AI agents invoke run_workflow to trigger actions in Daraja MCP. 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.
Running a workflow on a financial automation platform (Daraja/M-Pesa) could trigger financial transactions, data writes, or external operations depending on workflow contents. The description is vague, but the server context strongly implies workflows may include financial actions like STK push or fund transfers.
From the tool's definition 'run a workflow' — triggers execution of a pre-defined workflow on a server that handles M-Pesa financial transactions and automation
Documented attack patterns abuse exactly the kind of access run_workflow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Daraja MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"run_workflow": {
"limits": [
{
"counter": "run_workflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_workflow 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.
Free to start. No card required.
This tool help run a workflow. It is categorised as a Execute tool in the Daraja MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Daraja MCP server in PolicyLayer and add a rule for run_workflow: 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 Daraja MCP. Nothing to install.
run_workflow 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_workflow 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_workflow. 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_workflow is provided by the Daraja MCP server (jameskanyiri/darajamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Daraja MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Daraja MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.