Openzim Mcp

io.github.cameronryePublished by GitHub account cameronryev3.4.0Updated Oct 25, 2026

Offline MCP access to ZIM knowledge archives — Wikipedia, Wiktionary, Stack Exchange, Kiwix.

Overview

AI-generated overview

A local MCP server that gives an assistant structured, offline access to ZIM knowledge archives such as Wikipedia, Wiktionary and Stack Exchange.

What you can do
Search and query archives in natural language or with full-text search and suggestions, including across multiple archives at once, with paginated results and caching for large files. Read entries and sections, browse by namespace, and follow tables of contents and related articles. Inspect archive metadata, index capabilities and integrity, and extract link graphs, including inbound links to a page. Serve individual archive entries as MCP resources with change notifications, plus research, summarize and explore prompts in advanced mode.
When to use it
Use it when an assistant should answer from offline or air-gapped knowledge archives, such as a downloaded Wikipedia or Stack Exchange dump, instead of the live web. Simple mode suits small models; advanced mode suits larger models and clients that need fine-grained control over pagination, namespaces and link graphs.
Requirements
Runs locally over stdio, typically via uvx or pip (Python), or as a Docker image. Needs at least one ZIM archive file and a directory path to it; the server does nothing without an archive. No account or API key is required. Optional HTTP transport needs bearer-token and host settings.
Before you install
The server reads archives from a local directory, so point it only at folders you intend to expose. Optional HTTP mode with bearer auth and CORS should be configured carefully if reachable beyond localhost. Inbound link discovery needs a sidecar database built next to the archive, and sidecars from older versions must be rebuilt. The server is read-only over archives; it does not modify them.

Installation

In SourceWeft

  1. Open Openzim Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[OpenZIM MCP Logo]

OpenZIM MCP Server

Transform static ZIM archives into dynamic knowledge engines for AI models

[CI] [codecov] [CodeQL] [Security Rating]

[PyPI version] [PyPI - Python Version] [PyPI - Downloads] [License: MIT]

[OpenZIM MCP server quality badge]


✨ Highlights. A lean 8-tool advanced surface (zim_query, zim_search, zim_get, zim_get_section, zim_browse, zim_metadata, zim_links, zim_health) with a schema small enough for small-model dispatch — or one-tool Simple mode for natural-language queries. Archive-type presets auto-tune retrieval per source (Wikipedia, Stack Exchange, …), inbound link discovery answers "what links here," and native libzim introspection validates and inspects any archive. Available on Smithery and the official MCP Registry. Release notes → Docs →

OpenZIM MCP is a modern, secure, high-performance Model Context Protocol server that gives AI models structured, offline access to ZIM format knowledge archives — Wikipedia, Wiktionary, Stack Exchange, and the rest of the Kiwix Library.

Built for research assistants, knowledge chatbots, and content-analysis systems that need intelligent access to vast knowledge repositories — not just a raw text dump. Smart navigation by namespace (articles, metadata, media), structure-aware retrieval (sections, tables of contents, related articles), full-text search with suggestions and multi-archive search, and link-graph extraction to map content relationships. Cached, paginated operations keep things responsive across massive archives; comprehensive input validation and path-traversal protection keep things safe.

Streamable HTTP transport, per-entry MCP resources with live change notifications, and dual Simple / Advanced modes are all built in.

Install

bash
# uv (recommended — isolated CLI tool)uv tool install openzim-mcp
# pippip install openzim-mcp
# Docker (multi-arch image, ghcr.io) — runs as a local stdio MCP serverdocker pull ghcr.io/cameronrye/openzim-mcpdocker run -i --rm -v ~/zim-files:/data ghcr.io/cameronrye/openzim-mcp

The container defaults to stdio transport, so docker run -i speaks MCP over stdin/stdout — wire it into an MCP client the same way as the binary (see Quick start). For the long-running HTTP service (bearer auth, CORS, health endpoints), opt in at runtime with -e OPENZIM_MCP_TRANSPORT=http -e OPENZIM_MCP_HOST=0.0.0.0 -e OPENZIM_MCP_AUTH_TOKEN=… -p 8000:8000; see HTTP & Docker deployment.

Verify the install:

bash
openzim-mcp --help

Get your first ZIM archive

The server does nothing without an archive to read. Grab a real one — a 13.6 MB extract of English Wikipedia on climate change, from the openZIM project's own testing suite. No account, nothing to install:

bash
mkdir -p ~/zim-filescurl -fsSL -o ~/zim-files/wikipedia_en_climate_change_mini_2024-06.zim \  https://raw.githubusercontent.com/openzim/zim-testing-suite/main/data/withns/wikipedia_en_climate_change_mini_2024-06.zim

~/zim-files is the directory every example below points the server at — the server expands ~ itself, so it works from a shell and from a client config file alike. For full archives — Wikipedia, Wiktionary, Stack Exchange and the rest, ranging from a few hundred MB to tens of GB — browse browse.library.kiwix.org and save the .zim into the same directory. More detail, including checksums and a Windows PowerShell equivalent: Quick start.

Smithery & one-click install

OpenZIM MCP is listed on the Smithery registry and the official MCP Registry (as io.github.cameronrye/openzim-mcp). Add it to your MCP client with the Smithery CLI:

bash
npx @smithery/cli mcp add rye/openzim-mcp --client claude

For a one-click Claude Desktop extension, download the openzim-mcp-<version>.mcpb asset (and its .sha256) from the latest release and double-click it. The bundle launches the version-pinned uvx openzim-mcp@<version> (so the host needs uv) and prompts for your ZIM directory. Maintainer runbook: docs/distribution.md.

Quick start

Run the server in Simple mode (default — exposes one natural-language tool, zim_query):

bash
openzim-mcp ~/zim-files

Wire it into your MCP client. Example for Claude Desktop's claude_desktop_config.json (any MCP client that speaks stdio works the same way):

json
{  "mcpServers": {    "openzim-mcp": {      "command": "uvx",      "args": ["openzim-mcp", "~/zim-files"]    }  }}

Once the client connects, ask your LLM: "summarize the article on Photosynthesis" — zim_query dispatches to the right underlying tool automatically.

For full control, run in Advanced mode to expose all 8 specialized tools:

json
{  "mcpServers": {    "openzim-mcp-advanced": {      "command": "uvx",      "args": ["openzim-mcp", "--mode", "advanced", "~/zim-files"]    }  }}

For HTTP transport (long-running service with bearer auth, CORS, and health endpoints) see HTTP & Docker deployment.

Highlights

  • 8-tool advanced surface — zim_query, zim_search, zim_get, zim_get_section, zim_browse, zim_metadata, zim_links, zim_health. Down from 22; advanced-mode schema drops from ~36KB to ~24.1KB, clearing the MCP Tax pain band. API reference →
  • Streamable HTTP transport — bearer-token auth, CORS, health endpoints, multi-arch Docker image. HTTP & Docker deployment →
  • Per-entry MCP resources + subscriptions — zim://{name}/entry/{path} with native MIME types; clients open a subscriptions/listen stream and get resources/list_changed when a ZIM appears or disappears, resources/updated when one is replaced. Resources, prompts & subscriptions →
  • Simple-mode zim_query — one natural-language tool that dispatches to the right operation, tuned for small-model deployment targets. Quick start →
  • Archive-type presets — OpenZIM MCP detects the archive type (Wikipedia, Stack Exchange, and more) and auto-tunes retrieval and summarization for it — e.g. Stack Exchange dumps render as clean Q&A instead of vote-score noise. Operators can override the bundled defaults with a TOML file (OPENZIM_MCP_PRESETS_OVERRIDE_PATH).
  • Native libzim introspection — zim_health(zim_file_path=...) validates an archive's integrity (Archive.check() + checksum), and zim_metadata reports archive identity, full-text / title index capabilities, and an M/Counter mimetype breakdown. API reference →
  • Inbound link discovery ("what links here") — zim_links(direction="inbound") returns pages that link to an entry, ranked by linker importance. Requires a pre-built sidecar: openzim-mcp build link-graph <archive>.zim (writes <archive>.zim.linkgraph.sqlite next to the archive). API reference →

Modes

OpenZIM MCP ships two modes; pick one per client.

Simple mode (default) exposes a single intelligent tool, zim_query, that parses natural-language requests and dispatches to the right underlying operation. Built for small-model deployment targets — the wire footprint is minimal and the dispatch happens server-side, not in the LLM context. Start here unless you have a specific reason not to.

Advanced mode exposes all 8 specialized tools (zim_query, zim_search, zim_get, zim_get_section, zim_browse, zim_metadata, zim_links, zim_health) plus 3 MCP prompts (/research, /summarize, /explore) and per-entry resources. Built for larger models that can reliably dispatch over the full schema, and for clients that want fine-grained control over pagination, namespace browsing, and link-graph extraction.

Rule of thumb: models ≤ 13B parameters benefit from Simple mode; larger models (Claude Sonnet/Opus, GPT-4o-class, Llama 70B+) can dispatch Advanced mode directly. See LLM integration patterns for guidance on choosing.

Documentation

Full documentation lives at https://cameronrye.github.io/openzim-mcp/docs/.

GroupPages
Get startedIntroduction · Installation · Quick start · ZIM concepts · LLM integration patterns · Worked examples
ConceptsSmart retrieval · Search reranking · Architecture overview
ReferenceAPI reference · Configuration · Resources, prompts & subscriptions · CLI reference
OperateHTTP and Docker deployment · Performance optimization · Security best practices · Troubleshooting · FAQ · Upgrading

Project status

v3.4.0 is the current release (2026-10-25). v2.0.0 GA shipped 2026-05-27. Per SECURITY.md, the v1.x maintenance window closed when v2.5.0 shipped (2026-06-18); all active development is on the current major line. v3.0.0 is a breaking release for HTTP subscription clients: resources/subscribe/unsubscribe are no longer served — live updates ride subscriptions/listen on the 2026-07-28 protocol revision — and link-graph sidecars built by 2.x must be rebuilt. Tools, resources, and prompts are unchanged, and legacy-handshake clients keep working. Details in CHANGELOG.md, and step-by-step instructions in the upgrade guide.

Contributing

See CONTRIBUTING.md for development setup, test commands, code style, and the release process.

Security

See SECURITY.md for the vulnerability disclosure policy. No known CVEs.

License

MIT. See LICENSE.

Acknowledgments


Made with ❤️ by Cameron Rye

Source: README.md at commit 934d464

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package did not install.

Version history

3
  1. v3.4.0LatestOct 25, 2026
  2. v3.3.4Sep 18, 2026
  3. v3.3.3Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts