mcpField
J
Junê

Junê

Local
june.januraine.aiMemory & Knowledge
RepositoryVisit website

About Junê

Shared, cited knowledge-graph memory for agents: ask, search, remember, keep standing instructions

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "junemind-june": {
      "command": "uvx",
      "args": [
        "june-mcp"
      ],
      "env": {
        "JUNE_BASE_URL": "<JUNE_BASE_URL>",
        "JUNE_CANVAS": "<JUNE_CANVAS>",
        "JUNE_API_KEY": "<JUNE_API_KEY>",
        "JUNE_LLM_KEY": "<JUNE_LLM_KEY>",
        "JUNE_CANVAS_CREATE": "<JUNE_CANVAS_CREATE>",
        "JUNE_READONLY": "<JUNE_READONLY>",
        "JUNE_FILES_ROOT": "<JUNE_FILES_ROOT>",
        "JUNE_DOCS_CANVAS": "<JUNE_DOCS_CANVAS>",
        "JUNE_DOCS_REFRESH": "<JUNE_DOCS_REFRESH>",
        "JUNE_REFRESH_CALLS": "<JUNE_REFRESH_CALLS>",
        "JUNE_REFRESH_MINUTES": "<JUNE_REFRESH_MINUTES>",
        "JUNE_DIGEST_CHARS": "<JUNE_DIGEST_CHARS>",
        "JUNE_EXPORT_ROOT": "<JUNE_EXPORT_ROOT>"
      }
    }
  }
}
Run commanduvx june-mcp
Environment variables to set
JUNE_BASE_URLYour June endpoint, e.g. http://localhost:8000 (the Junê desktop app's local engine, your own june-local service, or a hosted Team workspace)
JUNE_CANVASThe canvas (workspace) to bind this connection to — a name (e.g. 'work') or a canvas id; names resolve at startup and ambiguous names fail closed
JUNE_API_KEYSecretYour June API key (set JUNE_ALLOW_ANON=1 instead to explicitly opt out for keyless local setups)
JUNE_LLM_KEYSecretBring-your-own LLM key for cited answers — forwarded per-request as a header, never logged or stored on the service
JUNE_CANVAS_CREATESet to 1 to create the named canvas on first run if it doesn't exist yet (refused in read-only mode)
JUNE_READONLYSet to 1 to hide and refuse all write tools (memory becomes read-only)
JUNE_FILES_ROOTOpt-in directory agents may upload files from via june_ingest_file — unset means that tool doesn't exist
JUNE_DOCS_CANVASCanvas holding the agent's standing docs/skills/learnings (default 'agent_docs')
JUNE_DOCS_REFRESHSet to 0 to disable the periodic standing-docs digest re-injected on tool results (default on)
JUNE_REFRESH_CALLSTool calls between digest injections (default 12) — lower it for small-context agents
JUNE_REFRESH_MINUTESWall-clock fallback between digest injections (default 10)
JUNE_DIGEST_CHARSStanding-docs digest size cap in characters (default 2000)
JUNE_EXPORT_ROOTOpt-in directory for repo sync — enables june_docs_export / june_page_export / june_page_import (fenced writes, commit-only git); unset means those tools don't exist

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypijune-mcp0.8.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.