How is the index kept in sync with the binary?

The database is pinned to the binary version; upgrading the binary triggers a re-fetch of the matching index.

What platforms does deadzone support?

Deadzone supports Linux and macOS natively; Windows is not supported due to upstream library limitations but can run under WSL.

How do I integrate deadzone with an MCP client?

Configure the client to launch deadzone as a stdio MCP server using the 'deadzone server' command or the provided Docker container.

What environment variables affect deadzone?

Setting DEADZONE_DB_OFFLINE=1 disables guessing and enforces offline mode.

Deadzone

Local vector-based semantic search over library documentation with a single Go binary and zero network usage after initial setup.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.

Manual Client & Custom JSON ConfigExpand JSON ▾

No confirmed setup config for this listing yet. We only publish a config block when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for laradji/deadzone, and we’d rather show nothing than a guess you’d paste into your client. Follow the project’s own setup instructions for the current steps.

Overview

This server provides local-first semantic search over programming library documentation using a vector index embedded in a single Go binary. It supports natural language queries and returns relevant documentation snippets without requiring internet access after the initial database fetch. The index is version-pinned to the binary, ensuring consistency and offline availability. It communicates via MCP over stdio and runs on Linux and macOS.

Use cases

Search library names and versions by natural language queries

Retrieve relevant documentation snippets for specific libraries

Integrate offline semantic doc search into AI tools

Run a local MCP server for doc search without cloud dependencies

Key features

Single binary with no external dependencies

Vector search using nomic-embed-text-v1.5 embeddings

Local Turso file database pinned to binary version

MCP protocol over stdio for easy integration

Prebuilt and SHA256-verified index auto-fetched on first run

Runs offline with zero telemetry and no API keys

Capabilities & Tool Schemas

Inspect callable tools, capabilities, and parameters exposed to AI agents by Deadzone.

Extracted Tool Capabilities

Single binary with no external dependencies

Vector search using nomic-embed-text-v1.5 embeddings

Local Turso file database pinned to binary version

MCP protocol over stdio for easy integration

Prebuilt and SHA256-verified index auto-fetched on first run

Runs offline with zero telemetry and no API keys

Documentation Overview

Code

         _                _
      __| | ___  __ _  __| |_______  _ __   ___
     / _` |/ _ \/ _` |/ _` |_  / _ \| '_ \ / _ \
    | (_| |  __/ (_| | (_| |/ / (_) | | | |  __/
     \__,_|\___|\__,_|\__,_/___\___/|_| |_|\___|

    > semantic doc search. local file. no cloud. no key.
    > you ask in english. it answers in snippets.

Status. Vector search wired end-to-end. MCP over stdio. One binary, Linux + macOS, zero telemetry. See releases for the latest tag and the roadmap for in-flight work. The scraper is still the messy half — #64 is honest about it.

The pitch, in one paragraph

Your AI client says "how do I register a tool?". The doc says AddTool. A grep-based index shrugs; a vector index doesn't. Deadzone is the vector index — nomic-embed-text-v1.5 over Turso's native cosine distance, wrapped in a Go binary that speaks MCP over stdio and keeps every byte on your laptop. It is, roughly, Context7 with the internet turned off.

Rules of the deadzone

One binary. deadzone. Subcommands for everything. No pip install, no npm i, no docker compose up.
The index never leaves. Local Turso file. No account. No API key. No egress on the hot path.
Natural language first. Embeddings over cosine. FTS5 is not invited.
The binary is the version. The DB is pinned to the binary. Upgrade the binary, the DB follows; don't, and it won't.
Fail loudly or not at all. DEADZONE_DB_OFFLINE=1 refuses to guess. Verification failures in the scraper drop the doc, not the run.

Install (pick one; they all converge on the same binary)

# macOS Apple Silicon — the one-liner
brew install laradji/deadzone/deadzone

# Linux — resolve the latest tag once, then pick a flavor
VERSION=$(curl -fsSL https://api.github.com/repos/laradji/deadzone/releases/latest | grep '"tag_name"' | cut -d'"' -f4)
ARCH=amd64    # or arm64

# self-mounting AppImage
curl -L -O "https://github.com/laradji/deadzone/releases/download/${VERSION}/deadzone_${VERSION}_linux_${ARCH}.AppImage"
chmod +x "deadzone_${VERSION}_linux_${ARCH}.AppImage"
mv "deadzone_${VERSION}_linux_${ARCH}.AppImage" deadzone

# or plain tarball (no FUSE needed)
curl -L "https://github.com/laradji/deadzone/releases/download/${VERSION}/deadzone_${VERSION}_linux_${ARCH}.tar.gz" \
  | tar xz --strip-components=1

Both flavors land a deadzone executable in your current directory, so the ./deadzone server snippet below works as-is.

# Container — multi-arch (linux/amd64 + linux/arm64), ships with the DB baked, runs offline by default
docker pull ghcr.io/laradji/deadzone:latest
docker run --rm -i ghcr.io/laradji/deadzone:latest server

The image bakes the binary, libonnxruntime, deadzone.db, and the nomic-embed-text-v1.5 ONNX weights (~230 MB total), and runs as a non-root user out of distroless (no shell, no package manager). DEADZONE_DB_OFFLINE=1 is set in the image so first launch is instant — no download, no volume mount, no --network access required. To refresh the index, pull a newer tag.

Windows is blocked upstream — no libtokenizers.a. Use WSL.

Verify checksums (optional but cheap):

Terminal

curl -L -O "https://github.com/laradji/deadzone/releases/download/${VERSION}/deadzone_${VERSION}_checksums.txt"
sha256sum  --ignore-missing -c "deadzone_${VERSION}_checksums.txt"   # Linux
shasum -a 256 --ignore-missing -c "deadzone_${VERSION}_checksums.txt"   # macOS

AppImage needs FUSE v2. Most desktops ship it; minimal servers don't. If you get dlopen(): libfuse.so.2, either apt-get install libfuse2 (or dnf install fuse-libs) or pass --appimage-extract-and-run to bypass FUSE entirely.

Run

./deadzone server

That's the quick-start. On first launch it fetches deadzone.db matched to this binary's version, SHA256-verifies, caches it under the platform data dir, and serves. Second launch onwards: zero network. Upgrade the binary and the DB re-fetches on next launch; don't, and the cache is served forever.

MCP client wire-up — native binary (Brew tap, tarball, or AppImage):

config.json

{
  "mcpServers": {
    "deadzone": {
      "type": "stdio",
      "command": "/path/to/deadzone",
      "args": ["server"]
    }
  }
}

MCP client wire-up — container (multi-arch on ghcr.io). The image ships with deadzone.db baked, so no volume mount is needed and every container start is offline-instant:

config.json

{
  "mcpServers": {
    "deadzone": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "--rm", "-i", "ghcr.io/laradji/deadzone:latest", "server"]
    }
  }
}

Then, from the client:

Code

search_libraries("terraform aws")                 → ranked (lib_id, version) pairs
search_docs("creating an s3 bucket", lib_id=...)  → snippets, token-budgeted

The two tools

Code

┌─────────────────────────────────────────────────────────────────────┐
│  search_libraries(name, limit?) → []LibraryHit                      │
│  ─────────────────────────────────────────────                      │
│  free text   ──►  vector match against the `libs` table             │
│                   ──► [{lib_id, version, doc_count, match_score}]   │
├─────────────────────────────────────────────────────────────────────┤
│  search_docs(query, lib_id?, version?, tokens?) → []Snippet         │
│  ──────────────────────────────────────────────────                 │
│  natural  ──► 768-dim embed ──► cosine over docs                    │
│  language                      ──► token-budgeted snippets back     │
└─────────────────────────────────────────────────────────────────────┘

Arg	Shape	Notes
`query`	string	Matched semantically. Don't write keywords; write what you want.
`lib_id`	`/org/project`	Optional filter. Grab one from `search_libraries`.
`version`	`"1.14"` or similar	Optional pin; requires `lib_id`. `version` alone is rejected.
`tokens`	int	Response budget. Default `5000`, min `1000`, ≈ 4 chars/token.
`limit`	int	On `search_libraries` — max results. Default `10`, max `50`.
`name`	string	Free text on `search_libraries`. Empty returns the most-indexed libs.

Under the hood

Code

  deadzone server
       │
       ▼
  ┌──────────────┐   stdio JSON-RPC       ┌───────────────┐
  │  MCP client  │ ─────────────────────► │   handler     │
  └──────────────┘                        └──────┬────────┘
                                                 │
                              ┌──────────────────┴──────────────────┐
                              ▼                                     ▼
                     ┌────────────────┐                   ┌──────────────────┐
                     │   embedder     │                   │   Turso (local)  │
                     │  hugot + ORT   │                   │  F32_BLOB(768)   │
                     │  nomic v1.5    │                   │  vector_distance │
                     └────────┬───────┘                   └──────────────────┘
                              │  768-dim                             ▲
                              └──────────────  query vector  ────────┘

Layer	Choice
Language	Go 1.26.2, pinned via `mise`
Storage	Turso local file — native `F32_BLOB(N)` + `vector_distance_cos`
Driver	`tursogo` — CGO-free via `purego`
Embedder	`hugot` → `nomic-ai/nomic-embed-text-v1.5`, 768-dim, 8192-token ctx (int8 quantized)
Runtime	ONNX Runtime — binary CGO-linked at build time; `libonnxruntime` auto-fetched + SHA256-verified on first launch
Protocol	`modelcontextprotocol/go-sdk` over stdio

The binary itself is CGO-linked (hugot ORT backend + static libtokenizers.a). At runtime the only native surface is libonnxruntime, loaded via dlopen after a SHA256-verified auto-download. Everything else — Go stdlib, tursogo, the model weights — is either statically linked or fetched on first launch against a pinned hash. No system installs. No sudo. If a download drifts from its pinned hash, the run aborts; there is no fallback to an unverified fetch.

Escape hatches for air-gapped boxes:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

4mo ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Deadzone

No, after the initial index download on first launch, deadzone operates fully offline with zero network egress.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/laradji-deadzone?style=directory)](https://allmcps.com/mcp/laradji-deadzone)

HTML Embed

<a href="https://allmcps.com/mcp/laradji-deadzone"><img src="https://allmcps.com/api/badge/laradji-deadzone?style=directory" alt="Deadzone on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

41Quality signal: Fair · 41/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools19/30

Adoption & activity2/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Deadzone →Install in Claude Desktop Install in Cursor Install in VS Code

Deadzone

Local vector-based semantic search over library documentation with a single Go binary and zero network usage after initial setup.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Manual Client & Custom JSON ConfigExpand JSON ▾

Overview

Use cases

Search library names and versions by natural language queries

Retrieve relevant documentation snippets for specific libraries

Integrate offline semantic doc search into AI tools

Run a local MCP server for doc search without cloud dependencies

Key features

Single binary with no external dependencies

Vector search using nomic-embed-text-v1.5 embeddings

Local Turso file database pinned to binary version

MCP protocol over stdio for easy integration

Prebuilt and SHA256-verified index auto-fetched on first run

Runs offline with zero telemetry and no API keys

Capabilities & Tool Schemas

Inspect callable tools, capabilities, and parameters exposed to AI agents by Deadzone.

Extracted Tool Capabilities

Single binary with no external dependencies

Vector search using nomic-embed-text-v1.5 embeddings

Local Turso file database pinned to binary version

MCP protocol over stdio for easy integration

Prebuilt and SHA256-verified index auto-fetched on first run

Runs offline with zero telemetry and no API keys

Documentation Overview

Code

         _                _
      __| | ___  __ _  __| |_______  _ __   ___
     / _` |/ _ \/ _` |/ _` |_  / _ \| '_ \ / _ \
    | (_| |  __/ (_| | (_| |/ / (_) | | | |  __/
     \__,_|\___|\__,_|\__,_/___\___/|_| |_|\___|

    > semantic doc search. local file. no cloud. no key.
    > you ask in english. it answers in snippets.

Status. Vector search wired end-to-end. MCP over stdio. One binary, Linux + macOS, zero telemetry. See releases for the latest tag and the roadmap for in-flight work. The scraper is still the messy half — #64 is honest about it.

The pitch, in one paragraph

Rules of the deadzone

One binary. deadzone. Subcommands for everything. No pip install, no npm i, no docker compose up.
The index never leaves. Local Turso file. No account. No API key. No egress on the hot path.
Natural language first. Embeddings over cosine. FTS5 is not invited.
The binary is the version. The DB is pinned to the binary. Upgrade the binary, the DB follows; don't, and it won't.
Fail loudly or not at all. DEADZONE_DB_OFFLINE=1 refuses to guess. Verification failures in the scraper drop the doc, not the run.

Install (pick one; they all converge on the same binary)

# macOS Apple Silicon — the one-liner
brew install laradji/deadzone/deadzone

# Linux — resolve the latest tag once, then pick a flavor
VERSION=$(curl -fsSL https://api.github.com/repos/laradji/deadzone/releases/latest | grep '"tag_name"' | cut -d'"' -f4)
ARCH=amd64    # or arm64

# self-mounting AppImage
curl -L -O "https://github.com/laradji/deadzone/releases/download/${VERSION}/deadzone_${VERSION}_linux_${ARCH}.AppImage"
chmod +x "deadzone_${VERSION}_linux_${ARCH}.AppImage"
mv "deadzone_${VERSION}_linux_${ARCH}.AppImage" deadzone

# or plain tarball (no FUSE needed)
curl -L "https://github.com/laradji/deadzone/releases/download/${VERSION}/deadzone_${VERSION}_linux_${ARCH}.tar.gz" \
  | tar xz --strip-components=1

Both flavors land a deadzone executable in your current directory, so the ./deadzone server snippet below works as-is.

# Container — multi-arch (linux/amd64 + linux/arm64), ships with the DB baked, runs offline by default
docker pull ghcr.io/laradji/deadzone:latest
docker run --rm -i ghcr.io/laradji/deadzone:latest server

Windows is blocked upstream — no libtokenizers.a. Use WSL.

Verify checksums (optional but cheap):

Terminal

curl -L -O "https://github.com/laradji/deadzone/releases/download/${VERSION}/deadzone_${VERSION}_checksums.txt"
sha256sum  --ignore-missing -c "deadzone_${VERSION}_checksums.txt"   # Linux
shasum -a 256 --ignore-missing -c "deadzone_${VERSION}_checksums.txt"   # macOS

Run

./deadzone server

MCP client wire-up — native binary (Brew tap, tarball, or AppImage):

config.json

{
  "mcpServers": {
    "deadzone": {
      "type": "stdio",
      "command": "/path/to/deadzone",
      "args": ["server"]
    }
  }
}

MCP client wire-up — container (multi-arch on ghcr.io). The image ships with deadzone.db baked, so no volume mount is needed and every container start is offline-instant:

config.json

{
  "mcpServers": {
    "deadzone": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "--rm", "-i", "ghcr.io/laradji/deadzone:latest", "server"]
    }
  }
}

Then, from the client:

Code

search_libraries("terraform aws")                 → ranked (lib_id, version) pairs
search_docs("creating an s3 bucket", lib_id=...)  → snippets, token-budgeted

The two tools

Code

┌─────────────────────────────────────────────────────────────────────┐
│  search_libraries(name, limit?) → []LibraryHit                      │
│  ─────────────────────────────────────────────                      │
│  free text   ──►  vector match against the `libs` table             │
│                   ──► [{lib_id, version, doc_count, match_score}]   │
├─────────────────────────────────────────────────────────────────────┤
│  search_docs(query, lib_id?, version?, tokens?) → []Snippet         │
│  ──────────────────────────────────────────────────                 │
│  natural  ──► 768-dim embed ──► cosine over docs                    │
│  language                      ──► token-budgeted snippets back     │
└─────────────────────────────────────────────────────────────────────┘

Arg	Shape	Notes
`query`	string	Matched semantically. Don't write keywords; write what you want.
`lib_id`	`/org/project`	Optional filter. Grab one from `search_libraries`.
`version`	`"1.14"` or similar	Optional pin; requires `lib_id`. `version` alone is rejected.
`tokens`	int	Response budget. Default `5000`, min `1000`, ≈ 4 chars/token.
`limit`	int	On `search_libraries` — max results. Default `10`, max `50`.
`name`	string	Free text on `search_libraries`. Empty returns the most-indexed libs.

Under the hood

Code

  deadzone server
       │
       ▼
  ┌──────────────┐   stdio JSON-RPC       ┌───────────────┐
  │  MCP client  │ ─────────────────────► │   handler     │
  └──────────────┘                        └──────┬────────┘
                                                 │
                              ┌──────────────────┴──────────────────┐
                              ▼                                     ▼
                     ┌────────────────┐                   ┌──────────────────┐
                     │   embedder     │                   │   Turso (local)  │
                     │  hugot + ORT   │                   │  F32_BLOB(768)   │
                     │  nomic v1.5    │                   │  vector_distance │
                     └────────┬───────┘                   └──────────────────┘
                              │  768-dim                             ▲
                              └──────────────  query vector  ────────┘

Layer	Choice
Language	Go 1.26.2, pinned via `mise`
Storage	Turso local file — native `F32_BLOB(N)` + `vector_distance_cos`
Driver	`tursogo` — CGO-free via `purego`
Embedder	`hugot` → `nomic-ai/nomic-embed-text-v1.5`, 768-dim, 8192-token ctx (int8 quantized)
Runtime	ONNX Runtime — binary CGO-linked at build time; `libonnxruntime` auto-fetched + SHA256-verified on first launch
Protocol	`modelcontextprotocol/go-sdk` over stdio

Escape hatches for air-gapped boxes:

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

4mo ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Deadzone

No, after the initial index download on first launch, deadzone operates fully offline with zero network egress.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/laradji-deadzone?style=directory)](https://allmcps.com/mcp/laradji-deadzone)

HTML Embed

<a href="https://allmcps.com/mcp/laradji-deadzone"><img src="https://allmcps.com/api/badge/laradji-deadzone?style=directory" alt="Deadzone on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

41Quality signal: Fair · 41/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools19/30

Adoption & activity2/15

Community engagement0/10

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Deadzone →Install in Claude Desktop Install in Cursor Install in VS Code