analyze_project
Diagnose a network for cleanup: report likely-dead operators (zero wired outputs, unreferenced, not displayed), broken external-file dependencies (file parameters pointing at missing files), orphan COMPs, and a dependency map of which operators reference which. Read-only and conservative — every ...
This record as markdown: /tools/hybridlabor-api-aos/analyze-project.md
What analyze_project does on Aos
AI agents call analyze_project to retrieve information from Aos without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why analyze_project is rated Low
analyze_project retrieves and analyzes existing project structure without modifying or executing anything. It generates diagnostic reports about operators, dependencies, and file references—pure read operations. The tool is designed as a non-destructive complement to other building/modification tools (plan_visual, snapshot_td_graph). No data is created, modified, deleted, executed, or monetized.
From the tool's definition Tool is explicitly described as 'Read-only and conservative' and performs diagnostic reporting: 'report likely-dead operators', 'broken external-file dependencies', and 'a dependency map'. All operations are information retrieval with no side effects.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs analyze_project safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For analyze_project, this is the rule to start with:
analyze_project is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Aos, apply this rule, and every analyze_project call is checked against it from then on.
Questions about analyze_project
Diagnose a network for cleanup: report likely-dead operators (zero wired outputs, unreferenced, not displayed), broken external-file dependencies (file parameters pointing at missing files), orphan COMPs, and a dependency map of which operators reference which. Read-only and conservative — every flagged item carries a human-readable reason. Complements plan_visual (which plans a build) and snapshot_td_graph (which dumps structure). It is categorised as a Read tool in the Aos MCP Server, which means it retrieves data without modifying state.
Register the Aos MCP server in PolicyLayer and add a rule for analyze_project: 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 Aos. Nothing to install.
analyze_project 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_project 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_project. 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_project is provided by the Aos MCP server (@hybridlabor-api/aos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aos, and thousands of servers like it.
This server
Across the catalogue