Skip to content

Latest commit

 

History

History
63 lines (53 loc) · 3.18 KB

File metadata and controls

63 lines (53 loc) · 3.18 KB
title CCPEDIA: AI-Ready Canton Network Knowledge Platform
sidebarTitle Home
description CCPEDIA syncs every official Canton surface and exposes 78 MCP tools through one endpoint. Connect your AI tool in under two minutes.

CCPEDIA is a continuously-synced knowledge layer for Canton Network developers. It aggregates 25 official Canton data sources — forum threads, GitHub issues, CIPs, mailing lists, dev fund proposals, the SV calendar, and more — and serves all of it through a single public MCP endpoint at https://ccpedia.xyz/mcp. Connect your AI tool once and ask Canton questions in plain language without pasting docs into every prompt.

Connect Claude Desktop, Cursor, or any MCP client in under two minutes. 78 tools across 10 categories. Auto-generated from the live registry. Config snippets for Claude Desktop, Cursor, Windsurf, Claude Code, and Zed. 20 Canton recipes covering the questions developers ask most.

How it works

Connect your AI tool to CCPEDIA's public MCP endpoint and start querying live Canton data — no API key, no account, no context-window pasting required.

Add `https://ccpedia.xyz/mcp` as an MCP server in your client's config. Every [integration guide](/integrations/overview) has the exact snippet to copy. Type your Canton question normally. Your AI client calls `tools/list` once at startup, then picks the right tool automatically based on what you ask. CCPEDIA returns data synced from the real source — not cached docs from the AI's training cut-off. Results reflect the current state of the Canton ecosystem.

What CCPEDIA covers

One tool call away via `tools/list`. Covers versions, errors, CIPs, governance, and more. Refreshed every 5 to 60 minutes. Forum, GitHub, docs, CIPs, mailing lists, videos, dev fund, and more. Authored recipes for the questions Canton developers ask most often.

Access layers

CCPEDIA exposes the same Canton data through several interfaces. Pick the one that fits your workflow.

Layer What it is Best for
MCP server at /mcp 78 tools your AI calls directly over JSON-RPC 2.0 Claude Desktop, Cursor, Windsurf, Zed
REST API v1 at /api/v1/* The same data served as plain HTTP JSON Dashboards, scripts, custom apps
Atom feeds at /feed/* Per-source event firehose in Atom format RSS readers, monitoring pipelines
Web UI at ccpedia.xyz Human-readable search and browse interface Developers and governance researchers