About Agent Wikis
Agent Wikis is a read-only MCP server that gives agents access to maintained knowledge bases assembled from changing sources. Its scope declarations, calibrated search confidence, and provenance help agents judge when results apply; an optional Pro key unlocks XL pages.
Key features
- 01Lists wikis with scope declarations
- 02Opens wiki metadata and document maps
- 03Ranks search results with a confidence flag
- 04Reads full documents or individual sections
- 05Includes provenance with document content
- 06Optional Pro access to XL pages
Use cases
- 01Find relevant pages in maintained knowledge bases
- 02Check whether a wiki covers a topic
- 03Retrieve a specific document section with provenance
- 04Search deeper per-item references using Pro
MCP support
Exposes four read-only tools to MCP clients: list_wikis, open_wiki, search, and read_document. An optional AGENTWIKIS_API_KEY enables search and reading across the XL tier.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y agentwikis-mcpAGENTWIKIS_URLBase URL of the Agent Wikis instance to query. Defaults to https://agentwikis.com; set to point at a self-hosted/private instance.AGENTWIKIS_API_KEYSecretAgent Wikis Pro API key. When set, open_wiki, search, and read_document include the Pro (XL) tier; without it the server serves the free tier only.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 5d ago
This tool takes no parameters.
Details
From the project READMEagentwikis-mcp
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:
| Tool | What it does |
|---|---|
list_wikis | Every wiki + its declared scope (covers / not covered / current-as-of) |
open_wiki | One wiki's metadata + full document map — orient in a single call |
search | Ranked pages with a calibrated confident flag — when false, fall back to web search |
read_document | Full page or a single section, with a provenance footer |
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.
Install
Claude Code
claude mcp add agentwikis -- npx -y agentwikis-mcp
Codex (~/.codex/config.toml)
[mcp_servers.agentwikis]
command = "npx"
args = ["-y", "agentwikis-mcp"]
Any MCP client (JSON config)
{ "mcpServers": { "agentwikis": { "command": "npx", "args": ["-y", "agentwikis-mcp"] } } }
Pro (XL) access
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:
{
"mcpServers": {
"agentwikis": {
"command": "npx",
"args": ["-y", "agentwikis-mcp"],
"env": { "AGENTWIKIS_API_KEY": "aw_..." }
}
}
}
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.
mcp_servers:
agentwikis:
command: npx
args: ["-y", "agentwikis-mcp"]
env:
AGENTWIKIS_API_KEY: "${AGENTWIKIS_API_KEY}"
| Without a key | With a Pro key | |
|---|---|---|
open_wiki | free pages; an xl field says how many Pro pages exist | free + XL pages, XL marked gated: true |
search | free pages only; an xl field reports how many Pro pages were not searched | ranks across both tiers, confident calibrated over the full corpus |
read_document | 402 on an XL path | returns the XL page |
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.
Self-hosted instances
Point the bridge at your own Agent Wikis deployment (e.g. a private-wiki install):
AGENTWIKIS_URL=https://wikis.internal.example npx -y agentwikis-mcp
What's inside
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.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.