Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions
Junê is an MCP integration. Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions.
The published pypi package is june-mcp, version 0.8.1. Its declared MCP transport is stdio.
The package declares JUNE_BASE_URL (required): Your 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_CANVAS (required): The 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_KEY (required): Your June API key (set JUNE_ALLOW_ANON=1 instead to explicitly opt out for keyless local setups); JUNE_LLM_KEY: Bring-your-own LLM key for cited answers — forwarded per-request as a header, never logged or stored on the service; JUNE_CANVAS_CREATE: Set to 1 to create the named canvas on first run if it doesn't exist yet (refused in read-only mode); JUNE_READONLY: Set to 1 to hide and refuse all write tools (memory becomes read-only); JUNE_FILES_ROOT: Opt-in directory agents may upload files from via june_ingest_file — unset means that tool doesn't exist; JUNE_DOCS_CANVAS: Canvas holding the agent's standing docs/skills/learnings (default 'agent_docs'); JUNE_DOCS_REFRESH: Set to 0 to disable the periodic standing-docs digest re-injected on tool results (default on); JUNE_REFRESH_CALLS: Tool calls between digest injections (default 12) — lower it for small-context agents; JUNE_REFRESH_MINUTES: Wall-clock fallback between digest injections (default 10); JUNE_DIGEST_CHARS: Standing-docs digest size cap in characters (default 2000); JUNE_EXPORT_ROOT: Opt-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.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 0.8.1 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related other integrations MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| JUNE_BASE_URL | Your June endpoint, e.g. http://localhost:8000 (the Junê desktop app's local engine, your own june-local service, or a hosted Team workspace) | Yes |
| JUNE_CANVAS | The 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 | Yes |
| JUNE_API_KEY | Your June API key (set JUNE_ALLOW_ANON=1 instead to explicitly opt out for keyless local setups) | Yes |
| JUNE_LLM_KEY | Bring-your-own LLM key for cited answers — forwarded per-request as a header, never logged or stored on the service | Optional |
| JUNE_CANVAS_CREATE | Set to 1 to create the named canvas on first run if it doesn't exist yet (refused in read-only mode) | Optional |
| JUNE_READONLY | Set to 1 to hide and refuse all write tools (memory becomes read-only) | Optional |
| JUNE_FILES_ROOT | Opt-in directory agents may upload files from via june_ingest_file — unset means that tool doesn't exist | Optional |
| JUNE_DOCS_CANVAS | Canvas holding the agent's standing docs/skills/learnings (default 'agent_docs') | Optional |
| JUNE_DOCS_REFRESH | Set to 0 to disable the periodic standing-docs digest re-injected on tool results (default on) | Optional |
| JUNE_REFRESH_CALLS | Tool calls between digest injections (default 12) — lower it for small-context agents | Optional |
| JUNE_REFRESH_MINUTES | Wall-clock fallback between digest injections (default 10) | Optional |
| JUNE_DIGEST_CHARS | Standing-docs digest size cap in characters (default 2000) | Optional |
| JUNE_EXPORT_ROOT | Opt-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 | Optional |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Persistent memory MCP server. 25 tools, BM25+MMR+OOD retrieval, CFR-21 audit, knowledge graph.
A Model Context Protocol (MCP) server that provides semantic search access to the complete Stanford Encyclopedia of Philosophy through vector
Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.
Verifiable Memory for AI Agents — knowledge graph, FTS, Starknet proofs, local or cloud