Auto-generate context graph nodes for new or unregistered files.
AI agents use refresh_graph to create or update resources in Codevira MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codevira MCP environment.
This tool creates new graph nodes in the knowledge base for files that are not yet registered. This is a Write operation as it creates new data entries in the shared knowledge base. It is not destructive since it targets unregistered files (no overwriting), not Execute since it doesn't run code/commands, and not Read since it modifies state.
From the tool's definition Auto-generate context graph nodes for new or unregistered files
Documented attack patterns abuse exactly the kind of access refresh_graph 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 refresh_graph:
{
"version": "1",
"default": "deny",
"tools": {
"refresh_graph": {
"limits": [
{
"counter": "refresh_graph_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}refresh_graph 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.
Auto-generate context graph nodes for new or unregistered files. It is categorised as a Write tool in the Codevira MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codevira MCP server in PolicyLayer and add a rule for refresh_graph: 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.
refresh_graph 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 refresh_graph 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 refresh_graph. 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.
refresh_graph 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.