One-shot orchestrator for agent-driven onboarding (B.2 flow). The agent scans the repository locally, builds a manifest (repository + nodes + edges + optional annotations), and sends it as a single tool call. Server fans out atomic writes, resolves node keys to IDs internally. Much faster than do...
AI agents use ingest_architecture to create or update resources in RoadBoard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RoadBoard environment.
This tool creates or modifies project architecture data (nodes, edges, annotations, and repository metadata) through a single orchestrated call. While it performs multiple write operations, they are all reversible and do not permanently delete data or trigger financial transactions. The 'atomic writes' language confirms data modification capability.
From the tool's definition Tool description states it 'sends it as a single tool call' and 'Server fans out atomic writes', directly indicating that this tool creates/modifies data.
Attacks that exploit this kind of access
One-shot orchestrator for agent-driven onboarding (B.2 flow). The agent scans the repository locally, builds a manifest (repository + nodes + edges + optional annotations), and sends it as a single tool call. Server fans out atomic writes, resolves node keys to IDs internally. Much faster than dozens of create_architecture_* calls. Use. It is categorised as a Write tool in the RoadBoard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RoadBoard MCP server in PolicyLayer and add a rule for ingest_architecture: 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 RoadBoard. Nothing to install.
ingest_architecture 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 ingest_architecture 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 ingest_architecture. 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.
ingest_architecture is provided by the RoadBoard MCP server (maless88/roadboard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →