wikipedia-mcp-server
by cyanheads
README.md
<div align="center">
<h1>@cyanheads/wikipedia-mcp-server</h1>
<p><b>Search Wikipedia articles, read summaries and full text, target sections, list an article's cited references, find nearby pages, and list language editions via MCP. STDIO or Streamable HTTP.</b>
<div>7 Tools</div>
</p>
</div>
<div align="center">
[](./CHANGELOG.md) [](./LICENSE) [](https://github.com/users/cyanheads/packages/container/package/wikipedia-mcp-server) [](https://modelcontextprotocol.io/) [](https://www.npmjs.com/package/@cyanheads/wikipedia-mcp-server) [](https://www.typescriptlang.org/) [](https://bun.sh/)
</div>
<div align="center">
[](https://github.com/cyanheads/wikipedia-mcp-server/releases/latest/download/wikipedia-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=wikipedia-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvd2lraXBlZGlhLW1jcC1zZXJ2ZXIiXX0=) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22wikipedia-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fwikipedia-mcp-server%22%5D%7D)
[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)
</div>
<div align="center">
**Public Hosted Server:** [https://wikipedia.caseyjhand.com/mcp](https://wikipedia.caseyjhand.com/mcp)
</div>
---
## Overview
Wikipedia in any language edition. Search articles, read summaries or just the sections you need, list the footnotes an article cites, find geotagged pages near a coordinate, and list an article's language editions. Ships the `wikipedia-guide` agent skill (`skill://wikipedia-guide/SKILL.md`), which MCP clients read for the gates that span tools: switching editions, disambiguation pages, section numbers versus `section_index`, and what to check before reporting something absent.
### Tools
| Tool | Description |
|:---|:---|
| `wikipedia_search_articles` | Full-text search across Wikipedia, returning ranked results with short descriptions, Wikidata QIDs, plain-text snippets, and page IDs, plus Wikipedia's spelling suggestion. |
| `wikipedia_get_summary` | Short summary for any article — plain text, Wikidata QID, description, thumbnail URL, page type, canonical URL, revision, and coordinates. |
| `wikipedia_get_article` | Full article or a targeted section as clean plain text, with section markers preserved, the canonical URL, and the revision it was read from. |
| `wikipedia_get_sections` | Table of contents with `section_index` values for targeted section reads. |
| `wikipedia_search_nearby` | Geotagged Wikipedia articles within a radius of a WGS 84 coordinate, sorted by distance, with short descriptions and Wikidata QIDs. |
| `wikipedia_get_languages` | All language editions available for an article, with titles and URLs, or just the editions you ask for. |
| `wikipedia_get_references` | The footnotes an article cites, in document order, with each footnote's text, external links (archive copies included), and DOIs, plus the full citations that short citations point to. |
## Capability reference
### `wikipedia_search_articles` <sub>tool</sub>
- Free-text `query` (an empty one fails with `empty_query`), positive integer `limit` (default 10, clamped to 500), and `offset` paging, passing back enrichment `nextOffset`. Only a clamped call carries `requestedLimit`, `appliedLimit`, and a clamp notice. Wikipedia serves no result past the 10,000th: an `offset` at or beyond it fails with `offset_too_large`, and a page ending on that window carries enrichment `truncated`
- CirrusSearch operators include `incategory:"1648 treaties"` (`wikipedia_get_sections` returns an article's category names), `morelike:Peace of Westphalia`, `intitle:Python`, `hastemplate:Infobox`, and `insource:Python` (support depends on the installation). `sort` defaults to `relevance`; alternatives are `last_edit_desc`, `create_timestamp_desc`, `incoming_links_desc`, and `title_natural_asc`. Enrichment echoes `sort`; keep it and `query` unchanged when paging
- Each result carries a plain-text snippet, page ID, word count, and — when the article has them — its short `description` and Wikidata QID (`wikibase_item`); enrichment `suggestion` carries Wikipedia's spelling correction (`einstien` → `einstein`). A page whose descriptions and QIDs could not all be loaded returns those results without either field, with a `notice`; `wikipedia_get_summary` returns both for any one title
- Invalid or over-complex `insource:/…/` and `intitle:/…/` regexes fail once with `invalid_query`, the `upstreamCode`, and guidance to correct or simplify the regex or remove the operator. A busy regex search remains retryable
---
### `wikipedia_get_summary` <sub>tool</sub>
- Takes a `title`; returns the REST summary extract — a fragment from the start of the lead (`wikipedia_get_article` with `section_index: 0` reads the whole lead) — plus the short description, thumbnail URL, Wikidata QID (`wikibase_item`), and, for a geotagged article, `latitude` / `longitude` to pass straight to `wikipedia_search_nearby`
- `page_type` discriminates `standard` / `disambiguation` / `mainpage` (the edition's Main Page) / `no-extract` (outside the article namespace, or non-wikitext content); on `disambiguation`, re-query with `wikipedia_search_articles`. `url`, `revision_id`, and `last_modified` name the revision read, and `?oldid=<revision_id>` is a permanent link to it
- Redirects are followed and reported in `redirected_from`, and in `redirect_section` when the alias points into a section, with a notice naming the `section_index` to read once the table of contents confirms the heading (otherwise pointing to `wikipedia_get_sections`); the extract still covers the whole article. The redirect lookup is best-effort: when it fails the summary returns without the fields and a notice says so
- An existing page without a summary extract succeeds with metadata, an empty `extract`, and guidance to open the canonical URL or try `section_index: 0`. Namespace pages may contain documentation rather than article prose. An empty description is absent; a missing title still fails with `not_found`
---
### `wikipedia_get_article` <sub>tool</sub>
- Without `section_index`: the full article with `== Section ==` markers, or a section outline (`truncated: true`) when it exceeds `WIKIPEDIA_ARTICLE_OVERFLOW_BYTES` (default 80,000 bytes). With a `section_index` from `wikipedia_get_sections` (`0` is the lead): that section plus its nested subsections
- Outline entries include verified `section_index` values where available, including 0 for the lead. Ambiguous or unindexed headings retain the section-list fallback. TOC verification gets one short attempt; unavailable verification is disclosed
- Redirects expose `redirected_from` and, for a section target, `redirect_section`. A full read remains full and includes targeted-read guidance; an explicit `section_index`, including 0, takes precedence
- `page_type: "disambiguation"` appears only on a disambiguation page, on full, outline, section, and table reads. Full and outline reads take it from their own request; on section and table reads it comes from a best-effort lookup beside the parse, and when that fails the read returns unflagged with a notice pointing to `wikipedia_get_summary`
- List items render as `- ` or numbered `N.` lines (an `<ol>`'s `start`, `reversed`, and item `value` honored), indented two spaces per nesting level up to 16 levels
- Every read returns `url` and `revision_id` (`?oldid=<revision_id>` is a permanent link to the text read); a full read, outline included, also returns `last_modified`. With `WIKIPEDIA_BASE_URL` set, a section read omits `url`
- Section reads render phylogenetic clade trees as fenced, indented branches, pairing each row’s label with its leaf and preserving unnamed forks. An unparseable tree leaves `[table omitted: unparseable clade]`; trees have no `table_index`
- Section reads also carry data tables as pipe-delimited rows and infoboxes as `label: value` lines, which the full-article extract strips; a table over 40,000 rendered bytes leaves a `[table omitted: N rows (table T)]` marker. Pass `table_index: T` with the section to read that table in complete row pages, then follow `next_cursor` as `cursor` with the same inputs. Continuations read the first page’s revision; caption and header appear once. Each page's table text fits 40,000 UTF-8 bytes on both surfaces, except an indivisible oversized row or first-page caption/header returned alone with `oversized_row: true`
---
### `wikipedia_get_sections` <sub>tool</sub>
- Takes a `title`; returns section titles, heading levels, hierarchical numbering (e.g. `"2.1"`), and the `section_index` to pass to `wikipedia_get_article` — the first entry is the lead (`index: 0`, titled `Introduction`)
- Heading titles use the article renderer’s script, formula, whitespace and single-pass entity normalization, so `CO₂` stays identical across the section list, article reads and verified outline entries
- Returns `categories`, the article's visible categories in upstream order, without the namespace prefix; pass one to `wikipedia_search_articles` as `incategory:"<name>"`. `page_type: "disambiguation"` appears only on a disambiguation page, with a notice
- Fails with `no_sections` on a stub, a very short article, or a disambiguation page with no headings — read a stub with `wikipedia_get_article`, and search for the intended article from a disambiguation page
- Redirect aliases expose `redirected_from` and optional `redirect_section`; `redirect_section_index` appears only when a unique anchor matches a real numeric TOC index
---
### `wikipedia_search_nearby` <sub>tool</sub>
- `latitude` −90…90 / `longitude` −180…180 (WGS 84), `radius_meters` 10–10,000 (default 1000; a larger value is clamped to 10,000, with `requestedRadiusMeters` beside `radiusMetersUsed` and a notice to search from adjacent points), and positive integer `limit` (default 10, clamped to 500), with no pagination past `limit`; enrichment `truncated` flags more matches than `limit` allowed — at 500, Wikipedia's ceiling, sweep narrower radii instead. Only a clamped call carries `requestedLimit`, `appliedLimit`, and a clamp notice
- Returns articles sorted by `distance_meters`, with coordinates, short `description`, and Wikidata QID (`wikibase_item`). Each is placed by the article's own GeoData coordinate tag, not its Wikidata item's coordinate, so a mistagged article appears where the tag puts it
---
### `wikipedia_get_languages` <sub>tool</sub>
- Takes a `title`; returns each edition's `language_code`, `edition_code`, article title, and URL, plus `source_title`, the resolved title. Pass `edition_code` — not `language_code` — as `language` on other tools; the two can differ (`gsw` vs `als`)
- `editions` narrows the list to the codes asked for, and `total_languages` stays the unfiltered count. Every code lands in one place: its `languages` entry; `source_editions` when it names the queried edition (`als` and `gsw` alike); `unknown_editions` when it names no Wikipedia edition (`jp` for `ja`; never reported while the edition registry is unavailable); or `missing` when the edition has no article. Legacy codes `nb`, `be-x-old`, and `egl` match their editions (`no`, `be-tarask`, `eml`)
- Fails with `no_other_languages` when an unfiltered call finds no translations; with `editions` given, an article with none succeeds with `languages: []`
---
### `wikipedia_get_references` <sub>tool</sub>
- Takes a `title`; returns `references[]` in document order across every reference list, each with `id`, `label` (the in-text marker), `group` (a notes list such as `lower-alpha`, absent for the main list), `text`, `urls` (archive copies included), and `dois` (from `doi.org` links, percent-decoded). `total_references` counts the footnotes on all pages. `wikipedia_get_article` drops footnote markers and reference lists. Redirects expose `redirected_from` and, for a section target, `redirect_section`
- A short citation such as "Galinsky 2012, pp. 75–76" carries `work_ids`, and `works` on the same page holds the full citations they name, each once. Bibliography and further-reading entries no footnote points to are not listed — read those sections with `wikipedia_get_article`
- Each page holds whole footnotes within 40,000 UTF-8 bytes on both surfaces; follow `next_cursor` as `cursor` with the same `title` and `language`. Continuations read the first page's `revision_id`, and a cursor past the last footnote fails `invalid_cursor`. An unreadable pinned revision fails `revision_unavailable`. An article with no footnotes returns an empty list with a `notice`, not an error
## Features
Built on [`@cyanheads/mcp-ts-core`](https://github.com/cyanheads/mcp-ts-core): stdio and Streamable HTTP transports, pluggable auth (`none` / `jwt` / `oauth`), swappable storage (`in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`), structured logging with optional OpenTelemetry tracing.
Wikipedia-specific:
- Dual API integration — MediaWiki REST API (`/api/rest_v1/`) for summaries, Action API (`/w/api.php`) for search, full text, sections, geo search, and language links
- Retry and backoff on every required request, including the transient refusals (search too busy, rate-limited, read-only) the Action API returns inside an HTTP 200 body, with an upstream `Retry-After` honored and each request's retries bounded at 30 s. The best-effort description lookup on search results gets one short attempt; `User-Agent` header per Wikimedia API policy
- Every read path renders HTML through one renderer to the same plain-text shape — `== Heading ==` markers, list items as `- ` / `N.` lines kept at their nesting, superscripts kept, code fenced: the full article from the Action API's HTML extract, a section from the parser's own HTML for that section, the summary from the REST `extract_html`. A section read additionally carries data tables, infoboxes, and the lists inside layout tables, none of which the extract carries. Footnote markers, reference lists, and the hidden Citation Style 1 maintenance messages (`CS1 maint: …`) are dropped on every path; `wikipedia_get_references` returns the footnotes
- Per-call `language` parameter on every tool (default `en`) — all Wikipedia language editions accessible in a single session; every title read follows redirects
- Language validation against a live edition registry built from the MediaWiki `action=sitematrix` endpoint (cached 24h) — catches structurally valid but nonexistent editions before they cause timeouts
Agent-friendly output:
- `page_type` on summaries discriminates `standard` / `disambiguation` / `mainpage` / `no-extract` — no string parsing needed — and article and section reads flag a disambiguation page the same way
- `wikibase_item` (Wikidata QID) on summaries and on search and nearby results enables direct cross-referencing with wikidata-mcp-server
- Article text, snippets, and titles are backslash-escaped on the way into the markdown `content[]` render, so an article that writes about markup or markdown syntax reads as itself instead of being interpreted by the client; `structuredContent` carries the same text unescaped. Fenced code blocks and table-row delimiters pass through unescaped, while table cells stay escaped. A nested list is fenced in `content[]` so its indentation survives a markdown read, and a notice that quotes a title or query is block-quoted and escaped there, raw in `structuredContent`
- `section_index` on table-of-contents entries links directly to the targeted-read parameter on `wikipedia_get_article`, index 0 included
- Titles MediaWiki cannot name a page with — `< > [ ] { }`, the `|` multi-title separator, percent escapes, magic tildes, relative paths — are refused before any request, with `invalid_title`; a trailing `#fragment` is accepted and resolves normally. Titles that name no page are refused with `invalid_title` on every read tool: `Special:` and `Media:` titles in any edition's spelling, special pages and files that do not exist, interwiki links such as `wikt:cat` or `fr:Chat`, and invalid entries such as `Talk:`
- Recovery hints on every error type — callers get actionable next steps (e.g., "use `wikipedia_search_articles` to find the correct title")
## Getting started
Connect to the hosted instance, no install:
```sh
claude mcp add --transport http wikipedia-mcp-server https://wikipedia.caseyjhand.com/mcp
```
Or run it locally:
```sh
claude mcp add wikipedia-mcp-server -- npx -y @cyanheads/wikipedia-mcp-server
```
For other clients, add this to the MCP config file:
```json
{
"mcpServers": {
"wikipedia-mcp-server": {
"command": "npx",
"args": ["-y", "@cyanheads/wikipedia-mcp-server"]
}
}
}
```
No API key is required — Wikipedia's API is public. For Docker or a source build, see [Running the server](#running-the-server).
## Configuration
| Variable | Description | Default |
|:---------|:------------|:--------|
| `WIKIPEDIA_USER_AGENT` | User-Agent header sent with every Wikimedia API request. Customize for your deployment. | `wikipedia-mcp-server/0.3.1 (https://github.com/cyanheads/wikipedia-mcp-server)` |
| `WIKIPEDIA_BASE_URL` | Optional single-instance override. Unset (default): compose per-language hosts, `language` selects the edition per call. Set to a full base URL (e.g. a private MediaWiki mirror): route every call at that one fixed host — `language` no longer varies it. | *(unset)* |
| `WIKIPEDIA_ARTICLE_OVERFLOW_BYTES` | Byte budget above which a full-article read (`wikipedia_get_article` without `section_index`) returns a section outline instead of the full text. Tuned for this domain — ordinary articles stay whole; only genuine mega-articles (World War II ~86 KB, United States ~94 KB) outline. Section-targeted reads are never affected. | `80000` |
| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |
| `MCP_HTTP_PORT` | Port for HTTP server. | `3010` |
| `MCP_SESSION_MODE` | HTTP session mode: `stateless`, `stateful`, or `auto` (which resolves to `stateful`). The Docker image ships `stateless`. | `auto` |
| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |
| `MCP_LOG_LEVEL` | Log level (RFC 5424). | `info` |
| `LOGS_DIR` | Directory for log files (Node.js only). | `<project-root>/logs` |
| `LOG_TOOL_FAILURE_PAYLOADS` | Log each failed tool call's arguments and result, redacted by key name and capped at `LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES` (default `16384`). A secret inside a free-form value is not redacted. | `false` |
| `OTEL_ENABLED` | Enable OpenTelemetry instrumentation (spans, metrics, completion logs). | `false` |
See [`.env.example`](./.env.example) for the full list of optional overrides.
## Running the server
### Local development
Requires [Bun v1.4.4](https://bun.sh/) or higher (or Node.js v24+).
- **Clone and install:**
```sh
git clone https://github.com/cyanheads/wikipedia-mcp-server.git
cd wikipedia-mcp-server && bun install
cp .env.example .env # optional: customize WIKIPEDIA_USER_AGENT or logging
```
- **Build and run:**
```sh
# One-time build
bun run rebuild
# Run the built server
bun run start:stdio
# or
bun run start:http # listens at http://localhost:3010/mcp (MCP_HTTP_PORT)
```
- **Run checks and tests:**
```sh
bun run devcheck # Lint, format, typecheck, security
bun run test # Vitest test suite
bun run lint:mcp # Validate MCP definitions against spec
```
### Docker
```sh
docker build -t wikipedia-mcp-server .
docker run --rm -p 3010:3010 wikipedia-mcp-server
```
The Dockerfile defaults to HTTP transport, stateless session mode, and logs to `/var/log/wikipedia-mcp-server`. To run the published image over stdio from an MCP client, use `"command": "docker"` with `"args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/wikipedia-mcp-server:latest"]`. OpenTelemetry peer dependencies are installed by default — build with `--build-arg OTEL_ENABLED=false` to omit them.
## Project structure
| Directory | Purpose |
|:----------|:--------|
| `src/index.ts` | `createApp()` entry point — registers tools and inits the Wikipedia service. |
| `src/config` | Server-specific environment variable parsing and validation with Zod. |
| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`) — one file per tool. |
| `src/services/wikipedia` | WikipediaService — REST API + Action API client with retry/backoff and language validation. |
| `skills/` | The published `wikipedia-guide` agent skill, served over MCP and shipped in the package. |
| `tests/` | Unit and integration tests mirroring `src/`. |
## Development guide
See [`CLAUDE.md`](./CLAUDE.md) for development guidelines and architectural rules. The short version:
- Handlers throw, framework catches — no `try/catch` in tool logic
- Use `ctx.log` for request-scoped logging, `ctx.state` for tenant-scoped storage
- Register new tools in `src/mcp-server/tools/definitions/index.ts`
- Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields
## Contributing
Issues are welcome. Run checks and tests before submitting:
```sh
bun run devcheck
bun run test
```
## License
Apache-2.0 — see [LICENSE](LICENSE) for details.
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessLimited data