> Source: https://vitna.ai/docs/api/v1/engine/mcp
> Raw Markdown: https://vitna.ai/docs/api/v1/engine/mcp.md
> Corpus index: https://vitna.ai/llms.txt
# Model Context Protocol (MCP)
Keyless Streamable HTTP MCP endpoint (`2025-03-26` and `2024-11-05`) exposing
ten read-only and zero-retention tools over Vitna's first-party Witness market
record, provider compliance terms, three-provenance SKU capabilities,
cryptographic citations, stack decision engine, rollout watchdog, compound
pipeline analyzer, and offline audit pack verifier.
## Server discovery
```
GET /api/v1/mcp
```
Returns the server descriptor and tool schemas as cacheable JSON.
```json
{
"serverInfo": {
"name": "vitna-mcp",
"version": "1.0.0"
},
"protocolVersion": "2025-03-26",
"transport": "streamable-http",
"endpoint": "/api/v1/mcp",
"tools": [
{
"name": "vitna_check_quote",
"description": "Evaluate a vendor AI pricing quote in memory against Witness list prices and peer spreads with zero retention.",
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
},
"inputSchema": { ... }
}
],
"meta": {
"generatedAt": "2026-11-02T00:00:00.000Z",
"source": "snapshot",
"count": 10
}
}
```
## JSON-RPC 2.0 Streamable HTTP calls
```
POST /api/v1/mcp
```
Accepts standard MCP JSON-RPC 2.0 methods (`initialize`,
`notifications/initialized`, `ping`, `tools/list`, and `tools/call`) with zero
authentication required.
Available tools:
- `vitna_check_quote` - evaluate a vendor quote against Witness list prices and peer spreads
- `vitna_get_market_tape` - read current Witness list prices by component class and provider
- `vitna_get_sku_history` - inspect append-only price period history for a SKU
- `vitna_get_provider_terms` - read curated provider retention, training, region, and BYOK terms
- `vitna_cite_observation` - resolve an observation ID into its SHA-256 evidence digest and copy-ready citation strings
- `vitna_get_sku_capabilities` - inspect a Witness SKU's three-provenance capability and runtime speed profile
- `vitna_decide_stack` - run a stateless, zero-retention stack migration evaluation
- `vitna_check_rollout` - evaluate standing-decision drift, shadow rule promotion readiness, and routed canary health with zero retention
- `vitna_analyze_pipeline` - compute a multi-stage, multi-class AI pipeline Bill of Materials, trace fan-out attribution, and spend optimization with zero retention
- `vitna_verify_audit_pack` - verify a `vitna.audit-pack.v1` procurement, FinOps, and governance attestation pack across all six layers or assemble one inline with zero retention
```bash
curl -X POST https://vitna.ai/api/v1/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "vitna_check_quote",
"arguments": {
"sku": "gpt-5.4",
"quotedAmountUsd": 2.10,
"dimension": "input_per_mtok"
}
}
}'
```