04 / Commercial InterfacesMCP/API
Operate Bitcode through MCP and API surfaces
MCP/API docs explain how programmable clients should attach context, write bounded intent, receive admission evidence, and reread proof-backed results.
Use this page when building external tools, agentic clients, or automation around the same DataPack state that product routes read.
After reading
You can design an MCP or API interaction that mirrors route write/read/proof discipline.
Bitcode MCP is a connected proof-readback interface
MCP exposes exactly eight product tools: measure, synthesize-asset-packs-for-deposit, synthesize-asset-packs-for-reads, packs, and four Auxillaries panes.
Keep the MCP surface narrow and explicit. Deposit/Read synthesize mirror website Synthesize DataPacks (obfuscations vs Need). Measure returns source-safe evidence. Packs and Auxillaries reread product posture.
Why this matters
Programmability only helps when it preserves DataPack proof parity with product routes.
- synthesize-asset-packs-for-deposit requires obfuscations configuration (empty allowed).
- synthesize-asset-packs-for-reads requires Need configuration.
- measure returns source-safe measurement evidence only.
- packs and auxiliary-* tools point at Packs/Auxillaries product routes.
- Writes are confirmation-gated; results point back to Packs-readable activity.
The API contract is write, reread, and prove
A useful API action writes bounded intent, returns admission evidence, and gives the caller a way to reread the resulting proof-backed activity state.
Docs for MCP therefore teach request shape, expected result, failure posture, and which proof readback confirms the write.
Why this matters
This mirrors the action manual for external developers and agentic clients.
Public docs expose guidance and proof posture, not protected source
MCP and public docs may describe tool names, schemas, measurements, and proof roots. They must not serialize protected source, unpaid DataPack source, credentials, or wallet private material.
When a measure or synthesize call returns roots and source-safe summaries, treat those as the admissible public surface.
Why this matters
Source-safety is protocol law on every interface, including MCP.
Public docs expose guidance and proof posture, not protected source
Public Bitcode docs derive from the active Protocol, package-owned catalogs, route contracts, and source-safe generated artifacts. They can explain usage, measurements, event ids, proof roots, docs links, runbook links, redaction posture, testnet rollout readiness, fee boundaries, and settlement posture.
They must not reveal protected source payloads, raw protected prompts, secret values, provider tokens, wallet private material, or unpaid DataPack source. Source-bearing DataPack contents cross to the reader only after settlement and rights transfer.
Why this matters
This keeps the public product understandable while preserving the boundary that makes DataPacks economically and operationally safe.
- Allowed: usage guidance, route links, state labels, source-safe measurements, proof roots, dashboard/runbook ids, redacted incident posture, testnet rollout readiness, LocalStagingTelemetryDocumentationRehearsal evidence, and fee/right boundaries.
- Interface docs may surface event ids, proof roots, docs links, runbook links, and redaction posture from TelemetryDocumentationInterfaceIntegration without revealing source-bearing payloads.
- Local and staging-testnet rehearsal docs may surface documentation discovery, telemetry event emission, dashboard/runbook lookup, docs QA, incident drill, source-safe proof-root review, and blocked value-bearing mainnet posture.
- Blocked: secrets, provider tokens, wallet private material, raw protected prompts, protected source payloads, and unpaid DataPack source.
- Docs QA fails closed when public docs, internal docs, route docs, interface docs, generated artifacts, proof posture, or workflow checks drift.
- Compatibility boundaries stay explicit: /exchange redirects to /exchange and does not create a parallel current product surface.