Model Context Protocol (MCP) server of Markdown based prompts.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"prompts-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# prompts-mcp Model Context Protocol (MCP) server of Markdown based prompts. Serves a directory of Markdown files as prompts to a chat session. Works with any MCP client supporting server-side prompts. ## Usage **Configure your client** (e.g. Claude Desktop) by adding to your `mcp.json`: ```json { "mcpServers": { "prompts": { "command": "uvx", "args": ["prompts-mcp"], "env": { "PROMPTS_DIR": "/path/to/your/prompts" } } } } ``` The location of the `mcp.json` file depends on your client and operating system. ### Configuration Set `PROMPTS_DIR` to a path containing the `.md` files you want to serve as prompts. ⚠️: The server will exit with an error if `PROMPTS_DIR` is not set or if the directory does not exist. Prompt naming: `_`'s in file names are converted to spaces and `.md` is dropped. ## Development About 100% coded by AI. See `CONTRIBUTING.md` for local setup.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.