Junê (june-mcp)
Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.
Ads
Overview
Give your agent a memory. june-mcp is the official MCP server for Junê — it connects any MCP host (Claude Desktop, Claude Code, and friends) to a June knowledge graph, so your agent can ask, search, and remember against a shared, cited, tenant-isolated memory. This package is a thin, zero-logic connector: all retrieval, graph assembly, and answering happen on the June endpoint you point it at. No engine code lives here — which is why it's small enough to read in one sitting. june-mcp speaks to any June service. Three ways to have one:
Installation
pip install june-mcp # just the connector (or: pipx install june-mcp)
Configuration
{
"mcpServers": {
"june": {
"command": "june-mcp",
"env": {
"JUNE_BASE_URL": "http://localhost:8000",
"JUNE_API_KEY": "your-key",
"JUNE_CANVAS": "work",
"JUNE_LLM_KEY": "your-llm-provider-key"
}
}Capabilities
- Ask cited questions
have your agent call `june_answer` to get grounded, cited answers from your knowledge graph, abstaining when uncertain.
- Search with evidence
use `june_search` to retrieve ranked, multi-hop evidence for any query across your connected memory.
- Remember new facts
write notes or facts into the graph via `june_remember`, making them immediately retrievable and citable.
- List everything
run `june_enumerate` to get recall-complete results for "list ALL X" queries, not just top-k matches.
- Ingest local files
upload PDFs, docs, images, or audio from an approved folder with `june_ingest_file` (when `JUNE_FILES_ROOT` is set).
- Explore graph structure
inspect the neighborhood around a node with `june_neighborhood` or export a bounded `june_subgraph`.
Related MCP servers
Memory MCP Server
OfficialPersist assistant memory as a lightweight knowledge graph across sessions.
OpenLore
OfficialAgent-native knowledge server. Serves docs to AI agents over SSH and MCP with identity-scoped views, governed writing, and structured metadata. Single binary, zero config.
gingugu/gingugu
Persistent memory for AI coding assistants. Local SQLite, no cloud. 16 MCP tools: store, recall, search, relate, consolidate, export, and credential vault (OS keychain). Typed memories with confidence lifecycle (verified/inferred/stale/deprecated), namespaces, knowledge graph, and hybrid BM25 + semantic search via fastembed ONNX. Works with Cursor, Windsurf, Claude, and any MCP client. `pip install gingugu`
GistPad-MCP
Use GitHub Gists to manage and access your personal knowledge, daily notes, and reusable prompts. This acts as a companion to https://gistpad.dev and the [GistPad VS Code extension](https://aka.ms/gistpad).