run_chain
Executes every step of a named chain (list names with find_chain / build_workflow_links) and returns ONE composite artifact whose execution_hash anchors all step outputs. compute:"server"/"auto" (default) runs each kernel-backed step server-side, threading step N's execution_hash into step N+1's ...
This record as markdown: /tools/postoaklabs-ainumbers-mcp-apps/run-chain.md
What run_chain does on Ainumbers Mcp Apps
AI agents invoke run_chain 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 |
|---|---|---|---|
chain | string | Yes | Chain name, e.g. "agent-commerce-conformance". List names with find_chain or build_workflow_links. |
inputs | object | — | Map of step tool_id -> policy_parameters overrides. Omitted steps run with {} (kernels needing required fields are reported, not failed silently). |
compute | string | — | "auto"/"server" (default) runs kernel-backed steps server-side; "browser" returns a zero-egress delegation bundle to run client-side. |
mandate | object | — | Optional §22 Work Mandate artifact. When supplied: §16 signature is verified and validity window is checked (unsigned/bad-sig/expired returns a structured error |
escalation_transport | string | — | How an OCG §22.8 escalation is delivered. "resolve_handle" (DEFAULT) never blocks: the run COMPLETES with status "escalated" plus the open record, its record_ha |
Parameters from the server's own tool schema.
Why run_chain is rated High
The tool triggers execution of multi-step workflows with server-side computation (compute:"server" option), threading execution state between steps. While described as part of a fintech system with read-only characteristics at the server level, run_chain itself performs active execution of chained operations whose effects depend on the chain configuration and input parameters supplied.
From the tool's definition Tool description states "Executes every step of a named chain" and "runs each kernel-backed step server-side", indicating execution of complex operations with server-side computation and state threading across multiple steps.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs run_chain 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 run_chain, this is the rule to start with:
run_chain 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 run_chain call is checked against it from then on.
Questions about run_chain
Executes every step of a named chain (list names with find_chain / build_workflow_links) and returns ONE composite artifact whose execution_hash anchors all step outputs. compute:"server"/"auto" (default) runs each kernel-backed step server-side, threading step N's execution_hash into step N+1's parent_hashes; compute:"browser" returns a zero-egress delegation bundle (composer URL + ordered deep-links) to run client-side instead — no data leaves the agent. Supply inputs as a map of step tool_id -> policy_parameters (field names per node manifest / build_chaingraph); a step whose kernel needs inputs you omit is reported per-step (status "input_required"), never failed silently. Steps that are browser-only (gpu:true or no registered kernel) are listed for browser delegation. Deterministic, zero PII, zero payload logging. Verify the result with verify_execution_hash. Response includes a ledger_url fragment link for human verification at ledger.ainumbers.co. 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_chain accepts 5 parameters: chain, inputs, compute, mandate, escalation_transport. Required: chain. 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_chain: 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_chain 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_chain 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_chain. 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_chain 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