codex_dispatch
Run formal Codex PM through local Codex OAuth/session with bounded dispatch receipts.
This record as markdown: /tools/io-github-nograai-nogra-mcp/codex-dispatch.md
What codex_dispatch does on Nogra
AI agents invoke codex_dispatch to trigger actions in Nogra. 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 codex_dispatch is rated High
This tool executes a formal process (Codex PM) through an OAuth/session mechanism, which constitutes triggering an external operation. The execution is bounded (mitigating risk to some degree) but remains an Execute action because it runs code/operations whose effects depend on context.
From the tool's definition Tool description states "Run formal Codex PM" and "dispatch" suggests triggering external operations. The phrase "bounded dispatch receipts" indicates the tool executes actions with measurable effects that are recorded.
Attacks that exploit this kind of access
The rule that runs codex_dispatch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nogra, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For codex_dispatch, this is the rule to start with:
codex_dispatch 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 Nogra, apply this rule, and every codex_dispatch call is checked against it from then on.
Questions about codex_dispatch
Run formal Codex PM through local Codex OAuth/session with bounded dispatch receipts. It is categorised as a Execute tool in the Nogra MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nogra MCP server in PolicyLayer and add a rule for codex_dispatch: 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 Nogra. Nothing to install.
codex_dispatch 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 codex_dispatch 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 codex_dispatch. 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.
codex_dispatch is provided by the Nogra MCP server (@nograai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nogra, and thousands of servers like it.
This server
Across the catalogue