Ao3 MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 116 installs a week from pypi. Last commit 28 Jul 2026.
Search AO3 and have fics read by a secondary model before they're recommended
Today is the operative word: we check Ao3 MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ao3-mcp -e 'GEMINI_API_KEY=<GEMINI_API_KEY>' -- uvx ao3-mcp
{
"mcpServers": {
"ao3-mcp": {
"command": "uvx",
"args": [
"ao3-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}
[mcp_servers.ao3-mcp]
command = "uvx"
args = ["ao3-mcp"]
env = { GEMINI_API_KEY = "<GEMINI_API_KEY>" }
{
"mcpServers": {
"ao3-mcp": {
"command": "uvx",
"args": [
"ao3-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}
{
"servers": {
"ao3-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"ao3-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}
Put your own value in place of
<GEMINI_API_KEY> (Gemini API key (free from https://aistudio.google.com/api-keys)).
The author’s registry entry marks it as required.
EU GDPR decisions by thedpo.eu — search all EU DPA decisions and recommendations
Search, read, and get recommendations for AWS documentation pages.
How often AI search picks a brand first. Recommendation Rate data from Modern Discovery.
A second opinion from an unrelated AI model before you commit to a decision.
Work a Noeto kanban board: read and search it, create, move and comment on cards, keep docs on them.
Search and read Apple Messages — chats and decoded text, sending off by default
Search second-hand listings on Vinted (anonymous, read-only).
Read-only MCP server for verified book recommendations and reading lists.
Answers built from our own checks of this server.