Create a new Devin session for code development and post the task to Slack. Note: This is the recommended approach as it will automatically post your task to Slack as @Devin mention. Please craft your request to Devin in the same language that the user is using to communicate with you, maintainin...
AI agents invoke create_devin_session to trigger actions in MCP-Devin. 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.
This tool triggers an external AI agent (Devin) to perform code development tasks and simultaneously posts to Slack. It initiates an autonomous execution session whose effects depend on the arguments (the task provided). This is an external operation/execution trigger, not merely writing data — it spawns an AI agent that can run code, make changes, etc.
From the tool's definition Create a new Devin session for code development and post the task to Slack
Documented attack patterns abuse exactly the kind of access create_devin_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Devin, and nothing reaches the server without passing your rules. This is the rule we recommend for create_devin_session:
{
"version": "1",
"default": "deny",
"tools": {
"create_devin_session": {
"limits": [
{
"counter": "create_devin_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}create_devin_session 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.
Create a new Devin session for code development and post the task to Slack. Note: This is the recommended approach as it will automatically post your task to Slack as @Devin mention. Please craft your request to Devin in the same language that the user is using to communicate with you, maintaining language consistency throughout the experience. It is categorised as a Execute tool in the MCP-Devin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP-Devin MCP server in PolicyLayer and add a rule for create_devin_session: 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 MCP-Devin. Nothing to install.
create_devin_session 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 create_devin_session 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 create_devin_session. 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.
create_devin_session is provided by the MCP-Devin MCP server (kazuph/mcp-devin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-Devin, 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.
5 MCP-Devin tools catalogued and risk-classified — across an index of 43,000+ MCP servers.