Wikipedia for AI agents. A Model Context Protocol server that gives Claude Code, Cursor, Windsurf — or any MCP-compatible AI agent — structured causal knowledge: 245 events, 457 causal links with confidence scores, and 8 insight patterns across 9 verticals of technology history.
Ask why a technology, architecture, or decision emerged — Causari answers from a sourced graph of cause-and-effect across computing history, delivered straight into your agent's context. It's a knowledge base of the world's technology causality, not a logger of your agent's actions.
{
"mcpServers": {
"causari": { "command": "npx", "args": ["-y", "@causari/mcp-server"] }
}
}Add to .mcp.json (Claude Code) or ~/.cursor/mcp.json (Cursor). Restart your IDE. Done.
1. "Why does Kubernetes exist?" → causal_chain("kubernetes", depth: 3) returns: Docker containers → Linux cgroups → Unix philosophy → and the pattern that open standards win infrastructure wars. Every link has evidence + confidence.
2. "My startup competes with a closed platform using an open protocol" → historical_resonance(...) matches TCP/IP vs OSI, Linux vs proprietary Unix, Web vs AOL. Returns predictive value scores and historical exemplars.
3. "High-impact computing events 1990-2010" → query_events(yearFrom: 1990, yearTo: 2010, domains: ["technology"]) returns Linux, World Wide Web, Java, Google, iPhone, Bitcoin — structured, filterable, scored by impact.
Wikipedia is excellent for humans, but unstructured for AI parsing. When you ask Claude "trace what led to the Transformer architecture", it stitches together prose memory — fluent but unsourced and uncalibrated.
This MCP server hands the agent a structured causal graph instead:
- Nodes: historical events with year, domain, impact score, sources
- Edges: causal links (
caused/enabled/accelerated/delayed/prevented) with confidence + evidence text - Patterns: recurring causal insights ("Information Democratization Cycle", "Substrate Substitution") that the agent can reuse for analogical reasoning
The agent reasons over real structure — and tells the user what it knows, where it's calibrated, and where it isn't.
| Plain Claude / Wikipedia lookup | Causari MCP | |
|---|---|---|
| Output shape | Prose paragraphs | Structured nodes + edges |
| Causal claims | Stitched from memory | Edges with confidence 0–1 + evidence text |
| Provenance | None inline | Source attributions per event |
| Pattern matching | Ad hoc | Named insight patterns reusable across queries |
| Token cost | High (verbose prose) | Low (compact JSON, no redundant fields) |
| Multi-hop reasoning | Implicit, opaque | Explicit BFS over the graph |
| Tool | What it does | When to call it |
|---|---|---|
query_events |
Search events by time / domain / impact / free text | You need historical context for a topic, era, or domain |
causal_chain |
BFS up/down the causal graph from a root event | You need to understand why something happened, or what it enabled |
historical_resonance |
Find historical patterns parallel to a present-day situation | You're reasoning about a current trend and want analogies with predictive value |
org_knowledge |
(Enterprise tier) Query an organization's private CKG | Working inside an enterprise namespace with private events configured |
predict_scenarios |
Generate scenario branches from current conditions + historical patterns | Strategic planning, stress-testing assumptions, risk assessment |
In Claude Code these surface as mcp__causari__causal_chain (and similar), depending on the IDE's prefixing convention.
{
"mcpServers": {
"causari": { "command": "npx", "args": ["-y", "@causari/mcp-server"] }
}
}Add to .mcp.json (Claude Code project or ~/.claude/mcp.json global) or ~/.cursor/mcp.json (Cursor).
Point directly to the hosted Cloudflare Worker — nothing to install or run locally:
{
"mcpServers": {
"causari": {
"url": "https://causari-mcp.huydv.workers.dev/mcp"
}
}
}Works with any MCP client that supports HTTP transport (Claude Desktop, Cursor, Windsurf, etc.).
git clone https://github.com/causari/mcp-server
cd mcp-server
pnpm install && pnpm build{
"mcpServers": {
"causari": {
"command": "node",
"args": ["/path/to/mcp-server/dist/cli.js"]
}
}
}In Claude Code:
Use the causari
causal_chaintool to trace what led to the Transformer architecture, depth 3.
You should see a structured response with nodes, confidence scores, and an evidence chain — not just prose.
{
"root": { "id": "transformer", "title": "Transformer Architecture", "year": "2017" },
"causes": [
{
"id": "turing_m", "title": "Turing Machine", "year": "1950", "hop": 1,
"relationship": "enabled", "confidence": 0.8,
"evidence": "Computational substrate for all neural architectures traces to Turing-complete machines."
},
{
"id": "mcculloch_pitts", "title": "McCulloch-Pitts Neuron", "year": "1943", "hop": 2,
"relationship": "enabled", "confidence": 0.9,
"evidence": "First formal model of artificial neurons; the foundational abstraction."
}
],
"relatedPatterns": [
{
"pattern": "Substrate Substitution",
"description": "A capability historically running on substrate A migrates to substrate B once B becomes cheaper or more flexible.",
"predictiveValue": 0.78
}
]
}Matches Information Democratization Cycle (predictive value 0.85), with exemplars spanning Language → Writing → Printing Press → Internet → Transformers — giving the agent a calibrated historical scaffold to reason from.
This is honest reporting, not marketing copy.
Current data depth (as of 2026-05-18):
- 245 events across 9 verticals: AI history, computing, web ecosystem, cloud/devops, databases, AI/ML tooling, security, mobile, and civilizational foundations
- 457 causal links with evidence text + confidence scores calibrated per-link
- 8 insight patterns (Abstraction Layer Migration, Standardization Cycle, Open vs Proprietary, Information Democratization Cycle, and more)
Strong coverage: Queries like causal_chain("docker"), causal_chain("reactjs"), causal_chain("jwt"), or historical_resonance("microservices vs monolith") return dense causal chains with evidence. Dev-term hit rate validated at 10/10.
Honest limitations:
- Confidence scores are curator estimates, not statistical posteriors.
predict_scenariosis pattern-matching over the historical record, not probabilistic forecasting. Treat output as structured hypotheses, not predictions.- Coverage outside the 9 current verticals is thinner. See causari/causari-data to request or contribute new verticals.
Roadmap:
- ✅ Hosted HTTP endpoint (
causari-mcp.huydv.workers.dev) — Cloudflare Worker, stateless - 🔜 API key + rate limiting — Pro tier
- 🔜 Embedding-based resonance — replace lexical match with semantic similarity
- 🔜 Org/Personal scope — user-curated private CKG via enterprise tier
npm run build
node dist/smoke.jsExpected: PASS: 10/10 with a sample causal chain printed. The smoke covers tool registration, query correctness on known events, and edge cases (missing event, depth cap).
┌───────────────────────────────────────────┐
│ AI Agent (Claude Code, Cursor, Windsurf) │
└──────┬──────────────────┬─────────────────┘
│ stdio (local) │ HTTP/SSE (hosted)
▼ ▼
┌──────────────┐ ┌─────────────────────────┐
│ cli.ts │ │ worker.ts │
│ (npx local) │ │ (Cloudflare Worker) │
└──────┬───────┘ └────────────┬────────────┘
│ │
└──────────┬────────────┘
▼
┌──────────────────────────────┐
│ server.ts / tools.ts │
│ - 5 tool definitions │ ← output shaping, token-efficiency
│ - MCP request handlers │
└──────────────┬───────────────┘
│ imports
▼
┌──────────────────────────────┐
│ @causari/ckg │
│ - types │ ← schema (Event, CausalLink, Insight)
│ - store │ ← in-memory + adjacency indexes
│ - query │ ← BFS, search, resonance, scenarios
│ - seed (9 verticals) │ ← 245 events, 457 links, 8 patterns
└──────────────────────────────┘
Token-efficiency note: tool outputs drop redundant fields and inline relationship + evidence so the LLM doesn't have to re-query for context. Confidence + provenance is surfaced so the model can communicate uncertainty honestly to the user.
The seed dataset is open under CC-BY-SA 4.0 in the causari/causari-data repo. See its CONTRIBUTING.md for event/link submission guidelines.
For server code contributions, file issues or PRs here.
This package is dual-licensed (see NOTICE):
- Server code — MIT (see
LICENSE). - Bundled Causal Knowledge Graph data (events, causal links, insight patterns compiled into
dist/) — CC-BY-SA 4.0. Reuse of the data — including extracting it from this package — requires attribution and share-alike, even though it ships inside this MIT-licensed package. The MIT code license does not relicense the data. Source dataset:causari/causari-data.
- Causari Powflow Canvas — the same CKG, visualized for humans
- Architecture decisions are documented internally in the Causari monorepo
- Model Context Protocol — the open standard this server implements