Lumen MCP server
Commit Oct 11, 2026Gives AI coding agents local semantic code search so they find relevant functions and types without reading entire files.
Also known as ory/lumen
- Stars
- 318
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 11, 2026
- License
- —
What is Lumen MCP?
Lumen gives AI coding agents local semantic code search so they find relevant functions and types without reading entire files.
Summary generated from the project's README
About Lumen MCP server
Providing AI coding agents with a local map of your codebase is what lumen does. Instead of forcing models like Claude to read entire files to find context, this MCP server enables semantic search to locate specific functions, types, and modules by their meaning. It is designed for developers using tools such as Claude Code, Cursor, Codex, or OpenCode who want to reduce token usage and speed up coding sessions.
The system operates entirely on your local machine using SQLite and your CPU, ensuring no data leaves your network. It requires a local embedding backend like Ollama or LM Studio to function. By using Merkle tree change detection, the server performs incremental updates, meaning it only re-indexes files that have actually changed, which makes it efficient for large projects.
Lumen supports 12 language families, including Python, Rust, TypeScript, and Go. It provides specific tools like semantic_search for retrieving code and maintenance skills such as doctor for health checks and reindex for manual updates. This approach helps maintain patch quality while significantly lowering the cost and time required for AI-driven bug fixes.
What you can do with it
- 1Reduce AI token costsA developer can use semantic search to find relevant code snippets instead of sending entire files to the model, lowering expenses.
- 2Speed up coding sessionsAn engineer can instruct an AI agent to find specific functions using semantic meaning to complete tasks faster.
- 3Maintain privacy with local embeddingsTeams working on sensitive codebases can perform semantic searches without uploading any data to the cloud.
- 4Efficiently index large projectsA developer can manage large repositories by only re-processing files that have been modified.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
LM_STUDIO_HOSTLUMEN_BACKENDLUMEN_EMBED_CTXLUMEN_EMBED_DIMSLUMEN_EMBED_MODEL
| Name | Description | |
|---|---|---|
| LM_STUDIO_HOST | — | |
| LUMEN_BACKEND | — | |
| LUMEN_EMBED_CTX | — | |
| LUMEN_EMBED_DIMS | — | |
| LUMEN_EMBED_MODEL | — |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableory/lumen is public and reachablegithub.com/ory/lumen ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-10-11github.com/ory/lumen ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub
Claude reads entire files to find what it needs. Lumen gives it a map.
Lumen is a 100% local semantic code search engine for AI coding agents. No API keys, no cloud, no external database, just open-source embedding models (Ollama or LM Studio), SQLite, and your CPU. A single static binary and your own local embedding server.
The payoff is measurable and reproducible: across 9 benchmark runs on 9 languages and real GitHub bug-fix tasks, Lumen cuts cost in every single language — up to 39%. Output tokens drop by up to 66%, sessions complete up to 53% faster, and patch quality is maintained in every task. All verified with a transparent, open-source benchmark framework that you can run yourself.
| With Lumen | Baseline (no Lumen) | |
|---|---|---|
| Cost (avg, bug-fix) | $0.29 (-26%) | $0.40 |
| Time (avg, bug-fix) | 125s (-28%) | 174s |
| Output tokens (avg) | 5,247 (-37%) | 8,323 |
| JavaScript (marked) | $0.32, 119s (-33%, -53%) | $0.48, 255s |
| Rust (toml) | $0.38, 204s (-39%, -34%) | $0.61, 310s |
| PHP (monolog) | $0.14, 34s (-27%, -34%) | $0.19, 52s |
| TypeScript (commander) | $0.14, 56s (-27%, -33%) | $0.19, 84s |
| Svelte (chat-ui) | $0.10, 56s (-26%, -31%) | $0.14, 80s |
| Patch quality | Maintained in all 9 tasks | — |
Table of contents
- Demo
- Quick start
- What you get
- How it works
- Benchmarks
- Supported languages
- Configuration
- Controlling what gets indexed
- Database location
- CLI Reference
- Troubleshooting
- Development
Demo
Claude Code asking about the
Prometheus codebase. Lumen's
semantic_search finds the relevant code without reading entire files.
Quick start
Prerequisites:
Platform support: Linux, macOS, and Windows. File locking for background indexing coordination uses
flock(2)on Unix andLockFileExon Windows (via gofrs/flock).
- Ollama installed and running, then pull the default
embedding model:
ollama pull ordis/jina-embeddings-v2-base-code - One of: Claude Code, Cursor, Codex, or OpenCode
Note: Installation differs by platform. Claude Code and Codex install from plugin marketplaces. OpenCode installs from npm. Cursor packaging is shipped in this repository and is ready for Cursor's plugin distribution workflow.
Install:
Claude Code
/plugin marketplace add ory/claude-plugins
/plugin install lumen@ory
Verify by starting a new Claude session and running /lumen:doctor.
Cursor
Lumen ships a native Cursor plugin bundle in this repository:
.cursor-plugin/plugin.json- plugin manifestmcp.json- locallumenMCP server wiringhooks/hooks-cursor.json- SessionStart hookskills/- shareddoctorandreindexskills
Use Cursor's plugin installation or distribution workflow with this bundle. Detailed packaging notes: .cursor-plugin/INSTALL.md
Verify by opening a new Cursor agent session and asking it to use the doctor
skill or the Lumen semantic_search tool.
Codex
Codex CLI 0.147.0 or newer installs Lumen as a native plugin:
codex plugin marketplace add ory/claude-plugins
codex plugin add lumen@ory
If the marketplace already exists, run codex plugin marketplace upgrade ory
before installing. Legacy manual-clone and broken-plugin repair instructions:
.codex/INSTALL.md.
Verify with:
codex mcp get lumen --json
OpenCode
Add @ory/lumen-opencode to the plugin array in your opencode.json:
{
"plugin": ["@ory/lumen-opencode"]
}
Detailed docs: .opencode/INSTALL.md
Verify with:
opencode mcp list
Updating
- Claude Code - update through Claude's plugin marketplace
- Cursor - refresh or reinstall the bundled plugin through Cursor after updating this repository or the published package
- Codex - upgrade the
orymarketplace, reinstalllumen@ory, and restart - OpenCode - update the version pin in
opencode.json(e.g.@ory/lumen-opencode@0.0.29) and restart OpenCode
On first Claude Code or Cursor session start, Lumen:
- Downloads the binary automatically from the latest GitHub release
- Indexes your project in the background using Merkle tree change detection
- Registers a
semantic_searchMCP tool that the host can use automatically
In Codex and OpenCode, the same binary download and index seeding happen on the
first semantic_search call. Codex stores the downloaded binary in the
plugin's writable data directory rather than the read-only package cache.
Two shared skills are also available: doctor (health check) and reindex
(forced re-indexing). Claude exposes them as /lumen:doctor and
/lumen:reindex; the other hosts discover the same shared skill content
through their native skill systems.
The same semantic_search, health_check, and index_status MCP tools plus
the shared doctor and reindex skills are exposed through the Codex,
Cursor, and OpenCode surfaces as well. The first semantic_search call seeds
or refreshes the index automatically.
What you get
- Semantic vector search — Claude finds relevant functions, types, and modules by meaning, not keyword matching
- Auto-indexing — indexes on session start, only re-processes changed files via Merkle tree diffing
- Incremental updates — re-indexes only what changed; large codebases re-index in seconds after the first run
- 12 language families — Go, Python, TypeScript, JavaScript, Svelte, Rust, Ruby, Java, PHP, C/C++, C#, Dart
- Git worktree support — worktrees share index data automatically; a new worktree seeds from a sibling's index and only re-indexes changed files, turning minutes of embedding into seconds
- Zero cloud — embeddings stay on your machine; no data leaves your network
- Ollama and LM Studio — works with either local embedding backend
How it works
Lumen sits between your codebase and Claude as an MCP server. When a session starts, it walks your project and builds a Merkle tree over file hashes: only changed files get re-chunked and re-embedded. Each file is split into semantic chunks (functions, types, methods) using Go's native AST or tree-sitter grammars for other languages. Chunks are embedded and stored in SQLite + sqlite-vec using cosine-distance KNN for retrieval.
Files → semantic chunks → vector embeddings → SQLite/sqlite-vec → KNN search
When Claude needs to understand code, it calls semantic_search instead of
reading entire files. The index is stored outside your repo
(~/.local/share/lumen/<hash>/index.db). Git worktrees from the same repository
use one collection for a compatible model, vector-storage, and chunking profile;
non-Git projects use private collections. Different profiles never collide.
Benchmarks
Lumen is evaluated using bench-swe: a SWE-bench-style harness that runs Claude on real GitHub bug-fix tasks and measures cost, time, output tokens, and patch quality — with and without Lumen. All results are reproducible: raw JSONL streams, patch diffs, and judge ratings are committed to this repository.
Key results — 9 runs across 9 languages, hard difficulty, real GitHub
issues (ordis/jina-embeddings-v2-base-code, Ollama):
| Language | Cost Reduction | Time Reduction | Output Token Reduction | Quality |
|---|---|---|---|---|
| Rust | -39% | -34% | -31% (18K → 12K) | Poor (both) |
| JavaScript | -33% | -53% | -66% (14K → 5K) | Perfect (both) |
| TypeScript | -27% | -33% | -64% (5K → 1.8K) | Good (both) |
| PHP | -27% | -34% | -59% (1.9K → 0.8K) | Good (both) |
| Ruby | -24% | -11% | -9% (6.1K → 5.6K) | Good (both) |
| Python | -20% | -29% | -36% (1.7K → 1.1K) | Perfect (both) |
| Go | -12% | -9% | -10% (11K → 10K) | Good (both) |
| C++ | -8% | -3% | +42% (feature task) | Good (both) |
| Svelte | -26% | -31% | -26% (4.0K → 3.0K) | Poor (both) |
Cost was reduced in every language tested. Quality was maintained in every task — zero regressions. JavaScript and TypeScript show the most dramatic efficiency gains: same quality fixes in half the time with two-thirds fewer tokens. Even on tasks too hard for either approach (Rust, Svelte), Lumen cuts the cost of failure by 26–39%.
See docs/BENCHMARKS.md for all 9 per-language deep dives, judge rationales, and reproduce instructions.
Supported languages
Supports 12 language families with semantic chunking (10 benchmarked):
| Language | Parser | Extensions | Benchmark status |
|---|---|---|---|
| Go | Native AST | .go |
Benchmarked: -12% cost, Good quality |
| Python | tree-sitter | .py |
Benchmarked: Perfect quality, -36% tokens |
| TypeScript / TSX | tree-sitter | .ts, .tsx |
Benchmarked: -64% tokens, -33% time |
| JavaScript / JSX | tree-sitter | .js, .jsx, .mjs |
Benchmarked: -66% tokens, -53% time |
| Dart | tree-sitter | .dart |
Benchmarked: -76% cost, -82% tokens, -79% time |
| Rust | tree-sitter | .rs |
Benchmarked: -39% cost, -34% time |
| Ruby | tree-sitter | .rb |
Benchmarked: -24% cost, -11% time |
| PHP | tree-sitter | .php |
Benchmarked: -59% tokens, -34% time |
| C / C++ | tree-sitter | .c, .h, .cpp, .cc, .cxx, .hpp |
Benchmarked: -8% cost (C++ feature task) |
| Svelte | tree-sitter | .svelte |
Benchmarked: -26% cost, -31% time |
| Java | tree-sitter | .java |
Supported |
| C# | tree-sitter | .cs |
Supported |
Go uses the native Go AST parser for the most precise chunks. All other languages use tree-sitter grammars. See docs/BENCHMARKS.md for all 10 per-language benchmark deep dives.
Configuration
All configuration is via environment variables:
| Variable | Default | Description |
|---|---|---|
LUMEN_EMBED_MODEL |
see note ¹ | Embedding model; use with LUMEN_EMBED_DIMS for unlisted models |
LUMEN_BACKEND |
ollama |
Embedding backend (ollama or lmstudio) |
OLLAMA_HOST |
http://localhost:11434 |
Ollama server URL |
LM_STUDIO_HOST |
http://localhost:1234 |
LM Studio server URL |
LUMEN_MAX_CHUNK_TOKENS |
512 |
Max tokens per chunk before splitting |
LUMEN_VECTOR_STORAGE |
int8 |
Vector precision (int8 or float32) |
LUMEN_EMBED_DIMS |
— | Override embedding dimensions (required for unlisted models) |
LUMEN_EMBED_CTX |
8192 (unlisted models) |
Override context window length |
¹ ordis/jina-embeddings-v2-base-code (Ollama),
nomic-ai/nomic-embed-code-GGUF (LM Studio)
Supported embedding models
Dimensions and context length are configured automatically per model:
| Model | Backend | Dims | Context | Recommended |
|---|---|---|---|---|
ordis/jina-embeddings-v2-base-code |
Ollama | 768 | 8192 | Best default — lowest cost, no over-retrieval |
qwen3-embedding:8b |
Ollama | 4096 | 40960 | Best quality — strongest dominance (7/9 wins), very slow indexing |
nomic-ai/nomic-embed-code-GGUF |
LM Studio | 3584 | 8192 | Usable — good quality, but TypeScript over-retrieval raises costs |
qwen3-embedding:4b |
Ollama | 2560 | 40960 | Not recommended — highest costs, severe TypeScript over-retrieval |
nomic-embed-text |
Ollama | 768 | 8192 | Untested |
qwen3-embedding:0.6b |
Ollama | 1024 | 32768 | Untested |
all-minilm |
Ollama | 384 | 512 | Untested |
Switching models creates a separate index automatically. The model name is part of the database path hash, so different models never collide.
Caveat: the DB path hash includes the model name but not the backend. If the same model name is configured on two backends (e.g. an Ollama and an LM Studio entry both named
foo), they share the same index — use distinct model names per backend to avoid collisions.
Selecting a server per invocation
lumen index and lumen search accept --model/-m and --backend/-b
to pick from a multi-server config.yaml. The selection filters the
configured servers to those matching both fields; failover still works
within the filtered subset.
# Index with the Ollama server matching this model name.
lumen index --model ordis/jina-embeddings-v2-base-code .
# Same model name hosted on LM Studio (present in YAML, not in the
# static registry) — accepted because the name is configured.
lumen index --model text-embedding-jina-embeddings-v2-base-code .
# Disambiguate when the same model is configured on two backends.
lumen index --model my-embed --backend lmstudio .
# Pick the first configured Ollama server regardless of model.
lumen search --backend ollama "…"
If --model is not configured in YAML but is a known registry model (and
--backend is unset), Lumen falls back to mutating the default server's
model — preserving lumen index --model all-minilm . for users with no YAML.
Using a custom or unlisted model
If your model is not in the registry above, set LUMEN_EMBED_DIMS to bypass the
registry check. LUMEN_EMBED_CTX is optional and defaults to 8192.
Both variables can also override values for known models — useful when running a model variant with a longer context window or different output dimensions.
LUMEN_BACKEND=lmstudio
LM_STUDIO_HOST=http://localhost:8801
LUMEN_EMBED_MODEL=mlx-community/Qwen3-Embedding-8B-4bit-DWQ
LUMEN_EMBED_DIMS=4096
LUMEN_EMBED_CTX=40960 # optional, defaults to 8192
Controlling what gets indexed
Lumen filters files through six layers: built-in directory and lock file skips →
.gitignore → .lumenignore → .gitattributes (linguist-generated) →
supported file extension. Only files that pass all layers are indexed.
.lumenignore uses .gitignore syntax. Place it in your project root (or
any subdirectory) to exclude files that aren't in .gitignore but are noise for
code search — generated protobuf files, test snapshots, vendored data, etc.
Directories: .git, node_modules, vendor, dist, .cache, .venv,
venv, __pycache__, target, .gradle, _build, deps, .idea,
.vscode, .next, .nuxt, .build, .output, bower_components, .bundle,
.tox, .eggs, testdata, .hg, .svn
Lock files: package-lock.json, yarn.lock, pnpm-lock.yaml, bun.lock,
bun.lockb, go.sum, composer.lock, poetry.lock, Pipfile.lock,
Gemfile.lock, Cargo.lock, pubspec.lock, mix.lock, flake.lock,
packages.lock.json
Database location
Index databases are stored outside your project:
~/.local/share/lumen/<hash>/index.db
Where <hash> identifies the Git common directory (or the absolute path for a
non-Git project), indexed scope, embedding model and dimensions, vector
precision, chunking profile, and index version. Worktrees in one repository
share content-addressed file revisions and vectors while retaining independent
project memberships. Vectors use int8 storage by default; set
LUMEN_VECTOR_STORAGE=float32 to opt out. No files are added to your repo.
You can safely delete the entire lumen directory to clear all indexes, or let
Lumen reclaim the space for you:
lumen clean # remove indexes unused for 30 days or whose project is gone
lumen clean --days 7 # tighten the cutoff to a week
lumen clean --days 0 # remove every eligible index except actively locked indexes
An index counts as used every time Lumen opens it (search, indexing, status, or session start), so indexes for projects you still work on are never removed. Indexes with an indexer currently running are always kept.
Git worktrees are detected automatically. A new worktree attaches unchanged path-and-content revisions directly from the repository collection and embeds only missing chunk inputs. Removing an old worktree drops its memberships; shared revisions and vectors remain until their final reference disappears. Legacy per-worktree indexes migrate lazily, reusing unchanged float32 vectors without contacting the embedding backend.
For the complete storage key, sharing rules, status metrics, migration process, and cleanup lifecycle, see Index storage and lifecycle.
CLI Reference
Download the binary from the GitHub releases page or let the plugin install it automatically.
lumen help
Troubleshooting
Ollama not running / "connection refused"
Start Ollama and verify the model is pulled:
ollama serve
ollama pull ordis/jina-embeddings-v2-base-code
Run /lumen:doctor inside Claude Code to confirm connectivity.
In Cursor, Codex, or OpenCode, use the shared doctor skill or call
health_check and index_status directly.
Stale index after large refactor
Run /lumen:reindex inside Claude Code to force a full re-index, or:
lumen index --force .
In Codex, use the bundled reindex skill to refresh the index through the MCP
server, or run the same CLI commands for a clean rebuild. The same shared
reindex skill is available in Cursor and OpenCode as well.
LM Studio: embedding model appears under LLMs instead of Embeddings
LM Studio classifies embedding models by matching the GGUF arch field against
a hardcoded allowlist (bert, nomic-bert). Models built on other
architectures — including Qwen2-based models like nomic-embed-code — are
misclassified as LLMs. This affects lms ls output and the /v1/embeddings
REST endpoint.
Fix (GGUF, v0.3.16+): Open LM Studio → My Models, click the gear icon next to the model, set Override Domain Type → Text Embedding.
macOS / Apple Silicon: MLX format models are significantly faster on Apple Silicon. However, LM Studio removed the domain type override for MLX in v0.3.30+, so MLX embedding models cannot be reclassified. Use the GGUF variant to retain the override option, or switch to Ollama (
ordis/jina-embeddings-v2-base-codeorqwen3-embedding:8b).
Switching embedding models
Set LUMEN_EMBED_MODEL to a model from the supported table above. Each model
gets its own database; the old index is not deleted automatically.
Changing LUMEN_VECTOR_STORAGE, LUMEN_EMBED_DIMS, or LUMEN_MAX_CHUNK_TOKENS
also selects a separate collection. Run lumen clean after the old profile is
no longer in use if you want to reclaim its disk space.
Understanding index size and deduplication
Call index_status for the project. It reports project-local file and chunk
counts alongside collection-wide unique vectors, shared references,
deduplication ratio, vector precision, database size, and currently reclaimable
SQLite pages. See
Index storage and lifecycle for
definitions and examples.
Slow first indexing
The first run embeds every file. Subsequent runs only process changed files (typically a few seconds). For large projects (100k+ lines), first indexing can take several minutes — this is a one-time cost.
Development
git clone https://github.com/ory/lumen.git
cd lumen
# Build locally (CGO required for sqlite-vec)
make build-local
# Run tests
make test
# Run linter
make lint
# Load as a Claude Code plugin from source
make plugin-dev
See CLAUDE.md for architecture details, design decisions, and contribution guidelines, and AGENTS.md for repo-specific agent instructions.
Lumen MCP questions
Does Lumen send my code to the cloud?
No. Lumen runs fully locally with open-source embedding models, SQLite, and your own CPU, so embeddings never leave your machine.
How much does Lumen reduce token costs?
Across 9 benchmark runs on 9 languages Lumen cut cost in every language, by up to 39%, while maintaining patch quality.
Which embedding backends does Lumen support?
It works with either Ollama or LM Studio as the local embedding backend.
Which languages can Lumen index?
Lumen supports 12 language families including Go, Python, TypeScript, JavaScript, Rust, Ruby, Java, PHP, C/C++, C#, Dart, and Svelte.
How does Lumen avoid re-indexing unchanged files?
It builds a Merkle tree over file hashes and only re-chunks and re-embeds files that changed.