workflow_conditional_step
Evaluate a condition against the stepResults argument and execute one of two tool branches. Supports built-in predicates: always_true, always_false, any_step_failed, success_rate_gte_N (N=0-100), variable_equals_KEY_VALUE, variable_contains_KEY_VALUE, variable_matches_KEY_REGEX, plus history-driv...
This record as markdown: /tools/io-github-vmoranv-jshookmcp/workflow-conditional-step.md
What workflow_conditional_step does on Jshookmcp
AI agents invoke workflow_conditional_step to trigger actions in Jshookmcp. 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.
Why workflow_conditional_step is rated High
Conditionally executes arbitrary tool branches based on evaluated predicates, allowing workflow logic control with potential side effects.
From the tool's definition Evaluate condition, execute tool branches, supports predicates
Attacks that exploit this kind of access
The rule that runs workflow_conditional_step safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Jshookmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For workflow_conditional_step, this is the rule to start with:
workflow_conditional_step 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 Jshookmcp, apply this rule, and every workflow_conditional_step call is checked against it from then on.
Questions about workflow_conditional_step
Evaluate a condition against the stepResults argument and execute one of two tool branches. Supports built-in predicates: always_true, always_false, any_step_failed, success_rate_gte_N (N=0-100), variable_equals_KEY_VALUE, variable_contains_KEY_VALUE, variable_matches_KEY_REGEX, plus history-driven predicates history_failure_rate_gte_N / history_failure_rate_lte_N, last_run_failed[:workflowId], recent_steps_failing_L[:workflowId], history_fallback_rate_gte_N / history_fallback_rate_lte_N. History predicates read the workflow run store (the last 10 runs of the workflow named by the :workflowId suffix, or the current workflow when none is given); they evaluate false when no history exists. When stepResults is omitted, an empty set is used, so value-based predicates (variable_*, success_rate_gte_N, any_step_failed) will not match. It is categorised as a Execute tool in the Jshookmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Jshook MCP server in PolicyLayer and add a rule for workflow_conditional_step: 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 Jshookmcp. Nothing to install.
workflow_conditional_step 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 workflow_conditional_step 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 workflow_conditional_step. 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.
workflow_conditional_step is provided by the Jshook MCP server (@jshookmcp/jshook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Jshook, and thousands of servers like it.
Across the catalogue