Extract entities and relationships from natural language text using an LLM, then store them in the knowledge graph. Requires an LLM provider (CEREBRAS_API_KEY or OPENROUTER_API_KEY). Use this to remember information from conversations, documents, or any unstructured text.
AI agents use store_fact 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.
The tool extracts entities and relationships from text and writes them into a knowledge graph. This is a reversible write operation (facts can be removed/decayed), not destructive. Misuse could pollute the knowledge graph with false or misleading facts, giving it medium severity.
From the tool's definition 'store them in the knowledge graph' and 'Use this to remember information from conversations, documents, or any unstructured text'
Documented attack patterns abuse exactly the kind of access store_fact 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_fact:
{
"version": "1",
"default": "deny",
"tools": {
"store_fact": {
"limits": [
{
"counter": "store_fact_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}store_fact 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.
Extract entities and relationships from natural language text using an LLM, then store them in the knowledge graph. Requires an LLM provider (CEREBRAS_API_KEY or OPENROUTER_API_KEY). Use this to remember information from conversations, documents, or any unstructured text. 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_fact: 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_fact 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_fact 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_fact. 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_fact 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.