mcp-reposkein

In the repo you want your agent to understand:

This downloads the indexer for your platform, installs git hooks + the navigation skill,builds the initial code graph, and prints an MCP config block. Then:
- Add the printed config to your agent(e.g. Claude Code's.mcp.json):

{ "mcpServers": { "reposkein": { "command": "reposkein-mcp", "env": { "REPOSKEIN_REPO_PATH": "/path/to/your/repo" } } } }

reposkein-mcp doctor . # ✓ binary ✓ indexed (N nodes) ✓ ready git add .reposkein/meta.json .reposkein/config.toml && git commit -m "add RepoSkein config"

npx skills add reposkein/reposkein --all

For complex setups — multi-repo workspaces, Neo4j backend, the local embedding server, or wiring up agents besides Claude Code (OpenCode, Cursor, Codex, Continue, Cline, …) — paste this into any MCP-capable agent and it'll walk you through:

Your agent (Claude Code / Cursor / …) ── guided by the reposkein skill │ MCP ▼ @reposkein/mcp semantic_find · get_context_profile · impact · get_temporal_context (TypeScript) read_cypher · write_semantic_summary · init_cpg_skeleton · reindex_file CLI: init · doctor · index · view │ reads ▼ .reposkein/ ← nodes.jsonl + edges.jsonl: derived, git-ignored, rebuilt on demand summaries/<xx>.jsonl: what your agents authored — commit this ▲ writes │ reposkein-indexer Tree-sitter parse → stable IDs → canonical JSONL (Rust) + git hooks that keep the local graph in step with your tree

Got nested repositories (a monorepo of indexed repos)? RepoSkein discovers them, links them withFEDERATES_TO, and stitchescross-repo call, import, and heritage edges(INHERITS/IMPLEMENTSto a base in a child repo) at load time. Passfederated: trueto traverse across repo boundaries. Federation edges are derived at load (never committed), so each repo stays independently deterministic.

Visualize the graph — the constellation viewer

reposkein-mcp view . # opens http://127.0.0.1:<port> in your browser

The map isdeterministic: a seeded force layout means the same graph always lays out the same way (cached in IndexedDB for instant reloads), and the layout is render-time only — it never touches the JSONL. Levels of detail map onto an astronomy metaphor —Repository → Directory → File → Symbolbecomegalaxy → constellation → solar-system → star— so you zoom or click to expand a cluster (a brief supernova animation) and click a star to inspect it. Federation galaxies and agent-written summaries render when present.

- Legible— per-edge-type colors + legend, importance-sized stars, adaptive labels, breadcrumb, per-language galaxy coloring, depth fog / bloom / nebula halos.
- Edges encode resolution— color = edge type (CALLS/IMPORTS/INHERITS/IMPLEMENTS/INSTANTIATES), opacity = confidence (exact/name_match/ambiguous), and flow particles show call direction.
- Analytical— one-click lenses (call graph / type hierarchy / imports / tests), an impact overlay (transitive callers + covering tests), a confidence-audit mode (see where the type-free resolver guesses), and a temporal-coupling overlay (git co-change).
- Explorable— ranked search-to-fly, N-hop neighborhood focus, source peek in the detail panel (a path-guarded read-only file slice + an "Open in editor"vscode://link), keyboard nav (/search,fframe-all, arrows to hop neighbors,Escback), a minimap, and PNG screenshot export.
- Guided tour— a cinematic, deterministically-derived flythrough (overview → largest modules → busiest hub → type hierarchy → entry point) with captions.

reposkein-mcp view --export ./site . # write a self-contained static site

--exportbakes the graph intograph-data.js(aswindow.__REPOSKEIN_GRAPH__) and emits aself-contained static site— it works fromfile://or any static host with no server, which is exactly how the live demo above is published. Handy for sharing a snapshot, embedding in docs, or a project landing page.

By defaultsemantic_findisdeterministic and lexical(BM25F — zero-infra, no keys). You can opt into ahybridtier (lexical + embedding cosine, fused via RRF) for fuzzier queries. It'sdefault-off, vectors are cached in.reposkein/local/embeddings/(gitignored, never committed), and itfalls back to lexicalautomatically on any error. Set env vars on the MCP server andpick one:

A) Voyage AI — cloud, easiest, best for code

REPOSKEIN_EMBED_PROVIDER=voyage VOYAGE_API_KEY=pa-... # optional: REPOSKEIN_EMBED_MODEL=voyage-code-3 # default — code-specialized

Sends document strings (qualified names, signatures, summaries) to Voyage's API. Use B or C if you can't egress code.

B) Ollama — local, off-the-shelf, no key

ollama pull nomic-embed-text # 768-dim (or mxbai-embed-large=1024, bge-m3=1024)

REPOSKEIN_EMBED_PROVIDER=http REPOSKEIN_EMBED_URL=http://127.0.0.1:11434/v1/embeddings REPOSKEIN_EMBED_MODEL=nomic-embed-text REPOSKEIN_EMBED_DIMS=768 # must match the model

C) Voyage's open model, self-hosted — offline + Voyage quality

voyage-4-nano(Apache-2.0) is a custom Qwen3-based model Ollama can't run, so RepoSkein ships a prebuilt server. The image ispublished to GHCR — public and multi-arch (amd64/arm64)— so there's nothing to build:

docker run -p 8080:8080 -v reposkein-hf:/root/.cache/huggingface \ ghcr.io/reposkein/reposkein-embed # auto-picks your architecture; first run downloads the model

REPOSKEIN_EMBED_PROVIDER=http REPOSKEIN_EMBED_URL=http://127.0.0.1:8080/v1/embeddings REPOSKEIN_EMBED_MODEL=voyage-4-nano REPOSKEIN_EMBED_DIMS=1024 # must equal the server's EMBED_DIMS

REPOSKEIN_EMBED_DIMSon the clientmust matchthe model's output dimension, or cosine scoring is skipped.

The zero-infra JSONL store is the default. Neo4j is an optional projection for very large graphs and raw Cypher at scale:

docker compose --profile neo4j up -d # from the repo root NEO4J_PASSWORD=reposkeintest reposkein-indexer load .