Junê (june-mcp)

- Ask cited questions— have your agent calljune_answerto get grounded, cited answers from your knowledge graph, abstaining when uncertain.
- Search with evidence— usejune_searchto retrieve ranked, multi-hop evidence for any query across your connected memory.
- Remember new facts— write notes or facts into the graph viajune_remember, making them immediately retrievable and citable.
- List everything— runjune_enumerateto 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 withjune_ingest_file(whenJUNE_FILES_ROOTis set).
- Explore graph structure— inspect the neighborhood around a node withjune_neighborhoodor export a boundedjune_subgraph.

Give your agent a memory.june-mcpis the officialMCPserver forJunê— it connects any MCP host (Claude Desktop, Claude Code, and friends) to a June knowledge graph, so your agent canask,search, andrememberagainst a shared, cited, tenant-isolated memory.

Claude Desktop / Claude Code ──stdio──▶ june-mcp ──HTTPS──▶ your June endpoint (graph · retrieval · answers)

pip install june-mcp # just the connector (or: pipx install june-mcp) pip install june-ai # umbrella: june-mcp + june-bench (the benchmark suite) pip install "june-bench[mcp]" # the bench, with the connector as an extra

june-mcpspeaks to any June service. Three ways to have one:
- Junê desktop app (local-first).Run theJunê appand connect to its local engine — your files, graph, and keys stay on your machine.
- Your own June service.Pro/Team customers running thejune-localengine package pointJUNE_BASE_URLat their own server.
- Hosted (Team).Point at your hosted June workspace endpoint with the API key from your console.

JUNE_BASE_URL=http://localhost:8000 JUNE_API_KEY=... JUNE_CANVAS=work june-mcp --doctor

{ "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" } } } }

claude mcp add june -e JUNE_BASE_URL=http://localhost:8000 \ -e JUNE_API_KEY=your-key -e JUNE_CANVAS=work \ -e JUNE_LLM_KEY=your-llm-provider-key -- june-mcp

june-mcp: connected http://localhost:8000 canvas name "work" → 11d2… [june-pro]

The tag is read from the service's own/v1/whoami(the same entitlement state that gates Pro routes server-side), so it can't disagree with what you actually get — and it's display-only: entitlements are enforced on the service no matter what any client prints. Older services without/v1/whoamisimply show no tag.

The tool surface exposesno canvas/workspace parameter— the workspace is bound server-side from your connection's context, fail-closed. A cross-tenant read isn't a permission check that could fail open; it'sunrepresentablefrom the client.JUNE_READONLY=1adds a second fence for read-only deployments. Your BYO LLM key rides each answer request as a header and is never persisted or logged by the service.

Every upstream failure maps to a typed, redacted error payload (built from exception type + HTTP status only — never from response bodies), so the server survives anything the endpoint throws and your agent sees a clean, actionable message.

MIT. The Junê engine itself is a separate, closed-source product — this connector is the open part, by design.

Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.

Persistent memory and semantic search for AI coding assistants across sessions

Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.

Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.

Your portable AI memory vault — memories, skills & configs, shared across every AI tool.

Local Work Model for AI agents that learns from real outcomes.

Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.

Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.

Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.

MCP-native memory layer for Claude Code, Cursor, Cline, Continue, and 16 other AI tools. Hybrid search (BM25 + pgvector + graph), self-hosted on Supabase + Vercel, 100% MIT, no paywall.