Use when: starting a session, tracking progress, logging decisions, setting goals, checking scope health, running structured workflows. Your game dev AI assistant — project state, decisions, goals, milestones, scope health, session orchestration. Adapts to your genre and phase. Actions: hello, ge...
AI agents use project to create or update resources in GameCodex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GameCodex environment.
This tool creates and modifies project metadata, goals, milestones, and session state. While reversible (goals can be cleared, decisions overwritten, features potentially removed), it persistently alters project tracking data. It does not execute code, delete irreversibly, or involve financial transactions, placing it in Write.
From the tool's definition Actions include 'set', 'add_feature', 'note', 'milestone', 'decide', 'goal', 'complete_goal', and 'session' — all state-modifying operations.
Attacks that exploit this kind of access
Use when: starting a session, tracking progress, logging decisions, setting goals, checking scope health, running structured workflows. Your game dev AI assistant — project state, decisions, goals, milestones, scope health, session orchestration. Adapts to your genre and phase. Actions: hello, get, set, suggest, decide, goal, complete_goal, clear_goals, milestone, note, recall, health, scope, add_feature, list, session. It is categorised as a Write tool in the GameCodex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GameCodex MCP server in PolicyLayer and add a rule for project: 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 GameCodex. Nothing to install.
project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the project 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 project. 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.
project is provided by the GameCodex MCP server (wesleysalzer/gamecodex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →