# Radix Wiki

> Community-maintained knowledge base for Radix DLT — search, read, and contribute wiki pages.

- name: wiki.radix/radix-wiki
- version: 3.2.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 81/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/wiki.radix%2Fradix-wiki
- tools: https://api.protogrid.dev/v1/servers/wiki.radix%2Fradix-wiki/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "radix-wiki": {
      "type": "http",
      "url": "https://radix.wiki/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-7d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 13 of 13 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 4 of 13 tools declare all four hints; missing: search_wiki (destructiveHint); get_page (destructiveHint); get_pages (destructiveHint); …
- pass `tools.token_cost`: about 2,702 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 9 tool changes in 30 days
- fail `stability.rug_pull`: 4 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 13, about 2,702 tokens to load them all
- tool set hash: aeec7ba986e4b3e5c175949c34221ebd
- tools last changed: 2026-10-19T19:01:55.229Z
- badge: [![protogrid quality](https://protogrid.dev/badge/wiki.radix/radix-wiki.svg)](https://protogrid.dev/servers/wiki.radix/radix-wiki)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `get_full_corpus` changed (description, inputSchema)
  - before: Every article as one plain-text document, for bulk ingestion rather than reading. PREFLIGHT FIRST: call it with sizeOnly=true for the exact character count, a token estimate and the per-branch breakdown — the whole corpus is several times a context window. Then pull it with `maxChars` (default 200000, max 1000000), or narrow it with `tagPath` to take one branch at a time. Truncation is page-aligned and honest: `truncated`, `omittedPages` and `nextSkip` say exactly where to resume (pass skip=nextSkip). Search or list first if you have a question; the same corpus is also served, cacheably and with an ETag, at /llms-full.txt.
  - after: The whole of the Radix Wiki as one text document, for bulk ingestion. Preflight first: sizeOnly=true returns the character count, a token estimate, the per-branch breakdown and the largest pages. Then pull it with `maxChars` (default 200000, max 1000000), or one branch at a time with `tagPath`. Truncation is page-aligned: `truncated`, `omittedPages` and `nextSkip` say where to resume (pass skip=nextSkip). For a handful of pages get_pages is cheaper.
- 2026-10-19 `get_recent_changes` changed (description, inputSchema) **meaning changed**
  - before: Pages edited within the last N days, newest first — what to poll when you are watching the wiki rather than reading it. Same row shape as list_pages. Look back at most 30 days and take at most 50 rows; for anything older, list_pages sorted by updatedAt.
  - after: Pages of the Radix Wiki edited within the last N days, newest first: what to poll when you are watching the wiki rather than reading it. Same rows as list_pages. Defaults: days 7 (max 30), limit 20 (max 50). `truncated: true` means the limit cut the list; raise it, or page through list_pages.
- 2026-10-19 `get_categories` changed (description) **meaning changed**
  - before: The wiki tag hierarchy as a tree, each node carrying its path, name, description and the page count of its whole branch. The cheapest way to orient before searching, and the only way to find a valid tagPath before create_page. Costs one call and a few kilobytes; prefer it to listing pages to find out what exists.
  - after: The category tree of the Radix Wiki, the cheapest way to orient before searching. Each node carries its `path` (a tagPath list_pages and search_wiki take), name, description, `pageCount` (pages filed at that path) and `pageCountDeep` (with every descendant). `tagPaths` lists every tag path that holds pages, including any the tree does not name.
- 2026-10-19 `list_pages` changed (description, inputSchema)
  - before: Browse the wiki by tag path rather than by keyword — every page under a branch, newest first by default. Returns the same rows as search_wiki (title, URL, tagPath, slug, snippet, updatedAt) plus a pagination envelope carrying totalPages, hasMore and nextPage. Omit tagPath to walk the whole wiki; pass one from get_categories to stay inside a branch. Sort by title for an A-Z pass.
  - after: Browse the Radix Wiki by tag path rather than by keyword: every page under a branch, newest first by default. `tagPath` matches the branch and everything beneath it; omit it to walk the whole wiki. Sort by title for an A–Z pass. Same rows as search_wiki, with `totalPages`, `hasMore` and `nextPage`. Defaults: page 1, pageSize 20 (max 100).
- 2026-10-19 `get_pages` added
  - Batch read: 1 to 20 pages of the Radix Wiki in full in one call, which is how to read search or listing results. Pass `paths` as the listings return them. Paths that do not exist come back in `missing` rather than failing the call, anything past 20 in `remaining`, and pages past `maxChars` (default 250000) in `omitted` with their sizes.
- 2026-10-19 `get_page` changed (description, inputSchema) **meaning changed**
  - before: Read one page in full: its extracted text, current version number, update date and declared metadata. Takes either the whole path as one string (the `url` a listing returns works as-is) or the tagPath/slug pair it splits into — not a title. A wrong pair is answered with the tools that find a right one rather than an empty result. For the whole article set at once use get_full_corpus, and for a page as markdown fetch its URL with `.md` appended.
  - after: One page of the Radix Wiki in full: its text, version, update date and metadata. Address it by `path` ("tag/path/slug", exactly the `path` or `url` a listing returns), or by `tagPath` + `slug`; a category's own path reads its hub article. Not a title. For 2 to 20 pages call get_pages, one round trip rather than N. A miss names the nearest pages, so a wrong guess is fixed in one retry. A page's URL with `.md` appended is its markdown.
- 2026-10-19 `search_wiki` changed (description, inputSchema) **meaning changed**
  - before: Keyword search across Radix Wiki titles and page text — the first call when you know what you are looking for. Returns a page of results, each with its title, URL, tagPath, slug, a matched snippet and the date it was last updated. The tagPath and slug identify the page every read tool accepts. Narrow with tagPath when a term is common; page through with page/pageSize. When you do not yet know what exists, call get_categories first.
  - after: Keyword search across the Radix Wiki: the first call when you know what you are looking for but not where it lives. Matches titles and body prose, ranked in four tiers: titles starting with the term, titles containing it, literal body hits, then English full-text hits by relevance, which stem words and drop stopwords. Not semantic: one distinctive word beats a sentence. Each row carries a `path`, its size in `chars` and a snippet windowed on the match. Feed the paths to get_pages in one call rather than looping get_page. Narrow with tagPath when a term is common. Defaults: page 1, pageSize 20 (max 50); keep paging while `hasMore` is true.
- 2026-10-15 `edit_page` changed (inputSchema)
- 2026-10-13 `get_network_activity` added
  - Daily Radix mainnet activity, one row per UTC day since Babylon (28 September 2023): transactions, active accounts, new accounts, components and resources created, NFTs minted, and fees, $XRD burned and royalties in $XRD. Summed from the Gateway transaction stream; counts cover user transactions only. Narrow with from/to. The same rows chart at /charts and download at /api/charts/activity?format=csv.

Full history: https://api.protogrid.dev/v1/servers/wiki.radix%2Fradix-wiki/changes

## Remotes

- https://radix.wiki/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (13)

- `create_page`: Create a new Radix Wiki page. Requires a ROLA bearer token — see https://radix.wiki/AGENTS.md for the challenge-sign-verify flow. Call get_categories first for a valid tagPath. Some paths are balance-gated (blog needs 50,000 $XRD). Earns contribution points.
- `edit_page`: Edit an existing Radix Wiki page. Requires a ROLA bearer token — see https://radix.wiki/AGENTS.md. Fetch the page with get_page first and send the full revised block array; the version bump, block-level diff, and revision entry are computed server-side. Locked and author-only pages are rejected. Earns contribution points.
- `get_categories`: The category tree of the Radix Wiki, the cheapest way to orient before searching. Each node carries its `path` (a tagPath list_pages and search_wiki take), name, description, `pageCount` (pages filed at that path) and `pageCountDeep` (with every descendant). `tagPaths` lists every tag path that holds pages, including any the tree does not name.
- `get_challenge`: Step 1 of writing to the wiki: a single-use ROLA challenge (5-minute expiry). The response spells out the exact recipe for the message your Ed25519 key must sign. You always sign with your OWN key — nothing here custodies anything. Takes no parameters.
- `get_full_corpus`: The whole of the Radix Wiki as one text document, for bulk ingestion. Preflight first: sizeOnly=true returns the character count, a token estimate, the per-branch breakdown and the largest pages. Then pull it with `maxChars` (default 200000, max 1000000), or one branch at a time with `tagPath`. Truncation is page-aligned: `truncated`, `omittedPages` and `nextSkip` say where to resume (pass skip=nextSkip). For a handful of pages get_pages is cheaper.
- `get_ideas_board`: Get the RADIX Wiki Ideas Pipeline kanban — community proposals and Radix DAO tasks grouped into status columns (Discussion → Proposed → Approved → In Progress → Testing → Done), each card carrying its working group, category, priority, and assignee. Use this to follow DAO / project progress.
- `get_network_activity`: Daily Radix mainnet activity, one row per UTC day since Babylon (28 September 2023): transactions, active accounts, new accounts, components and resources created, NFTs minted, and fees, $XRD burned and royalties in $XRD. Summed from the Gateway transaction stream; counts cover user transactions only. Narrow with from/to. The same rows chart at /charts and download at /api/charts/activity?format=csv.
- `get_page`: One page of the Radix Wiki in full: its text, version, update date and metadata. Address it by `path` ("tag/path/slug", exactly the `path` or `url` a listing returns), or by `tagPath` + `slug`; a category's own path reads its hub article. Not a title. For 2 to 20 pages call get_pages, one round trip rather than N. A miss names the nearest pages, so a wrong guess is fixed in one retry. A page's URL with `.md` appended is its markdown.
- `get_pages`: Batch read: 1 to 20 pages of the Radix Wiki in full in one call, which is how to read search or listing results. Pass `paths` as the listings return them. Paths that do not exist come back in `missing` rather than failing the call, anything past 20 in `remaining`, and pages past `maxChars` (default 250000) in `omitted` with their sizes.
- `get_recent_changes`: Pages of the Radix Wiki edited within the last N days, newest first: what to poll when you are watching the wiki rather than reading it. Same rows as list_pages. Defaults: days 7 (max 30), limit 20 (max 50). `truncated: true` means the limit cut the list; raise it, or page through list_pages.
- `list_pages`: Browse the Radix Wiki by tag path rather than by keyword: every page under a branch, newest first by default. `tagPath` matches the branch and everything beneath it; omit it to walk the whole wiki. Sort by title for an A–Z pass. Same rows as search_wiki, with `totalPages`, `hasMore` and `nextPage`. Defaults: page 1, pageSize 20 (max 100).
- `login`: Step 2: exchange the signed ROLA proof for a 7-day Bearer token — the same verification the human wallet flow runs. Send the returned token as an HTTP `Authorization: Bearer <token>` header on every later create_page / edit_page call; tool arguments never carry it.
- `search_wiki`: Keyword search across the Radix Wiki: the first call when you know what you are looking for but not where it lives. Matches titles and body prose, ranked in four tiers: titles starting with the term, titles containing it, literal body hits, then English full-text hits by relevance, which stem words and drop stopwords. Not semantic: one distinctive word beats a sentence. Each row carries a `path`, its size in `chars` and a snippet windowed on the match. Feed the paths to get_pages in one call rather than looping get_page. Narrow with tagPath when a term is common. Defaults: page 1, pageSize 20 (max 50); keep paging while `hasMore` is true.