AI agents use board_update_project to create or update resources in Agent Board — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Board environment.
This tool modifies project metadata/fields in a reversible manner. It does not delete data (Destructive), execute arbitrary code (Execute), or handle financial transactions (Financial). While updates could impact workflow coordination across the agent team, the reversible nature and typical scope of project field updates (name, description, status, etc.) classify this as Write severity.
From the tool's definition Tool name 'board_update_project' combined with description 'Update project fields' indicates modification of existing project data. The verb 'update' is characteristic of Write category tools that create or modify data reversibly.
Documented attack patterns abuse exactly the kind of access board_update_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Board, and nothing reaches the server without passing your rules. This is the rule we recommend for board_update_project:
{
"version": "1",
"default": "deny",
"tools": {
"board_update_project": {
"limits": [
{
"counter": "board_update_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}board_update_project 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.
Free to start. No card required.
Update project fields. It is categorised as a Write tool in the Agent Board MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Board MCP server in PolicyLayer and add a rule for board_update_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 Agent Board. Nothing to install.
board_update_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 board_update_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 board_update_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.
board_update_project is provided by the Agent Board MCP server (quentintou/agent-board). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Board, 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.
14 Agent Board tools catalogued and risk-classified — across an index of 43,000+ MCP servers.