Skip to content
CCPEDIAby Unity Nodes
Knowledge layer // Live

19 sources. One unified corpus.

Every Canton Network knowledge source you would search separately, indexed continuously and exposed through 88 MCP tools. The numbers below refresh every minute, straight from the production database.

Foundation KB drift: 3 items behind live · JSON →
Knowledge layer19 sources · syncing
88MCP TOOLS
176.0msAVG LATENCY
SERVER DATA
CIPs
123
Docs
2 664
Whitepapers
7
Blog
1 157
Forum
4 247
Mailing
3 167
YouTube
171
Discussions
51
GitHub Items
6 773
Releases
1 971
SDK Versions
8 039
Radar
436
Dev Fund
507
Ecosystem
547
Foundation
140
DSO
1 327
Sv Calendar Event
696
On
600
Cip Attachment
54
Example MCP calls SAMPLE
Total indexed records19 of 19 sources · semantic search enabled
32 677across 19 sources
88 MCP tools34 035 RAG chunks5 min - 24 hr sync/api/v1/sources
Apache 2.0
How the data lands here

Each source is polled on its own cadence - the forum every 5 min, the SDK index every 6 hr, whitepapers every 24 hr. Anything changed since the last sync is upserted and re-embedded.

Why one corpus matters

Cross-source queries (“which CIP introduced this forum breakage?”) only work when forum, docs, CIPs, GitHub and proposals share a single semantic index.

Verify the numbers

The widget calls /api/v1/sources. Same endpoint anyone can hit - no caching, no embellishment.