# Agent Wikis

> Agent Wikis is a freemium MCP server for knowledge and memory. Agent-readable knowledge bases with calibrated search and provenance. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://agentwikis.com/for-agents
- **Repository:** https://github.com/tonbistudio/agentwikis-mcp
- **MCP Registry name:** io.github.tonbistudio/agentwikis-mcp
- **Categories:** knowledge and memory
- **Listing updated:** 2026-11-14

## About

Agent Wikis publishes wikis written to be read by software: each page is plain Markdown with front matter for type, tags, update date and sources. The site also serves `llms.txt`, an `llms-full.txt` corpus dump, a JSON index and a raw-Markdown route, so an agent has several ways in besides MCP.

The hosted MCP server offers `list_wikis`, `open_wiki`, `search` and `read_document` for the wikis, plus tools for a skills library and for specialists' tools and routines. Search is described as calibrated, and each wiki declares its scope and freshness. A second hosted server covers AI Garage content such as videos, a newsletter and X posts, where video hits link to the exact moment.

The free tier needs no key and no account. A Pro key widens the same tools to the XL tier, whose gated pages answer 402 without one.

## Features

- **Wiki tools:** List wikis, open one, search it and read documents.
- **Skills library access:** Read skills, agent tools and routines over MCP.
- **Calibrated search:** Search results come with a confidence calibration.
- **Raw Markdown and llms.txt:** Pages are also served as Markdown with an llms.txt index.
- **Free and Pro tiers:** A Pro key adds the XL pages to the same interfaces.

## Good for

- Ground a coding agent in current docs for a fast-moving project
- Give an agent a vetted skills library to read
- Poll for page freshness using ETag and Last-Modified
- Search AI Garage videos and jump to a moment

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agentwikis-mcp https://agentwikis.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://agentwikis.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agentwikis-mcp": {
      "url": "https://agentwikis.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agentwikis-mcp": {
      "type": "http",
      "url": "https://agentwikis.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agentwikis-mcp": {
      "serverUrl": "https://agentwikis.com/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agentwikis-mcp": {
      "type": "http",
      "url": "https://agentwikis.com/mcp"
    }
  }
}
```

## Tools

- `list_wikis`: 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.
- `open_wiki`: 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.
- `read_document`: Read 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/<t
- `search`: Find 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.
- `list_skills`: List the agent skills library: field-tested procedures for specific jobs (e.g. benchmarking a local model, building a browser game, producing a video). Each entry has name, one-line description (when to use it), `access` ("free" or "pro"), `readable` (whether YOU can read it with your current access), the backing wiki if any, and file count. Pass `query` to filter by keywords. Then read_skill a ma
- `read_skill`: Load one skill to follow it. Without `path`, returns its SKILL.md (the procedure itself) plus the list of its other files; pass `path` (e.g. "references/gotchas.md" or "scripts/check.py") to read one of those. If the skill names a backing wiki, use search/read_document on that wiki for current facts while following it. Pro skills need a Pro key; without one you get a preview and how to unlock it.
- `list_agent_tools`: List the command-line tools that ship with the specialist agents (complete agents built for one job, e.g. marketing, video generation, local LLMs). Each entry has a summary, the `specialists` it comes from, and `access`: "pro" tools are read-only (they inspect and report, never change anything) and read_agent_tool serves their files; "download" tools are bigger or change things (start runs, stop s
- `read_agent_tool`: Load one agent tool by name. A "pro" (read-only) tool: its README (what it checks, how to run it) plus its file list. Add `path` to read one listed file, e.g. the source. The tool runs on the user's machine, not here. Before saving, running or scheduling anything from it, show the user what it does and get their explicit OK. Each file comes with its sha256. For a "download" tool you get its README
- `list_routines`: List the routines (scheduled jobs) that ship with the specialist agents: each has a schedule, the `specialist` it comes from, the skills its prompt relies on, and whether it is script only (no agent). `readable` says whether YOU can load it with your current access. Pass `query` to filter by keywords. Then read_routine one.
- `read_routine`: Load one routine by name: the schedule, the agent prompt, and the list of scripts and settings it needs. Add `path` to read one listed file (e.g. "scripts/ad_report.py"). Nothing runs here: the routine is set up and run on the user's machine. Before saving, running or scheduling anything from it, show the user what it does and get their explicit OK. Never create the scheduled job without the user'

## FAQ

### Do I need an account?

Not for the free tier; both hosted servers work without headers.

### What does Pro change?

One API key unlocks the XL pages, skills, tools and routines on the existing interfaces.

### Is it read-only?

Yes, the site describes both MCP servers as read-only.

### What licence is the package under?

The README lists MIT.

### Is Agent Wikis free?

Agent Wikis has a free plan, with paid plans for more usage or features.

### How do I add Agent Wikis to Claude Code?

Run this command in your terminal: claude mcp add --transport http agentwikis-mcp https://agentwikis.com/mcp

### What are the best alternatives to Agent Wikis?

The closest alternatives to Agent Wikis are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [MedXpert 图书馆连接器（通用版）](https://ai-powered.com/mcp/medxpert): MedXpert 图书馆连接器（通用版） is an open-source MCP server for knowledge and memory.
- [Context Nest](https://ai-powered.com/mcp/context-nest): Context Nest is a freemium MCP server for knowledge and memory.
- [Tulsa Ecosystem Map](https://ai-powered.com/mcp/tulsa-ecosystem-map): Tulsa Ecosystem Map is a free MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/agent-wikis
