Limits & Quotas
Guardrails that keep agent traffic predictable, plus what to know about how current the data an agent reads really is.
| Limit | Value | Notes |
|---|---|---|
| MCP requests | 300 / 5 min | Per MCP connection. Exceeding it returns HTTP 429 (rate_limited). |
| MCP request body | 256 KB | Per request. Larger bodies are rejected with HTTP 413. |
| AI writes | 30 / 10 min | Applied mutations per workspace — shared between MCP clients and the built-in assistant. |
| Tool executions | 150 / 5 min | Per account, on the REST tool endpoint. Exceeding it returns HTTP 429. |
| Assistant chat requests | 30 / 10 min | Applies to the built-in AI assistant. |
| Tools per assistant reply | 12 | Across at most 5 model round-trips, so one question always terminates. |
| Result size | ~60 KB | Larger results are summarised and explicitly marked as truncated. |
| Project list | 100 | Most recent projects; filter by type to narrow. |
| Deep model inspection | 4 models | Per validate_project call with deep: true. Model files are read with a bounded, time-limited request that never downloads full geometry. |
Data freshness
Tools read the last saved state of a project. The editor autosaves a few seconds after each change, so an edit made moments ago may not be visible yet. If an agent reports something that contradicts what you see on screen, save the project and ask again.
Continue reading
TroubleshootingStructured error categories, what each one means, and fixes for the most common MCP and tool-call failures.Resources for AgentsMachine-readable resources for LLMs and AI agents: llms.txt, the full plain-text MCP reference, the live tool schema endpoint, and the sitemap.MCP ChangelogEvery change to the Simplio3D agent surface — tools added, connection scopes, transport and OAuth releases, and confirmation-policy changes — newest first. The current surface version is 1.8.0, which is exactly what serverInfo.version reports on initialize.IntroductionWhat the Model Context Protocol is, what the Simplio3D MCP server exposes to AI agents, and the current availability of each capability.