Use Hjarni with Meta Muse

Does Meta Muse support MCP?

Building your own agent with Muse Spark on the Meta Model API? Your application runs the MCP client and passes Hjarni's tools to the model. Meta AI Connectors is another route: a developer preview for integrating services into Meta AI, covered below.

Sources: Muse Code MCP documentation, Muse connector guidelines, and Meta AI Connectors.

Connect Muse Code over MCP

Search your project decisions before a coding session. Save what changed when you finish. The notes stay in Hjarni, where Claude and ChatGPT can use them too.

{
  "schema_version": 1,
  "mcp_servers": {
    "hjarni": {
      "transport": "streamable_http",
      "url": "https://hjarni.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      },
      "enabled": true,
      "mode": "optional"
    }
  }
}

muse mcp login hjarni

This configuration follows Meta's MCP documentation and settings reference. We have not yet verified the Hjarni connection end to end in Muse Code.

Connect the Muse app through REST

The API contract Muse needs

Everything below is what a custom connector has to know. The Markdown twin of this page is the same content without the markup, which is the URL to hand any agent. The full REST API reference documents every endpoint, including the ones Muse will not need.

Base URL

https://hjarni.com/api/v1

Auth

Authorization: Bearer YOUR_API_TOKEN

Content type

application/json

Pagination

page and per_page query params, 25 per page by default and 100 at most. The total comes back as an X-Total-Count header, with X-Page and X-Per-Page beside it.

Rate limit

100 requests per minute, per account rather than per token, so this connector shares one budget with every other token on the account. Over it returns 429 with Retry-After.

Response shape

No envelope on the way out: collections are bare JSON arrays, a single note or folder a bare object. Writes take the {"note": {...}} wrapper, reads do not return one.

Note format

Markdown body, plus a short summary the agent should always write.

The six calls that cover ordinary use

Worked examples

Run these in a terminal first, so a later failure has one fewer cause. A working curl rules out the token and the endpoint; it does not by itself prove the remaining fault is Muse's, since a connector can also be sending a shape the API refuses.

Confirm the token

curl https://hjarni.com/api/v1/me \
  -H "Authorization: Bearer YOUR_API_TOKEN"

Search, titles and summaries only

curl "https://hjarni.com/api/v1/search?q=quarterly+planning&search_scope=personal&exclude_body=true" \
  -H "Authorization: Bearer YOUR_API_TOKEN"

Create a note

curl -X POST https://hjarni.com/api/v1/notes \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "note": {
      "title": "Kitchen renovation quotes",
      "body": "- Vanhoof: EUR 14,200\n- De Smet: EUR 12,800",
      "summary": "Two quotes for the kitchen, with prices and lead times.",
      "tag_list": "house, renovation",
      "container_id": 12
    }
  }'

That container_id is an example. Take a real one from GET /containers and make sure the token has Write access there. An unknown or inaccessible folder is refused. With an agent token, leaving the folder out also needs a grant on the destination inbox, so send an explicit folder ID. A request carrying no note object at all answers 400.

Two shapes, and a connector that reads only one reports the other as a blank failure: a single error string, or an errors array when a note fails validation. Most errors are JSON, but not all of them are guaranteed to be, so send Accept: application/json and treat a non-JSON error body as possible rather than impossible.

What to ask the Muse app once connected

With the agent token above, Muse can search and read the personal or team notes its grants reach, and write where you gave it Write access. A full-access, account-wide REST token searches across teams but opens and edits personal notes, so a team search hit may not be readable with that token. Try these prompts when the relevant folders and other connectors are available:

• Across Gmail and your notes. “Find the contractor emails from last month and add anything new to my kitchen renovation note in Hjarni.”
• Before a meeting. “My calendar says I am seeing Anna at 3. Search Hjarni for what we agreed last time.”
• Capture on the phone. “Save this as a Hjarni note in my Ideas folder, with a summary.”
• Keep one note true. “Update my ‘working preferences’ note rather than making a new one.”

Tell Muse once to always write a two or three sentence summary on a new note. Summaries are indexed for search and are what a result list carries in place of a full body, so a connector that skips them leaves every other assistant less to go on when it picks which note to open.

What to expect from a REST connector

These limits apply to the Muse app's custom REST connector. Muse Code uses MCP and receives the server's tool descriptions directly.

If Muse is your only assistant, this is a reasonable connection and the notes stay yours either way. If you also use Claude or ChatGPT, connect those over MCP and treat Muse as a second reader of one knowledge base. MCP vs API is the longer version of this argument.

What about Meta AI Connectors?

Meta's developer site describes a separate connector program for Meta AI on its app, web, and AI glasses. Developers onboard REST endpoints through a guided interface or MCP onboarding, then link user accounts with OAuth.

That MCP onboarding is a developer workflow. It does not establish that a Muse app user can paste in Hjarni's MCP URL. Meta AI's program is a limited developer preview, with public publishing planned for a later phase.

Hjarni has a REST API and an MCP server, but this guide does not provide a published Meta AI connector. For now, use the Muse Code setup above or the Muse app REST contract above. Read Meta's connector preview details for the program's current availability.