Search the NodeSpace knowledge graph using natural language.
AI agents call nodespace_search_semantic to retrieve information from Nodespace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves information from a local knowledge graph without creating, modifying, deleting, or executing external operations. It is a pure read operation with no side effects, matching the Read category definition. Severity is low because misuse would only expose existing project context data without enabling destructive, financial, or code execution impacts.
From the tool's definition Tool performs 'Search the NodeSpace knowledge graph using natural language' — a query operation that retrieves data without modifying it. The server description emphasizes 'query a local knowledge base' for read-only context retrieval.
Documented attack patterns abuse exactly the kind of access nodespace_search_semantic gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nodespace, and nothing reaches the server without passing your rules. This is the rule we recommend for nodespace_search_semantic:
{
"version": "1",
"default": "deny",
"tools": {
"nodespace_search_semantic": {}
}
}nodespace_search_semantic 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.
Search the NodeSpace knowledge graph using natural language. It is categorised as a Read tool in the Nodespace MCP Server, which means it retrieves data without modifying state.
Register the Nodespace MCP server in PolicyLayer and add a rule for nodespace_search_semantic: 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 Nodespace. Nothing to install.
nodespace_search_semantic 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 nodespace_search_semantic 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 nodespace_search_semantic. 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.
nodespace_search_semantic is provided by the Nodespace MCP server (nodespaceai/nodespace-core). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nodespace, 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.
5 Nodespace tools catalogued and risk-classified — across an index of 43,000+ MCP servers.