AI agent integration matrix
Use this page to choose an integration path. It is written for assistant builders (ChatGPT Actions, Claude projects, Cursor rules, MCP clients) and for humans steering an agent who want the same vocabulary. Machines should still read /agent-tools.json or /mcp-tools.json.
Goals × integration mechanism
| Goal | Mechanism | Primary entry |
|---|---|---|
| Save model output tokens—user runs the transform in a tab | Prefilled HTTPS URL from manifest | /ai-agents, /agent-tools.json |
| Headless automation needs a JSON result (no browser) | Allowlisted POST execute | GET /api/agent/v1/capabilities, Server API matrix |
| Exclude AIGC catalog entries | Non-AIGC manifest | /mcp-tools.json |
| Stdio MCP in IDE (Cursor, Claude Code, …) | Local MCP server in repo | bun run mcp — see MCP & Actions guide |
| Quick terminal-style deep links | Pseudo-CLI | /tools/cli |
| Generative explain / NL → regex, etc. | AIGC tool page + POST /api/ai/* | /tools/ai, Server route matrix |
| Match natural-language queries to tools | Curated phrases index | /tools/keywords |
Copy-paste for LLM system prompts
GET /llm-prompt.txt mirrors the English instructions in the manifest. Pair it with Offload compute from LLMs when explaining why to delegate work to Toolcore.
Common use cases
- Onboard a new teammate wiring GPT Actions or MCP: send this matrix plus /ai-agents/server-api.
- Decide in one glance whether the next step is a prefilled URL or a POST to /api/agent/v1/execute.
Common mistakes to avoid
Skipping GET /api/agent/v1/capabilities before POST execute
The allowlisted operation IDs and body shape are versioned there; hard-coding URLs without refreshing capabilities can break after deploys.
FAQ
Is this page a substitute for the JSON manifests?
No. Crawlers and agents should still fetch /agent-tools.json or /mcp-tools.json for the full tool list and prefill rules. This page is a human- and retrieval-friendly map.