# Homespun (npm · @homespunapps/mcp) Deploy a multi-user web app from your agent: hosting, auth, database, and permissions. - Trust score: 68/100 (medium) - Change this week: +61 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-03 ## Components - remote · `homespun.dev`: 79/100, [markdown](https://verifymcp.io/servers/dev-homespun-homespun/homespun.md), [page](https://verifymcp.io/servers/dev-homespun-homespun/homespun) - npm · `@homespunapps/mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/dev-homespun-homespun/homespunapps-mcp.md), [page](https://verifymcp.io/servers/dev-homespun-homespun/homespunapps-mcp) ## Channel facts - Registry: `npm` - Package: `@homespunapps/mcp` - Version: `1.6.42` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-08-03. - **Supply Chain Security**: 87/100 - No malware found by supply-chain analysis. - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree. - No install/post-install scripts declared. - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree. - **Provenance & Transparency**: 45/100 - Source repository is publicly reachable at the declared URL. - Provenance check failed: no build-provenance attestation is published. - Clear OSI-approved license (MIT). - Actively maintained (last published 0 days ago). - Disclosure check failed: no security disclosure policy was found in the source repository. - **Schema Quality & AI Usability**: 68/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 10460 tokens (~454/item across 23 items; 22 tools + 1 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 27/100 - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### Claude ```bash claude mcp add dev-homespun-homespun -- npx -y @homespunapps/mcp ``` ### Codex ```bash codex mcp add dev-homespun-homespun -- npx -y @homespunapps/mcp ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "dev-homespun-homespun": { "type": "local", "command": [ "npx", "-y", "@homespunapps/mcp" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add dev-homespun-homespun --command npx --arg -y --arg @homespunapps/mcp ``` ### Hermes ```yaml mcp_servers: dev-homespun-homespun: command: "npx" args: ["-y", "@homespunapps/mcp"] ``` ### Other ```json { "mcpServers": { "dev-homespun-homespun": { "command": "npx", "args": [ "-y", "@homespunapps/mcp" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-08-03 (score 68, +1) No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-08-02 (score 67, +44) - [security regression] Provenance: unverified → fail - [security improvement] Install scripts: unverified → pass - [security improvement] Known CVEs: unverified → partial - [security improvement] Malware scan: unverified → pass - [functional improvement] MCP protocol: unverified → pass - [functional improvement] Maintenance: unverified → pass - [functional improvement] Dependency health: unverified → partial - [functional improvement] License: unverified → pass - [functional improvement] Schema quality: unverified → good - [functional improvement] Stability: unverified → 0.23 - [functional] Licence: MIT - [functional] Package version: 1.6.41 → 1.6.42 ### 2026-08-01 (score 23, +18) - [functional improvement] Tool coverage: unverified → 100 - [functional improvement] Schema quality: unverified → 100 - [functional] First check of Schema quality: unverified - [functional] First check of Schema quality: fail - [functional] First check of Schema quality: fail - [functional] First check of Tool coverage: 100 - [functional] Package version: 1.6.39 → 1.6.41 ### 2026-07-31 (score 5, −1) - [security] First check of Stability: unverified - [functional] First check of Capabilities: unverified - [functional] Package version: 1.6.34 → 1.6.39 - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-30 (score 6, 0) - [functional] Package version: 1.6.25 → 1.6.34 - [functional] Package version: 1.6.25 → 1.6.29 - [functional] Package version: 1.6.25 → 1.6.26 ### 2026-07-29 (score 6, 0) - [security regression] Provenance: unverified → fail - [security improvement] Install scripts: unverified → pass - [security improvement] Known CVEs: unverified → partial - [functional improvement] License: unverified → pass - [functional improvement] Dependency health: unverified → partial - [functional improvement] Maintenance: unverified → pass - [functional] Licence: MIT - [functional] Package version: 1.6.19 → 1.6.25 - [functional] Package version: 1.6.19 → 1.6.22 ### 2026-07-28 (score 6, −1) - [functional regression] Dependency health: partial → unverified - [functional regression] Security disclosure: fail → unverified - [functional] Package version: 1.6.13 → 1.6.19 - [functional] Package version: 1.6.13 → 1.6.15 - [functional] Package version: 1.6.13 → 1.6.14 ### 2026-07-27 (score 7) First indexed and scored. ## MCP tools (22) ### `deploy_app` (~1771 tokens) Deploy App Deploy a v2 app: an HTML document plus a capability manifest, hosted at its own URL. ON REDEPLOY, SEND ONLY WHAT CHANGES. Every content field is optional when `app_id` is given, and an omitted one keeps what is live: omit `manifest` for an HTML-only change, omit `html` for a manifest-only change, omit `assets` to keep the current files. This is the cheap path and it is the one to reach for by default, because the omitted field costs no output tokens at all: a one-line colour change should not resend the whole document, and a manifest edit should not resend it either. Send a field only when its content is different from what is live. `assets: []` is the explicit way to clear the asset set, and omitting all three is refused, since there would be nothing to change. The manifest carries eight extension keys: app metadata; collections, with per-collection write, update, read and delete role lists, where write gates creates and also gates updates unless an update list is declared; externalHosts, a fetch allowlist; cdn, to allow CDN scripts and styles; capabilities, for Permissions-Policy opt-ins; embeds, an iframe frame-src allowlist; notify, for email-on-row rules; and webhooks, for signed HTTP POST on-row rules. The manifest grammar is documented in the Homespun guide that get_skill returns. Pass no `app_id` to create, which mints a slug and URL and requires both `html` and `manifest`, or pass `app_id` to redeploy an existing app. Supply the HTML inline as `html`, or as `html_path`, an absolute path read on the MCP-server host, which is the relay for a hosted connector or the CLI host for a locally-run one, and not the remote agent's machine; it avoids retransmitting a large HTML file on every deploy, only a locally-run connector can read it, and inline `html` wins if both are given. `dry_run:true` (alias `check`) validates only: it runs the full manifest and asset validation, the redeploy compat gate and the schedule-timezone advisory, then returns { ok, warnings,… Input parameters: - `app_id` (string): Omit to CREATE a new app; pass an existing app's id to REDEPLOY it (a new version, compat-gated unless force:true). - `assets` (array): Optional bundle of files shipped WITH the app in ONE deploy: images, fonts, audio/video, data. Each asset either carries its bytes inline as `content_base64` OR references an already-uploaded attachm… - `check` (boolean): Alias for `dry_run`. - `dry_run` (boolean): Validate only: run the full manifest + asset-shape validation, the compat gate (for a redeploy), and the schedule-timezone advisory, then return { ok, warnings, compat?, breaks? } WITHOUT creating a… - `force` (boolean): REDEPLOY only. Bypass the compat gate, whether it fired on a stranded-rows narrowing or on a widening of what the install screen discloses (a removed collection is detached, never deleted). - `html` (string): The app's UI as a complete HTML document (single file, up to the relay's size cap), sent inline. Provide either this or `html_path`. Inline is required for a hosted or remote connector that has no fi… - `html_path` (string): ABSOLUTE path to the app's HTML document, read on the MCP-SERVER host (the machine running this connector: the relay for a hosted connector, or your CLI host for a locally-run one), NOT on the remote… - `manifest` (object): The x-homespun-manifest capability document (a JSON object). REQUIRED to create; ON REDEPLOY, omit it to keep the live manifest, which is what most redeploys want (the manifest was byte-identical to… - `slug` (string): CREATE only. Accepted with visibility private or public, including the private default; rejected with explicit visibility 'link', where the slug is always server-generated. - `visibility` (string): CREATE only. Default 'private' (owner plus invited members, sign-in gated). 'link' shares with anyone holding the returned share_url, whose #k= fragment carries a secret key that can be reset (rotate… ### `list_rows` (~138 tokens) List Rows List rows in a v2 app's mutable collection. This is also how a collection's current state is polled, since MCP has no streaming: pass the prior next_cursor as `since` to fetch only rows that are new or changed. Returns { rows, next_cursor, has_more }. Input parameters: - `app_id` (string, required): The app id. - `collection` (string, required): The collection name declared in the app's manifest. - `limit` (integer): Page size. - `since` (string): Opaque cursor from a previous call's next_cursor. Also the POLL handle: pass it back to fetch only newer/changed rows. ### `get_row` (~81 tokens) Get Row Fetch a single row by its key from a v2 app collection, through a dedicated relay route rather than a client-side scan. Returns { row }, or an isError row_not_found. Input parameters: - `app_id` (string, required): The app id. - `collection` (string, required): The collection name. - `key` (string, required): The key of the row to fetch. ### `upsert_row` (~266 tokens) Upsert Row Create a row in a v2 app's collection, or return the existing row when `key` is already present (deduped:true). Row creation goes through this tool; there is no separate strict-create verb. Omit `key` to add a new row with a server-generated key, or pass `key` to ensure a row exists at that key. The collection must be declared in the app's manifest with 'agent' in its `write` list, which is the list that gates creates. When `key` matches a row the collection's `read` list does not reach for this caller, the result is row_not_found rather than the row, matching what get_row would return, so this never reads past `read`. Returns { row, deduped? }. Input parameters: - `app_id` (string, required): The app id. - `collection` (string, required): The collection name. - `data` (required): The row body - any JSON value valid against the collection's row schema (an object, or any JSON value for a schemaless collection). - `key` (string): Optional stable key. Reusing an existing key returns the existing row (deduped:true), or row_not_found when the collection's read list does not reach that row for you. ### `update_row` (~198 tokens) Update Row Update an existing row in a v2 app's collection, replacing its data. Gated by the collection's `update` role list when it declares one, and by its `write` list otherwise, so a collection that scopes updates to the row's `creator` refuses an edit on someone else's row. Pass if_match with the row's current version for an optimistic-locked update; on a version mismatch the relay returns the current row, which is what a retry needs. Returns { row }. Input parameters: - `app_id` (string, required): The app id. - `collection` (string, required): The collection name. - `data` (required): The new row body (replaces the row's data) - any JSON value valid against the collection's row schema. - `if_match` (integer): Optional optimistic-lock version. On mismatch the update is rejected with the current row in details.current. - `key` (string, required): The key of the row to update. ### `delete_row` (~129 tokens) Delete Row Soft-delete a row from a v2 app's collection. RECOVERABLE: the row is tombstoned, not destroyed, and restore_row brings it back for 30 days (see list_deleted_rows). A watcher sees the deletion live as op:delete on the change feed. Pass if_match for an optimistic-locked delete. Returns { deleted: true }. Input parameters: - `app_id` (string, required): The app id. - `collection` (string, required): The collection name. - `if_match` (integer): Optional optimistic-lock version. - `key` (string, required): The key of the row to delete. ### `list_deleted_rows` (~146 tokens) List Deleted Rows List a collection's recently deleted rows: the recovery bin. Deleting a row is a SOFT delete, so it can be restored with restore_row until recoverable_until passes (30 days after deletion by default). Owner or agent only, and deliberately independent of the collection's read permissions. Rows already purged appear with purged:true and cannot be restored. Returns { rows, next_before }. Input parameters: - `app_id` (string, required): The app id. - `before` (string): Cursor for the next page: pass back the previous page's next_before. - `collection` (string, required): The collection name. - `limit` (integer): Max rows to return (default 100). ### `restore_row` (~123 tokens) Restore Row Restore a soft-deleted row, undoing delete_row. The row comes back with its original data and creator, its version bumped. Find restorable keys with list_deleted_rows. Owner or agent only. Fails with restore_expired if the row was purged, or restore_conflict if another live row took a unique value this one held while it was deleted. Returns { row }. Input parameters: - `app_id` (string, required): The app id. - `collection` (string, required): The collection name. - `key` (string, required): The key of the deleted row to restore. ### `get_feed_events` (~269 tokens) Get App Feed Events Poll a v2 app's change feed for what has happened: row creates, updates and deletes, from any writer, agent or human. It is the long-poll analogue of `homespun apps watch`, since MCP has no streaming. The loop is: call with no `since` first, process the returned entries, keep the cursor, then call again passing it as `since` to get only newer entries. Passing wait (around 25) holds the request open until an entry arrives or it times out, which is how the feed is waited on rather than busy-polled. A `since` older than the retention floor returns resync_required, and the collections are then re-listed with list_rows. Returns { entries, cursor, truncated }. Input parameters: - `app_id` (string, required): The app id. - `limit` (integer): Max entries per page (capped server-side by FEED_PAGE_MAX). - `since` (integer): Opaque numeric cursor from a previous call's cursor. Omit (or 0) to read from the beginning. - `wait` (integer): Optional long-poll: how long the relay holds the request open waiting for a new entry (0-30s). Use ~25 when waiting for activity, then call again with the same cursor. ### `apps` (~525 tokens) Manage Apps The v2 app lifecycle apart from creation and redeploy, which deploy_app covers. Actions: list returns the owning human's apps; show returns full detail including manifest, timezone and has_share_token; update changes visibility and timezone, the slug being immutable, and switching to 'link' returns a share_url once; share_link_rotate issues a new share token for a 'link' app, returning a new share_url and revoking the old link, and generates one if the app has none; delete is an idempotent soft-delete; wake wakes a dormant app and is otherwise a no-op that reports the actual status; domain_set binds a custom domain and returns the DNS records the domain owner must publish, where the first domain bound serves the app and every later one redirects to it, which is how apex plus www is configured; domain_status returns the serving domain and its `aliases`, live-refreshed against Cloudflare when that is enabled, with last_error carrying the reason a domain is not activating; domain_remove unbinds one domain, or all of them when no `domain` is given, and is idempotent. Input parameters: - `action` (string, required): list: YOUR owning human's apps. show/update/delete/wake: act on one app (app_id). share_link_rotate: rotate a 'link' app's share token, returning a new share_url (the old link stops working); also ge… - `app_id` (string): Required for show/update/share_link_rotate/delete/wake/domain_set/domain_status/domain_remove. - `cursor` (string): list only. Opaque cursor from a previous next_cursor. - `domain` (string): domain_set: the bare custom domain to bind (e.g. app.example.com); the response's dns_records lists the DNS entries the domain owner must publish. domain_remove: OPTIONAL, the one domain to unbind -… - `limit` (integer): list only. Page size. - `slug` (string): list only. Exact-match slug filter. - `status` (string): list only. Default: active. - `timezone` (string): update only. The app's IANA timezone for `schedules` reminders (e.g. Europe/Berlin). An app that declares schedules with no timezone fires reminders at 08:00 UTC. - `visibility` (string): update only. The new visibility (slug is immutable). ### `members` (~558 tokens) Manage App Members A v2 app's membership (auth spec section 6): who besides the owner can sign in to a private app and write to member-scoped collections. Actions: add invites or attaches a member by email, attaching immediately when the email already has a Human and otherwise sending a magic-link invite; list returns the app's owner and members; set_role changes an existing member's declared custom role in place, or clears it when null, and leaves their sessions intact, which is what makes it the way to re-role someone rather than removing and re-adding them; remove is idempotent and also revokes the human's live sessions on this app, and the app owner cannot be removed; roles returns the derived roles summary, giving the effective access a holder actually has per declared role and collection, reported separately for signed-in members and for grant-link holders because their role floors differ, along with member and active-grant-link counts. Input parameters: - `action` (string, required): add: invite-or-attach a member by email (app_id+email; optional custom_roles). list: the app's owner + members (app_id). set_role: replace an existing member's declared roles in place without signing… - `app_id` (string, required): The app id. - `custom_roles` (array): add (optional) and set_role (required). The DECLARED roles (x-homespun-manifest.roles keys) attached to the member ALONGSIDE their base member powers. A member may hold several and holds the union of… - `email` (string): add only. The email to invite/attach. If a Human already exists for it, the member row is attached immediately; otherwise the relay emails a magic-link invite. - `human_id` (string): remove and set_role. The Human id to target — see list's `humanId` field. The app owner can be neither removed nor re-roled. - `role` (string): add only. Defaults to 'member' server-side — no other role is assignable via this API (ownership transfer is not available here). ### `grants` (~579 tokens) Manage App Grant Links A v2 app's grant links (M5). A grant link is a capability URL that confers a declared custom role (x-homespun-manifest.roles) on a stable per-holder anonymous identity, so a holder's own rows are isolated by author/:own scoping. A grant does not escalate to owner, member or agent. Actions: mint creates a link and returns a `grant_url` carrying the token in its #g= fragment, shown once and not recoverable afterwards; list returns the app's links and never a token; revoke is idempotent. mode 'once' is one-time, claimed by the first browser to open it; 'multi' is shared, capped by max_uses within expiry. An optional pin (pin_row_key or pin_where) narrows a holder to specific rows and never widens their access. One consequence worth knowing when minting: a write-only grant pinned to a single row key can still read that row's existing data back through create dedup, so such a grant exposes that row's current contents to the holder. Input parameters: - `action` (string, required): mint: create a grant link carrying a declared custom role (app_id+role). list: the app's grant links (app_id). revoke: revoke one link (app_id+grant_id). - `app_id` (string, required): The app id. - `grant_id` (string): revoke only. The grant link id (see list's `id` field). - `label` (string): mint only. Optional owner label shown in the grant list. - `max_uses` (integer): mint only (multi mode). Cap total claims; omit for unlimited within expiry. Ignored for once (forced to 1). - `mode` (string): mint only. once: one-time link, claimed by the first browser that opens it (a real per-person link; later opens by others are inert). multi (default): a shared link, capped by max_uses within expiry. - `pin_row_key` (string): mint only. Optional narrowing pin to a single row key. NARROWS within the role (never widens). Mutually exclusive with pin_where. - `pin_where` (array): mint only. Optional narrowing pin as Wave C2 where conditions ({field, op, value}[]). NARROWS within the role (never widens). Mutually exclusive with pin_row_key. - `role` (string): mint only. A DECLARED custom role for the app (an x-homespun-manifest.roles key). A built-in role (owner/member/agent/anyone) is rejected: a grant can never escalate. - `ttl_seconds` (integer): mint only. Grant lifetime in seconds; defaults to the server default (30 days) and is clamped to the server max. ### `ingest` (~593 tokens) Manage App Inbound Hooks A v2 app's inbound catch-hooks (inbound-webhooks). A catch-hook lets an external system such as Stripe, Zapier, Make, Home Assistant or an email router POST JSON to a secret URL that writes into a declared collection, so the app receives data with no agent online. Hooks are declared in the manifest (x-homespun-manifest.ingest) and materialized at deploy, so this tool has no create or delete: it reads back the URL, rotates a leaked one, and manages the opt-in signing secret. After deploying a manifest that declares a hook, list is what yields the exact URL to paste into the external system. Actions: list returns the app's hooks, each with its full secret URL, current rule collection, mode, wake and handshake settings, per-status delivery counts and signing-secret state; rotate mints a fresh URL secret for one hook by name and returns the new url once, after which the old url stops working immediately with no redeploy needed; set_signing_secret provisions or rotates a hook's signing secret, which is a different secret from the URL and is what a provider HMACs the body with, minting one returned once when `secret` is omitted or storing a provider value verbatim when it is passed, and never echoing it back; clear_signing_secret removes it. Signature verification currently ships dark: nothing verifies a signature yet. Input parameters: - `action` (string, required): list: the app's inbound catch-hooks, each with its full secret URL, current rule (collection/mode/wake/handshake), and per-status delivery counts (app_id). rotate: mint a fresh URL secret for one hoo… - `app_id` (string, required): The app id. - `grace_seconds` (number): set_signing_secret only. On a rotation, how long the previous secret stays valid so deliveries verify while you update the provider (default 3600, max 86400). - `name` (string): rotate / set_signing_secret / clear_signing_secret. The manifest ingest hook name (an x-homespun-manifest.ingest[].name). See list's `name` field. - `secret` (string): set_signing_secret only. A provider-generated signing secret to store verbatim (the Stripe path). Omit to have the relay mint one (the GitHub path), returned ONCE in the response. ### `attachments` (~1381 tokens) Manage Attachments Binary attachments (images, PDFs, audio, video) referenced from event payloads and input_data via `format: homespun-attachment-id`. Actions: upload, fetch, presign, finalize, download, show, list, delete, mint_token, revoke_token, list_tokens. Choosing an upload path matters for cost. An inline upload with `content_base64` carries the bytes in the tool-call arguments, so they enter the model context at a token cost proportional to file size, paid again on every retry; a few-hundred-KB image is already expensive. Two paths avoid that entirely: fetch, when the bytes are reachable at a URL, and presign plus finalize, when the client can PUT the raw bytes out of band. Inline upload suits small assets and clients that have neither a URL nor an out-of-band PUT. fetch takes { source_url (https), scope } and the relay downloads the URL itself behind an SSRF guard (https only, no private, loopback or metadata hosts, DNS pinned, redirects refused, size-capped and timed out), then runs the same byte-sniff, allowlist, size, quota and scan checks as any upload. It works on any storage backend. upload takes either `content_base64` (base64 bytes, no filesystem) or `file_path` (an absolute path read on the relay host, so it only applies when the file is local to the relay). presign plus finalize is token-free: presign with { mime, size, sha256, scope } returns { put_url, attachment_id }, the caller PUTs the raw bytes to put_url over plain HTTP out of band, then finalize with the attachment_id. At finalize the relay re-reads the stored bytes, sniffs the real type, and enforces the same allowlist, size, sha256, quota and scan checks, so a presign that misstates its mime is caught and never served inline. The presigned path requires the Azure storage backend; a filesystem self-host returns a clear not-supported error and fetch or inline upload apply there instead. download writes to an absolute out_path or returns base64. An upload is scoped to agent (the default, reusable) or app.… Input parameters: - `action` (string, required): Binary attachment operations. The upload path affects token cost: `fetch` and presign plus finalize keep the bytes out of the model context entirely, while upload with `content_base64` carries them i… - `app_id` (string): Required when scope=app. - `attachment_id` (string): Attachment id. Required for download/show/delete/mint_token/revoke_token/list_tokens. - `content_base64` (string): upload: the file bytes as base64, sent inline with no filesystem access. The base64 rides in the tool-call arguments and enters the model context, costing tokens proportional to file size; a few-hund… - `cursor` (string): list pagination cursor. - `file_path` (string): upload: ABSOLUTE path to a file read on the SERVER host running this MCP connector (the relay), NOT your machine. Only works when the file is local to the relay (e.g. a locally-run CLI). For a hosted… - `filename` (string): upload: display filename (defaults to the file's basename). - `limit` (integer): list page size (1..100). - `mime` (string): upload/presign: advisory Content-Type. The relay BYTE-SNIFFS the actual bytes and stores/serves that sniffed type regardless (a lying mime is caught, never served inline). Required for presign (scope… - `once` (boolean): mint_token: token self-deletes on first GET. - `out_path` (string): download: ABSOLUTE path to write the bytes to. If omitted, the bytes are returned base64-encoded in the result. - `scope` (string): upload scope (default agent). - `sha256` (string): presign: the hex SHA-256 (64 chars) of the exact bytes you will PUT. Committed at presign and re-verified against the uploaded bytes at finalize. - `size` (integer): presign: the exact byte length you will PUT. Committed at presign and re-verified against the uploaded bytes at finalize. - `source_url` (string): fetch: an https URL the relay downloads server-side, so the bytes do not enter the model context and cost no tokens. SSRF-guarded: https only, no private, loopback, link-local or metadata hosts, DNS… - `token_id` (string): revoke_token: the token id to revoke. - `ttl_seconds` (integer): mint_token: per-token TTL (clamped by scope default). ### `taste` (~165 tokens) Manage UI Taste Notes The agent's UI taste notes: a short freeform markdown document of presentation preferences gathered from human feedback, such as 'denser layout' or 'no rounded corners'. Reading it before generating or revising an app is what carries earlier feedback into new output. Actions: get returns the current document; set replaces it in whole, so it does not append; clear discards it. Scoped to presentation preferences rather than general storage. Input parameters: - `action` (string, required): The agent's freeform UI taste notes (markdown) — presentation preferences learned from human feedback. get: read them before generating an app. set: whole-document replace (taste, non-empty). clear:… - `taste` (string): The full markdown notes (required for set; whole-document replace, not append). ### `key` (~304 tokens) Manage API Key The calling agent's API key. Actions: list returns key info (agent_id, key_prefix, timestamps); mint creates a sibling API key for the caller's own agent identity with the same scope and ownership and returns its raw value once, which is how an MCP-driven agent hands a CLI or child process a working credential, and the raw value is not retrievable afterwards, the sibling appears in a later list made with it, and the owner can revoke it; revoke destroys the agent's own key, which stops working immediately and cannot be undone, so it requires confirm:true. The relay derives identity from the caller's token, so every action applies to the caller's own agent and mint cannot target another agent's id. Input parameters: - `action` (string, required): The calling agent's API key. list: key info (agent_id, key_prefix, timestamps). mint: mint a NEW sibling API key for YOUR OWN agent identity (same scope/ownership) and return its raw value ONCE, so u… - `confirm` (boolean): Required (true) for revoke. ### `feedback` (~165 tokens) Manage Feedback Feedback to the relay operator. Actions: create records a bug, feature or note with a message and an optional app_id; list returns the agent's own submissions, newest first, paginated by `before`. Input parameters: - `action` (string, required): Feedback to the relay operator. create: submit a bug|feature|note with a message (optional app_id). list: the agent's own submissions, newest first. - `app_id` (string): Optional app this feedback relates to (create). - `before` (string): list cursor from a prior page's next_before. - `limit` (integer): list page size (default 50, max 100). - `message` (string): Message body (required for create). - `type` (string): Feedback category (required for create). ### `agent` (~195 tokens) Manage Agent Identity Agent identity and binding. Actions: whoami returns the resolved relay URL, the active profile and whether a key is configured, with no network call and no secrets; claim binds this agent to a human using a one-shot claim code from their Settings UI, and is one-way; logout clears the locally saved key and profile but does not revoke it on the relay, which is what the `key` tool's revoke action does. Input parameters: - `action` (string, required): Agent identity. whoami: show the resolved relay URL, active profile, and whether a key is configured (no network, no secrets). claim: bind this agent to a human via a one-shot claim code the human ge… - `code` (string): The one-shot claim code (required for claim). ### `community` (~1851 tokens) Community Templates Publishing an app as a community template, taking your own listing back down, installing a template, and, for relay operators, reviewing submissions. Actions: publish, unpublish, get_config_contract, install, list_pending, get_submission, approve, reject, set_trust_level. publish captures a live app (html, manifest, the seed rows of its seedOnInstall collections, and listing metadata) into a pending template. It is installable by the returned direct link but is not listed in the public gallery until an operator approves it, and it requires a verified email and no more than a few pending submissions at once. Privacy consequence: an approved template's content and its captured seed rows become public to every platform user, so seed data in a published app must be example-only rather than real personal data. attest_example_only:true records that this was checked. A template may take a per-publisher `slug` (namespaced as /) and a semver `version` defaulting to 1.0.0, and a republish under the same slug must bump the version. unpublish is the publisher's own undo for a live listing, taken down by snapshot_id: it leaves the public gallery, search, and the direct snapshot install link. It works only on your own submissions, and a snapshot that does not exist or belongs to someone else reads as not found either way. Existing installs are unaffected, because an install is a fresh private copy rather than a live reference, so unpublishing never breaks an app someone already installed. It is idempotent, and publishing a new version is the way to put the listing back. get_config_contract reads what a template needs at install, meaning its settings collection and its ordered config and upload steps, by `ref`. install creates a fresh private copy of a template for the caller's owning human, passing answers as `config`, where a 'config' value is a string and an 'upload' value is a pre-uploaded attachment id from the attachments tool. The review actions are limit… Input parameters: - `action` (string, required): publish: publish one of YOUR apps as a community template (app_id; optional title/description/category/tags). PRIVACY: publishing makes the template content AND the captured seed rows (the LIVE rows… - `app_id` (string): publish only. The id of an app YOU own to publish. - `attest_example_only` (boolean): publish only. Set true to attest that the template content AND the captured seed rows contain NO real personal data. Publishing makes both PUBLIC to every platform user, so seed data (the live rows o… - `category` (string): publish only. Optional single-word category (e.g. 'household'). - `changelog_note` (string): publish only. A short note recorded in this version's changelog. - `config` (object): install only. The install-time answers as { stepKey: value } from the config contract: a 'config' step's value is a string, an 'upload' step's value is a pre-uploaded attachment id. Omit for a templa… - `cursor` (string): list_pending only. Opaque cursor from a prior next_cursor. - `derived_from_snapshot_id` (string): publish only. Optional remix/fork lineage: the snapshot id this template was derived from. - `description` (string): publish only. Listing blurb (up to 200 chars). Defaults to the manifest description. - `handle` (string): set_trust_level only. The @-handle of the publisher to promote or demote. - `limit` (integer): list_pending only. Page size (1..200). - `long_description` (string): publish only. Optional long-form description (up to 4000 chars) shown on the template detail page below the short blurb, for readers and search ranking. Plain text: blank lines become paragraphs, and… - `note` (string): reject only. The required rejection note shown to the publisher (delivered to their app feed). - `ref` (string): get_config_contract/install only. The template to read or install: a namespaced '/' or a community snapshot id. - `setup_steps` (array): publish only. Ordered typed setup steps an installing agent follows after install (up to 20). A 'config'/'upload' step may carry a `key` naming a field of the manifest's settingsCollection that its i… - `slug` (string): publish only. Optional per-publisher slug (lowercase, 3 to 48 chars, hyphens). Gives the template a namespaced id /; a republish reuses the slug and must bump the version. - `snapshot_id` (string): Required for get_submission/unpublish/approve/reject. The submission's snapshot id (from publish's response or list_pending). - `tags` (array): publish only. Up to 6 curation tags. - `title` (string): publish only. Listing title (1 to 80 chars). Defaults to the app's manifest name. - `trust_level` (string): set_trust_level only. 'established' fast-tracks the publisher's future submissions through review; 'new' reverts to full review. - `version` (string): publish only. Semver MAJOR.MINOR.PATCH (default '1.0.0'). A republish under the same slug must be strictly greater than the current version. ### `publisher` (~324 tokens) Publisher Profile The caller's community publisher identity: the @-handle and public profile shown in the template gallery. Actions: get returns the profile, including the handle, whether it has been claimed, tenure, and the rating and template counters; claim sets the handle from a lowercase 3-to-32-character string and may be used only once, after which the handle is permanent, and it refuses a handle that is reserved or already taken; update changes display_name, bio or url at any time. claim and update require a verified email. An existing publisher may hold a provisional `maker-...` handle assigned automatically, which claim renames on its one allowed use. Input parameters: - `action` (string, required): get: return YOUR publisher profile (handle, tenure, counters). claim: set your @-handle ONCE (handle arg; lowercase, 3 to 32 chars, permanent after claiming; needs a verified email). update: change y… - `bio`: update only. Short public bio (up to 500 chars); null clears it. - `display_name`: update only. Public display name (up to 80 chars); null clears it. - `handle` (string): claim only. The lowercase @-handle to claim (^[a-z0-9](?:[a-z0-9-]{1,30}[a-z0-9])$). Permanent once claimed. - `url`: update only. Public http(s) URL (up to 200 chars); null clears it. ### `review` (~538 tokens) Community Reviews Ratings and reviews of community templates, responses from a template's own publisher, and, for relay operators, moderation. Actions: create leaves a 1-to-5 star rating and an optional written body on a template the caller has installed, identifying it by `template` (\"/\") or by `handle` plus `slug`, and requires a verified email; each install yields exactly one review, and the aggregate carries across template versions. A body containing a link or a contact email is held automatically for a moderator before it appears. respond replies to a review of the caller's own template line (review_id plus response, or null to clear it), with one editable response per review. report flags a review for the relay's moderators (review_id plus reason) and is deduped per account. remove and unhold are limited to the relay's configured community reviewers: remove takes a review down and adjusts the rating aggregate, and unhold publishes a previously held review into the aggregate. Input parameters: - `action` (string, required): create: leave a star rating (1..5) and optional body on a community template YOU have installed (identify it by `template` "/" or by `handle`+`slug`); requires a verified email, and one… - `body` (string): create only. Optional written review (up to 2000 chars). - `handle` (string): create only. Publisher handle (with `slug`), an alternative to `template`. - `reason` (string): report only. Why you are reporting this review (up to 500 chars). - `response`: respond only. The publisher's public response (up to 2000 chars); null clears it. - `review_id` (string): Required for respond/report/remove/unhold. The review's id. - `slug` (string): create only. Per-publisher slug (with `handle`). - `stars` (integer): create only. Star rating, an integer 1 to 5. - `template` (string): create only. The namespaced template id / to review. ### `get_skill` (~114 tokens) Get Skill Guide The relay's SKILL.md, a generated guide to the Homespun workflow covering events versus records, the schema grammars and the poll loop. Needs no API key. Useful when working out how the other tools fit together, or to refresh a cached copy. Pass version_only:true to return just the relay's skill version string, which is enough to tell whether a cached copy is current. Input parameters: - `version_only` (boolean): If true, return only the relay's current skill version string instead of the full SKILL.md markdown. ## Diagnostics Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/dev-homespun-homespun/homespunapps-mcp#diagnostics ## Score history - 2026-08-03: 68 - 2026-08-02: 67 - 2026-08-01: 23 - 2026-07-31: 5 - 2026-07-30: 6 - 2026-07-29: 6 - 2026-07-28: 6 - 2026-07-27: 7 ## Links - npm package: https://www.npmjs.com/package/@homespunapps/mcp - Socket report: https://socket.dev/npm/package/@homespunapps/mcp - Repository: https://github.com/homespunapps/homespun - Website: https://docs.homespun.dev/ - Changelog RSS feed: https://verifymcp.io/servers/dev-homespun-homespun/homespunapps-mcp/changelog.xml - Changelog JSON feed: https://verifymcp.io/servers/dev-homespun-homespun/homespunapps-mcp/changelog.json - HTML version of this page: https://verifymcp.io/servers/dev-homespun-homespun/homespunapps-mcp