v3.1.0 M6 Phase B: Scan decisions written since this IDE
AI agents call consensus_check to retrieve information from Codevira MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to query or inspect decisions and consensus state that have been recorded since a particular session, consistent with the server's documented purpose of maintaining a shared knowledge base. The action is inspection/retrieval of data with no side effects.
From the tool's definition Tool name is 'consensus_check' with description 'Scan decisions written since this IDE' — the verb 'scan' and 'check' indicate a passive read operation that retrieves or queries existing decision data without modifying, executing, or destructing anything.
Documented attack patterns abuse exactly the kind of access consensus_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codevira MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for consensus_check:
{
"version": "1",
"default": "deny",
"tools": {
"consensus_check": {}
}
}consensus_check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
v3.1.0 M6 Phase B: Scan decisions written since this IDE. It is categorised as a Read tool in the Codevira MCP MCP Server, which means it retrieves data without modifying state.
Register the Codevira MCP server in PolicyLayer and add a rule for consensus_check: 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 Codevira MCP. Nothing to install.
consensus_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the consensus_check 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 consensus_check. 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.
consensus_check is provided by the Codevira MCP server (sachinshelke/codevira). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codevira 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.
48 Codevira MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.