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 Exchange results.
Use this page when building external tools, agentic clients, or automation around the same Source Shares state that Terminal reads.
After reading
You can design an MCP or API interaction that mirrors Terminal write/read/proof discipline.
Bitcode MCP is a connected Exchange interface
MCP tools should expose current Bitcode actions and reads: attach source, express Read, admit AssetPack intent, read activity, inspect proof posture, and return write-admission evidence.
The MCP surface should be narrow and explicit. Non-admitted generic tools are support or reference surfaces until the Protocol, Exchange, and Terminal can read their effects.
Why this matters
MCP makes Bitcode programmable, but programmability is only valuable if it keeps source-to-shares proof parity.
- Tool calls must be confirmation-gated when they write.
- Tool results must point back to Exchange-readable activity.
- PromptPart and attachment structures preserve source and Read context.
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 Exchange state.
Docs for MCP should therefore teach request shape, expected result, failure posture, and which Terminal read confirms the write.
Why this matters
This mirrors the Terminal action manual for external developers and agentic clients.
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 AssetPack source. Source-bearing AssetPack 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 Source Shares 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 AssetPack source.
- Docs QA fails closed when public docs, internal docs, route docs, interface docs, generated artifacts, proof posture, or workflow checks drift.
- Deferred boundaries stay explicit: V35 documents Exchange and Conversations usage while deeper product depth remains future-canon work.