AI agents use add_knowledge to create or update resources in Mcp Graph Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Graph Engine environment.
This tool modifies the graph by ingesting new knowledge through a domain-specific language, which is a write operation. Severity is medium because while it can introduce incorrect or malicious relationships into the knowledge graph, the effects are reversible (can be deleted via delete_graph or by removing specific facts). It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool name 'add_knowledge' combined with description 'Add knowledge using text DSL' indicates the tool creates or modifies data in the graph database. The DSL format suggests structured data input that persists in the graph.
Documented attack patterns abuse exactly the kind of access add_knowledge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Graph Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for add_knowledge:
{
"version": "1",
"default": "deny",
"tools": {
"add_knowledge": {
"limits": [
{
"counter": "add_knowledge_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_knowledge 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.
Add knowledge using text DSL. Format:. It is categorised as a Write tool in the Mcp Graph Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Graph Engine MCP server in PolicyLayer and add a rule for add_knowledge: 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 Mcp Graph Engine. Nothing to install.
add_knowledge 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 add_knowledge 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 add_knowledge. 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.
add_knowledge is provided by the Mcp Graph Engine MCP server (utilitydelta/mcp-graph-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Graph Engine, 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.
24 Mcp Graph Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.