build_session_receipt
Aggregates execution_hashes from N ChainGraph tool calls in one agent session into a single SHA-256 Merkle root (session_receipt_root). Returns a tamper-evident session receipt and a regulator-framed PTG-01 audit prompt. One receipt covers an entire agent session: supply all execution_hashes in c...
This record as markdown: /tools/postoaklabs-ainumbers-mcp-apps/build-session-receipt.md
What build_session_receipt does on Ainumbers Mcp Apps
AI agents call build_session_receipt to retrieve information from Ainumbers Mcp Apps without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
framing | string | — | Optional framing context for the PTG-01 regulator prompt (e.g. "DORA incident review" or "EU AI Act Art.12 transparency log"). |
tool_ids | array | — | tool_id values corresponding to execution_hashes, in the same order. Used for the audit narrative. |
session_id | string | — | Optional agent session identifier for the audit narrative (e.g. a UUID or timestamp). |
prior_receipt | object | — | An earlier receipt from this SAME session (its mmr_peaks/mmr_size/mmr_bagged_root). When supplied, execution_hashes MUST start with that earlier receipt's full |
execution_hashes | array | Yes | Ordered list of execution_hash values from ChainGraph tool calls in this session (each produced by emit_chaingraph_artifact or a kernel tool). Minimum 1. |
Parameters from the server's own tool schema.
Why build_session_receipt is rated Low
This tool performs a purely computational/aggregation operation: it takes a list of execution hashes and produces a deterministic SHA-256 Merkle root plus an audit prompt. There are no side effects, no data written, no external calls triggered, and no destructive or financial actions. It is a read/compute-only tool consistent with the server description of 'Read-only, no auth, zero PII.'
From the tool's definition Aggregates execution_hashes into a single SHA-256 Merkle root... deterministic — the same hashes in the same order always produce the same root. Read-only, no auth, zero PII.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs build_session_receipt 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_session_receipt, this is the rule to start with:
build_session_receipt is read-only, so it stays allowed. 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_session_receipt call is checked against it from then on.
Questions about build_session_receipt
Aggregates execution_hashes from N ChainGraph tool calls in one agent session into a single SHA-256 Merkle root (session_receipt_root). Returns a tamper-evident session receipt and a regulator-framed PTG-01 audit prompt. One receipt covers an entire agent session: supply all execution_hashes in call order. The Merkle root is deterministic — the same hashes in the same order always produce the same root. Compliant with EU AI Act Art. 12 (transparency) and DORA ICT audit-trail requirements. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
build_session_receipt accepts 5 parameters: framing, tool_ids, session_id, prior_receipt, execution_hashes. Required: execution_hashes. 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_session_receipt: 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_session_receipt is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the build_session_receipt 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_session_receipt. 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_session_receipt 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.
This server
Across the catalogue