
Servidor MCP de Homespun
Qué servidores MCP son de Homespun, del registro oficial y encontrados preguntando a su propio dominio, si responden y qué ofrecen. Un programa comprobó cada dato; nada está copiado de la página del producto.
leído el 2026-10-26
- Nombre en el registrodev.homespun/homespunverificado en el registro MCP
El nombre en el registro está bajo homespun.dev. El registro solo permite usar ese espacio de nombres a quien demuestra control del dominio por DNS o HTTP.
- Estadorespondecomprobado el 2026-10-26
- Herramientas27
- El servidor se llamahomespun
- Versión del servidor1.6.99
- Versión del protocolo2025-06-18
El 2026-10-26 el servidor respondió a initialize y tools/list sin iniciar sesión. Primera respuesta en 132 ms.
- Aún no se ha juzgado si sus herramientas hacen el trabajo del producto.
- Comprobado 2 de los 7 días necesarios para juzgar su fiabilidad.
Una vez conectado
- Para "collect order forms and read the entries back later", la primera llamada probable es deploy_app.
- document_upload, add_row, update_row, delete_row, transfer cambian datos sin iniciar sesión: cualquiera con la dirección puede llamarlas.
- Sus definiciones ocupan unos 20004 tokens de contexto: activa solo las herramientas que necesita la tarea.
Lo dicen reglas a partir de las mediciones de arriba. La primera llamada probable la elige un modelo de la lista de herramientas; lee su descripción antes de fiarte.
- Nota INITE MCPtras una semanala nota necesita 7 comprobaciones diarias: 2 hasta ahora
- Uso453 descargas en npm por semana1 estrellas en GitHub
- Respondiómidiendo2 de las 7 comprobaciones diarias necesarias para mostrar el porcentaje
- Mediana de la primera respuesta462 ms
- Espacio en el contexto del agente≈ 20.004 tokenslas definiciones de todas sus herramientas (27), que el agente lleva en cada turno
- Definiciones de herramientasA · 100 de 100
- Resultados tipados0 de 27 herramientasdeclaran outputSchema: el resultado llega tipado y se lee de una vez
- Todas las herramientas pasan las seis comprobaciones.
Qué puede hacer un agente con él
- no está claro · build a booking page that emails you on new bookings
- puede · collect order forms and read the entries back later
- no está claro · run a shift signup or rota that others can join
Cada caso de uso del producto se le preguntó a Jev junto con la lista de herramientas de este servidor: ¿puede un agente hacerlo con estas herramientas?
Conviene revisar
- Herramientas que cambian datos, en un servidor que responde sin iniciar sesión: document_upload, add_row, update_row, delete_row, transfer
Un programa comprueba el servidor una vez al día: initialize y tools/list, sin modelo. Los tokens son la longitud de las definiciones, a unos cuatro caracteres por token. La nota promedia seis comprobaciones del nombre, la descripción, el esquema y las anotaciones de cada herramienta; dice lo bien descritas que están, no si funcionan. La nota pondera solo lo medido: si responde (25%), si hace el trabajo del producto (25%), definiciones (20%), contexto (10%), uso (10%) y lo fácil que es conectarse (10%). Lo que no se midió queda fuera, y una instrucción oculta limita la nota a 40. El estado de los servidores MCP de los proveedores: método y números →
document_uploadCreate a short-lived, byte-scoped upload session for an HTML document authored in a native editor or shell. The caller supplies the exact UTF-8 byte length and SHA-256 hex digest as { size, sha256, app_id? }. The returned `upload_url`…
deploy_appDeploy a v2 app: an HTML document plus a capability manifest, hosted at its own URL. For sandbox-authored files in hosted chat, native file editing and shell tools can create and validate the document. Its UTF-8 byte length and SHA-256 go…
list_rowsList 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…
count_rowsThe live row count of a v2 app's collection (spec B4, issue #1056), a whole-scope total with no filter and no paging. Gated by the collection's countRead opt-in, independent of its read list: a collection that opted in returns its count…
get_rowFetch 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.
add_rowCreate 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…
update_rowUpdate 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…
delete_rowSoft-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…
list_deleted_rowsList 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…
restore_rowRestore 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…
get_feed_eventsPoll 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`…
appsThe 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; audit is a read-only security review…
membersA 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…
grantsA 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…
transferA v2 app's ownership transfer (issue #1847): handing the app, and the quota and billing responsibility that come with it, to a different human. This is two steps, and `start` completing is only the first one. start mints a pending offer…
credentialsA v2 app's scoped service credentials (#1354, #1355): the bearer token an app owner points a backend they host themselves at, so their own server can read and write the app's data without holding the owner's full authority. Effective…
connectionsA v2 app's Connections: the stored credential (a static header token, or a full generic OAuth2 client) a manifest webhook rule authenticates its delivery target with, bound to a host so the credential can never be exfiltrated to another…
ingestA 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…
attachmentsBinary 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…
tasteThe 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…
keyThe 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…
feedbackReports a problem with homespun itself to the relay operator, and lists what this agent has already reported. A report is the operator's only visibility into a failure that happened inside an agent's session, so an unreported one is a…
agentAgent 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…
communityPublishing 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…
publisherThe 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…
reviewRatings 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…
get_skillThe 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…
Cómo conectar
Añade el servidor a la configuración de tu cliente MCP. Claude Desktop, Cursor y la mayoría de los demás clientes leen este formato:
{
"mcpServers": {
"homespun": {
"type": "http",
"url": "https://homespun.dev/mcp"
}
}
}Añadirlo
Claude Code, en una terminal
claude mcp add --transport http homespun https://homespun.dev/mcpAñadir a CursorAñadir a VS Code
claude.ai, ChatGPT y otros clientes: añade https://homespun.dev/mcp como conector personalizado en los ajustes.
También se distribuye por: npm
Cada línea es algo que un programa encontró al buscar: la entrada del registro, la respuesta del propio servidor, una especificación que se puede leer. Si falta una línea, es que no la encontramos, no que no exista.
Cookies
Antes de contar esta visita
La analítica y la medición de anuncios nos dicen qué páginas y cuáles de nuestros anuncios cumplen su función: Google Analytics y Google Ads, el píxel de Meta, Yandex Metrica y un identificador propio. No se guarda nada hasta que respondas, y rechazar no cambia nada del sitio.