For agents
Mayphus.org is a public working memory for people and AI agents. The same published pages, notes, projects, and capabilities are available through one read-only MCP gateway.
One gateway
Connect explicitly to the public MCP server. It exposes published material and bounded tools; it does not grant access to private site areas or change site content.
Nothing here silently installs or connects an agent. A person or developer chooses to add this endpoint.
Capabilities
Six small public capabilities, described once and shared by this page, JSON, and MCP.
Discover public work
PUBLIC · READ ONLYList the public capabilities, projects, and pages that Mayphus has chosen to share.
- Human
- /agents/
- MCP
discover_capabilitiesdiscover_projects
Search public knowledge
PUBLIC · READ ONLYSearch across public pages, projects, articles, notes, and capability descriptions.
- Human
- /notes/
- MCP
search
Fetch a public record
PUBLIC · READ ONLYRetrieve one public search result by its stable identifier with a canonical citation URL.
- Human
- /agents/
- MCP
fetchget_project
Follow public updates
PUBLIC · READ ONLYRead recent public articles and notes without inferring private activity.
- Human
- /notes/
- MCP
get_public_updates
Generate a city map
PUBLIC · READ ONLYTurn a bounded city-and-topic request into a public OpenStreetMap-based result without changing server state.
Read the public profile
PUBLIC · READ ONLYRetrieve Mayphus Tang's deliberately published profile, names, links, and selected work.
- Human
- /profile/
- MCP
searchfetch
Connect
Keep tool approval enabled when trying a new remote MCP server, even when its published tools are read-only.
ChatGPT
Create a custom MCP app or connector and use this server URL.
https://mayphus.org/mcp
Codex
Add this remote server to the Codex MCP configuration.
[mcp_servers.mayphus]
url = "https://mayphus.org/mcp"
Responses API
Place this object in the request's tools array.
{
"type": "mcp",
"server_label": "mayphus",
"server_url": "https://mayphus.org/mcp",
"require_approval": "always"
}
Public discovery
These indexes are ordinary public files. They make the site easier to inspect, cite, and reuse, but they are not an automatic authorization mechanism.
- llms.txt — compact public reading guide
- ai.json — structured public site index
- capabilities — stable capability records
- notes — public non-todo notes
- site manifest — canonical discovery URLs
- RSS and sitemap — public change and route feeds