are not text | |
| phrase | boolean | no | Match the query words as one adjacent phrase in the normalized unit text. |
| limit | integer | no | Maximum units per page, from 1 to 10. |
| cursor | no | Continue from a returned next_cursor, keeping all other arguments unchanged. |
List sections derived from recorded source headings, preserving their hierarchy. Return titles and identifiers for reading sections or browsing their children.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| version_id | string | yes | Text-version ID from a returned passage or work occurrence. |
| section_id | no | Parent section whose direct children to list. Omit to list root sections. | |
| limit | integer | no | Maximum sections per page, from 1 to 20. |
| cursor | no | Continue from a returned next_cursor, keeping all other arguments unchanged. |
Find document records by title, publication contributor, supported date or matching passage text. Returns metadata and identifiers rather than document text. Omit filters to browse records.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | no | Find titles containing all supplied terms after normalization. Accepts 1–16 terms and supports partial-word matches. Example: Hidden Words. | |
| content_query | no | Keep documents containing a passage that matches all supplied terms. Accepts 1–64 searchable terms. | |
| document_type | no | Filter by the exact recorded document type. | |
| responsibility | no | Filter by a publication contributor in any recorded role, such as author, issuer, compiler or translator. Accepts a name, recognized alias or contributor ID. Name matching normalizes case, punctuation | |
| date_from | no | Inclusive lower bound for supported document dates, in YYYY-MM-DD format. Month-only date ranges are separate metadata and are excluded from exact date filtering. | |
| date_to | no | Inclusive upper bound for supported document dates, in YYYY-MM-DD format. Month-only ranges do not establish an exact day. | |
| date_status | no | Select documents whose date is supported, unknown or ambiguous. | |
| order | string | no | Sort by title or ascending document_date. Date ordering places unknown or ambiguous dates last. |
| limit | integer | no | Maximum documents per page, from 1 to 20. |
| cursor | no | Continue from a returned next_cursor, keeping all other arguments unchanged. |
Read an identified passage, complete source group, section or recorded work version. Supports continued reading and adjacent-source navigation. Supply exactly one source identifier; work_id also requires language.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| passage_id | no | Read this exact passage occurrence. | |
| unit_id | no | Read this complete source group, such as a Q&A pair or multi-paragraph extract. | |
| section_id | no | Read this source section in order, including its headings. | |
| occurrence_id | no | Read a work version listed in returned work metadata, within its recorded source boundaries. | |
| work_id | no | Read a catalogued work in the requested language, using its default eligible source version. Supply language. If several versions qualify, the result lists the choices. | |
| language | no | Recorded language value to select with work_id, such as ar, en or fa. Use und for unknown-language or mul for mixed-language occurrences. | |
| direction | string | no | Select current, next or previous content. Passage targets navigate adjacent passages; group targets navigate adjacent groups or ungrouped passages. Navigation stays within the enclosing section, or te |
| context | integer | no | For a current passage target, include adjacent passage positions on each side, from 0 to 3. |
| text_start | integer | no | Starting Unicode character offset for a passage target. Defaults to 0. |
| limit | integer | no | Maximum passages per page, from 1 to 5. A passage target returns one selected passage plus requested context. |
| text_chars | integer | no | Maximum Unicode characters per passage slice: 1–12,000 for passage targets; 1–4,000 for other targets. |
| cursor | no | Continue from next_cursor, keeping all other arguments unchanged. |
Free
$0 forever
- 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 Bahá’í 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: —
ATool-list grade · score 96 / 100
Release 2.1.0 · scanned 7 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest43e710b9b2950cc386e84d001bb20faf112a2dd53fbc36f92a2fe066f3f411b8
Score vectorthreat 100 → client 96
| 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 |
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.
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.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
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 |
|---|---|---|
| library_info | no tags | |
| search_passages | no tags | |
| lookup_work | no tags | |
| search_passage_groups | no tags | |
| list_sections | no tags | |
| find_documents | untrusted-input | untrusted-input: keyword "browse" |
| read_text | 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 digest43e710b9b2950cc3
Scanned2026-11-07
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 2.1.0.
2.1.0
undated
latestNo release note was published with this version.
—
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 Bahá’í 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.