Arc Fit Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Output feeds: art-43-arc-cpn-model, art-44-arc-stablefx-model, art-45-arc-xreserve-linter, art-46...
AI agents invoke run_arc_fit_diagnostic 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 |
|---|---|---|---|
compute | string | — | Compute mode (v0.4 Compute Binding). "auto" (default) = server for gpu:false nodes with registered kernels; "server" = force server-side; "browser" = always ret |
parent_hashes | array | — | execution_hash values from upstream ChainGraph AP2 artifacts to chain from (sets chain.parent_hashes in the export). |
parent_tool_ids | array | — | tool_id values matching parent_hashes, in the same order. |
policy_parameters | object | — | Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is "auto" or "serv |
Parameters from the server's own tool schema.
The 'run_' verb combined with 'Runs deterministically' indicates this tool executes code/logic rather than merely retrieving data. Although the server claims zero PII and no auth, the execution of compute nodes that generate chain provenance artifacts and feed multiple downstream systems constitutes Execute-category risk.
From the tool's definition Tool name contains 'run_' prefix and description states it 'Runs deterministically in-browser' and 'Runs' an Arc Fit Diagnostic compute node.
Attacks that exploit this kind of access
Arc Fit Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Output feeds: art-43-arc-cpn-model, art-44-arc-stablefx-model, art-45-arc-xreserve-linter, art-46-arc-paymaster-model, art-47-arc-cctp-transfer. Open at: https://ainumbers.co/chaingraph/art-42-arc-fit-diagnostic.html. 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.
run_arc_fit_diagnostic accepts 4 parameters: compute, parent_hashes, parent_tool_ids, 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 run_arc_fit_diagnostic: 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.
run_arc_fit_diagnostic 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 run_arc_fit_diagnostic 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 run_arc_fit_diagnostic. 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.
run_arc_fit_diagnostic 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 →