Graph analysis for decision networks. Computes PageRank (most influential decisions), Louvain communities (clusters of related decisions), bottlenecks (blocking nodes), and critical path. Use for dependency analysis, project planning, or understanding decision impact chains.
AI agents call analyze_decision_graph to retrieve information from Oraclaw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool analyzes and queries properties of a decision graph to extract information (influence metrics, clusters, bottlenecks, critical paths). No data creation, modification, deletion, or external execution occurs. The operations are read-only analytical computations typical of graph analysis libraries.
From the tool's definition Tool performs graph analysis and computation operations: 'Computes PageRank', 'Louvain communities', 'bottlenecks', and 'critical path' on existing decision networks.
Documented attack patterns abuse exactly the kind of access analyze_decision_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Oraclaw, and nothing reaches the server without passing your rules. This is the rule we recommend for analyze_decision_graph:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_decision_graph": {}
}
}analyze_decision_graph 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.
Graph analysis for decision networks. Computes PageRank (most influential decisions), Louvain communities (clusters of related decisions), bottlenecks (blocking nodes), and critical path. Use for dependency analysis, project planning, or understanding decision impact chains. It is categorised as a Read tool in the Oraclaw MCP Server, which means it retrieves data without modifying state.
Register the Oraclaw MCP server in PolicyLayer and add a rule for analyze_decision_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 Oraclaw. Nothing to install.
analyze_decision_graph 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 analyze_decision_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 analyze_decision_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.
analyze_decision_graph is provided by the Oraclaw MCP server (@oraclaw/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Oraclaw, 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.
19 Oraclaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.