io.github.tonbistudioPublished by GitHub account tonbistudiov0.2.3Updated Oct 30, 2026
Maintained, agent-readable knowledge bases with calibrated search and provenance. Pro key adds XL.
Read-only MCP bridge to Agent Wikis, maintained knowledge bases an assistant can list, search and read with scope and confidence signals.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
MCP server for Agent Wikis — maintained, agent-readable knowledge bases compiled from messy, fast-moving sources. Read-only; no API key or account needed for the free tier, and an optional Pro key adds the XL tier.
Four tools shaped for an agent's loop:
The scope declarations and the confident flag exist so your agent knows when not to trust the wiki — measured ~94% correct abstention. Details and the full eval: agentwikis.com/why-wikis.
Claude Code
Codex (~/.codex/config.toml)
Any MCP client (JSON config)
Wikis ship in two tiers: the free wiki/ pages, and an XL tier of deeper
per-item reference pages included with Agent Wikis Pro.
Set AGENTWIKIS_API_KEY to your Pro key and all three read tools widen to cover it:
Hermes Agent: keep the key in your profile's .env and map it in
config.yaml. Hermes passes a stdio server only its configured env, never
the .env itself. If the variable is unset, the server falls back to the free
tier.
Without a key, a confident: true search result means "the best free page covers
your terms" — the xl field on the response tells you how much you didn't see.
Routing tip. XL pages are per-item depth, not broader coverage. When a question
names a specific plugin, hook, CLI surface, runtime, API, or deployment procedure,
prefer the gated: true page over the general concept page.
Point the bridge at your own Agent Wikis deployment (e.g. a private-wiki install):
The bridge talks to agentwikis.com/api/* and returns the same payloads as the self-hosted stdio server — same document formatting, same provenance footers, same search calibration. Requires Node 18+.
Agent Wikis also serves everything as plain Markdown + llms.txt if you'd rather skip MCP entirely: see agentwikis.com/for-agents.
MIT
Source: README.md at commit 8d9397a
List all available wikis with metadata: slug, title, description, tags, status, last updated, document count, and `scope` (what each wiki covers, what it does NOT cover, and how current it is — use this to pick a wiki and to decide when to fall back to web search). Includes "coming soon" placeholders, marked by status.
Takes no parameters.
Orient yourself in one wiki, in a single call: returns its metadata, `scope` (coverage / not-covered / freshness), document count, the entry document, and a `map` of all documents (paths + titles, grouped by folder) so you can pick what to read_document next. Use a slug from list_wikis. Free tier: the map omits Pro (XL) pages. The response's `xl` field says how many exist and where to list them; set AGENTWIKIS_API_KEY to include them.
wikirequiredRead one document in a wiki. Without `section`, returns the full Markdown (frontmatter stripped) plus a provenance footer. To save tokens on a long page, pass `section` (a heading title as it appears in the page body, or its slug anchor) to retrieve ONLY that section and its subsections. The Markdown may contain [[wikilinks]] to related docs — follow one by calling read_document with path "wiki/<target>.md".
pathrequiredwikirequiredsectionFind the best-matching PAGES for a query, ranked by how many of your query terms each page covers. Searches one wiki if `wiki` is given, otherwise every active wiki. Each result has its wiki, path, matched terms, and a short snippet for orientation — then read_document the page to get the answer. Returns a `confident` flag: if false, the wiki(s) likely lack this — fall back to web search. Free tier only. When the response carries an `xl` field, Pro pages in scope were NOT searched and `confident` describes the free tier alone — do not read a confident hit as "this is the best the wiki has".
wikiqueryrequired90% 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.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
claude mcp add agentwikis -- npx -y agentwikis-mcp[mcp_servers.agentwikis]command = "npx"args = ["-y", "agentwikis-mcp"]{ "mcpServers": { "agentwikis": { "command": "npx", "args": ["-y", "agentwikis-mcp"] } } }{ "mcpServers": { "agentwikis": { "command": "npx", "args": ["-y", "agentwikis-mcp"], "env": { "AGENTWIKIS_API_KEY": "aw_..." } } }}mcp_servers: agentwikis: command: npx args: ["-y", "agentwikis-mcp"] env: AGENTWIKIS_API_KEY: "${AGENTWIKIS_API_KEY}"AGENTWIKIS_URL=https://wikis.internal.example npx -y agentwikis-mcp