Store an entity in the knowledge graph. Deduplicates by text+type — if an entity with the same text and type exists, it is updated instead of duplicated.
AI agents use store_entity to create or update resources in CodeGraph — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CodeGraph environment.
This tool creates or updates entities in the knowledge graph. It is reversible in the sense that data can be modified or overwritten, but does not irreversibly delete. The 'updated instead of duplicated' behavior confirms it can overwrite existing data, placing it firmly in Write. Misuse could corrupt knowledge graph state, hence medium severity.
From the tool's definition Store an entity in the knowledge graph. Deduplicates by text+type — if an entity with the same text and type exists, it is updated instead of duplicated.
Documented attack patterns abuse exactly the kind of access store_entity gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraph, and nothing reaches the server without passing your rules. This is the rule we recommend for store_entity:
{
"version": "1",
"default": "deny",
"tools": {
"store_entity": {
"limits": [
{
"counter": "store_entity_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}store_entity 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.
Store an entity in the knowledge graph. Deduplicates by text+type — if an entity with the same text and type exists, it is updated instead of duplicated. It is categorised as a Write tool in the CodeGraph MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CodeGraph MCP server in PolicyLayer and add a rule for store_entity: 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 CodeGraph. Nothing to install.
store_entity 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 store_entity 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 store_entity. 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.
store_entity is provided by the CodeGraph MCP server (phoenixrr2113/codebase-graph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraph, 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.
18 CodeGraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.