Medium Risk

create_source

This tool help create a connector from data source to unstructured server where will be processed

How to control create_source ↓

What create_source does on Daraja MCP

AI agents use create_source to create or update resources in Daraja MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Daraja MCP environment.

Medium Risk

Why create_source needs a policy

This tool creates a new connector/configuration resource, which is a reversible write operation. While the server context involves financial transactions (Daraja/M-Pesa), this specific tool appears to create a data source connector rather than move money or commit financial obligations. The vague description lowers confidence, but the 'create' verb and connector setup nature place it in Write rather than Execute.

From the tool's definition Tool description states it 'create a connector from data source to unstructured server where will be processed' - the word 'create' indicates data structure modification. However, the description is vague about what exactly is being created and stored.

Documented attack patterns abuse exactly the kind of access create_source gives an agent:

How to control create_source

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 create_source:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_source": {
      "limits": [
        {
          "counter": "create_source_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_source stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Daraja MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_source

What does the create_source tool do? +

This tool help create a connector from data source to unstructured server where will be processed. It is categorised as a Write tool in the Daraja MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_source? +

Register the Daraja MCP server in PolicyLayer and add a rule for create_source: 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.

What risk level is create_source? +

create_source is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_source? +

Yes. Add a rate_limit block to the create_source 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.

How do I block create_source completely? +

Set action: deny in the PolicyLayer policy for create_source. 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.

What MCP server provides create_source? +

create_source 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.

Enforce policy on every Daraja MCP tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.