get_started
How to start a gleanyard project
Explain how to start a gleanyard collection project without installing anything (template repo, Claude Code on the web, Codespaces).
Takes no parameters.

io.github.kausalflowPublished by GitHub account kausalflowv0.14.0Updated Nov 11, 2026
Search gleanyard source recipes and read public gleanyard projects' records and health.
Read-only remote MCP server for searching gleanyard web-source recipes and reading public gleanyard projects' records and health.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.kausalflow%2Fgleanyard/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"gleanyard-read-only": {
"type": "http",
"url": "https://gleanyard-connector.leima.workers.dev/mcp"
}
}
}A read-only remote MCP server for Cloudflare Workers. Any AI app that takes a custom MCP connector (claude.ai, ChatGPT, Claude Desktop, ...) can then search the gleanyard source registry and read what public gleanyard projects publish, with nothing installed.
worker.js, with no dependencies and no build step./mcp, JSON responses, no sessions, no auth.REGISTRY_URL) and raw.githubusercontent.com; never
the sites projects collect from. Responses are cached for ten minutes.get_started, search_recipes, get_recipe, get_schema, project_status,
search_records, recent_changes.Docs: https://kausalflow.github.io/gleanyard/concepts/no-install/
Source: connector/README.md at commit 217a65c
How to start a gleanyard project
Explain how to start a gleanyard collection project without installing anything (template repo, Claude Code on the web, Codespaces).
Takes no parameters.
Search the source registry
Search the public gleanyard source registry for recipes: sources that already work, with a fixture, a terms review and a health count. Empty query lists all.
queryschemaRead one recipe
Read one registry recipe: its index entry, source file, recipe notes and terms evidence, and the command that installs it.
reciperequiredRead a registry schema
Read a record schema the registry's recipes are written for, e.g. family-event.
namerequiredHealth of a public project
Read status.json of a public gleanyard project on GitHub: each source's health, record count, warnings and last success.
refreporequiredSearch a project's published records
Search the rights-filtered export of a public gleanyard project (exports/records.jsonl, or the path its dataherb.json names) by text, optionally for one source.
refpathreporequiredtextlimitsource_idRecent changes in a project
Records added, changed or removed lately in a public gleanyard project, newest first, from its change feed (exports/changes.json).
refreporequiredlimitsource_id100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
node test.mjs # offline tests (fetch is mocked)npx wrangler dev # local server at http://localhost:8787/mcpnpx wrangler deploy # deploy to your Cloudflare account