build_evidence_pack
Composes a session receipt (build_session_receipt logic), an optional §27.6 HA evidence bundle (ha_bundle_export logic, included only when ha_records is supplied and non-empty), and a disclosure manifest (build_disclosure_manifest logic) from one array of already-produced artifacts, all keyed to ...
This record as markdown: /tools/postoaklabs-ainumbers-mcp-apps/build-evidence-pack.md
What build_evidence_pack does on Ainumbers Mcp Apps
AI agents invoke build_evidence_pack to trigger actions in Ainumbers Mcp Apps. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
sd_jwt | boolean | — | When true, also return an SD-JWT export of the HA bundle (mirrors ha_bundle_export, default false; no-op when ha_records is absent). |
framing | string | — | Optional framing context for the session receipt's PTG-01 regulator prompt. |
artifacts | array | Yes | Already-produced artifacts this pack documents, in call order. |
ha_records | array | — | §27 human_accountability_records -- omit entirely for no HA section. |
room_label | string | — | Label for the disclosure-manifest room. |
session_id | string | — | Session identifier to embed in the receipt, if the caller tracks one. |
subject_hash | string | — | The sha256: subject hash the pack documents (defaults to artifacts[0].execution_hash if omitted). |
decision_trail | array | — | Per-step decision reason trail from the run_chain result (pass its decision_trail — response field or composite_output.decision_trail). Carried verbatim into th |
kernel_version | string | — | Version tag of the kernel that produced verification_result. |
policy_version | string | — | Version tag of the policy the kernel was evaluated against. |
submission_receipt | string | — | Populate ONLY after a real transmission -- never fabricate (same rule as ha_bundle_export). |
verification_result | string | — | The §16/§18/§20 verdict. |
Parameters from the server's own tool schema.
Why build_evidence_pack is rated High
build_evidence_pack triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsHigh parameter count (23 properties)
Attacks that exploit this kind of access
The rule that runs build_evidence_pack safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ainumbers Mcp Apps, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For build_evidence_pack, this is the rule to start with:
build_evidence_pack stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ainumbers Mcp Apps, apply this rule, and every build_evidence_pack call is checked against it from then on.
Questions about build_evidence_pack
Composes a session receipt (build_session_receipt logic), an optional §27.6 HA evidence bundle (ha_bundle_export logic, included only when ha_records is supplied and non-empty), and a disclosure manifest (build_disclosure_manifest logic) from one array of already-produced artifacts, all keyed to the same input hashes -- replacing what today takes 4-6 separate tool calls with hand-carried hashes. Calls the same in-process functions those standalone tools use; if any one section fails to build, the whole call fails isError:true with that section's own message -- no partial pack. Optionally carries a run_chain decision_trail (per-step reason codes: gate rule id, escalation rule id, input_required cause) as pack-level metadata so an auditor-facing pack answers "why did each step happen" without a second round-trip. It is categorised as a Execute tool in the Ainumbers Mcp Apps MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
build_evidence_pack accepts 12 parameters: sd_jwt, framing, artifacts, ha_records, room_label, session_id, subject_hash, decision_trail, kernel_version, policy_version, submission_receipt, verification_result. Required: artifacts. The full parameter table on this page comes from the server's own tool schema.
Register the Ainumbers Mcp Apps MCP server in PolicyLayer and add a rule for build_evidence_pack: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ainumbers Mcp Apps. Nothing to install.
build_evidence_pack is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the build_evidence_pack rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for build_evidence_pack. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
build_evidence_pack is provided by the Ainumbers Mcp Apps MCP server (postoaklabs/ainumbers-mcp-apps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ainumbers Mcp Apps, and thousands of servers like it.
Across the catalogue