Independently verify a ChainGraph artifact (ChainGraph Standard v0.1 §6). Recomputes SHA-256 over the canonical (sorted-key, whitespace-stripped) JSON of policy_parameters + output_payload and compares it to the claimed execution_hash. A match proves the artifact's stated inputs deterministically...
AI agents call verify_execution_hash to retrieve information from Ainumbers Mcp Apps without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
artifact | object | — | A full ChainGraph artifact envelope (must contain policy_parameters, output_payload, and execution_hash). |
claimed_hash | string | — | The execution_hash to check against (if not passing a full artifact). |
output_payload | object | — | Artifact output_payload (if not passing a full artifact). |
policy_parameters | object | — | Artifact policy_parameters (if not passing a full artifact). |
Parameters from the server's own tool schema.
This tool retrieves and validates existing data (artifacts and their hashes) through deterministic cryptographic comparison. It has no side effects, makes no modifications, triggers no external operations, and stores nothing. The verification is purely computational and informational, making it a Read operation with minimal risk even if misused by an agent.
From the tool's definition Tool description explicitly states it "Recomputes SHA-256" and "compares it to the claimed execution_hash" to "verify" and "proves" outputs. The phrase "Pure client-safe compute -- no data is stored" confirms read-only verification.
Attacks that exploit this kind of access
Independently verify a ChainGraph artifact (ChainGraph Standard v0.1 §6). Recomputes SHA-256 over the canonical (sorted-key, whitespace-stripped) JSON of policy_parameters + output_payload and compares it to the claimed execution_hash. A match proves the artifact's stated inputs deterministically produce its stated outputs. Pass either a full artifact object, or policy_parameters + output_payload + claimed_hash. Pure client-safe compute -- no data is stored. Use this to verify artifacts from any vendor that conforms to the ChainGraph Standard. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
verify_execution_hash accepts 4 parameters: artifact, claimed_hash, output_payload, policy_parameters. 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 verify_execution_hash: 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.
verify_execution_hash 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 verify_execution_hash 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 verify_execution_hash. 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.
verify_execution_hash 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →