AI Tool Integrations
Isartor is an OpenAI-compatible and Anthropic-compatible gateway that deflects repeated or simple prompts at Layer 1 (cache) and Layer 2 (local SLM) before they reach the cloud. Clients integrate by overriding their base URL to point at Isartor or by registering Isartor as an MCP server — no proxy, no MITM, no CA certificates.
Endpoints
Isartor's server defaults to: http://localhost:8080.
Authenticated chat endpoints:
| Endpoint | Protocol | Path |
|---|---|---|
| Native Isartor (recommended for direct use) | Native | POST /api/chat / POST /api/v1/chat |
| OpenAI Models | OpenAI | GET /v1/models |
| OpenAI Chat Completions | OpenAI | POST /v1/chat/completions |
| Anthropic Messages | Anthropic | POST /v1/messages |
| Cache lookup / store (used by MCP clients) | Native | POST /api/v1/cache/lookup / POST /api/v1/cache/store |
Authentication
Isartor can enforce a gateway key on authenticated routes when Layer 0 auth is enabled.
Supported headers:
X-API-Key: <gateway_api_key>Authorization: Bearer <gateway_api_key>(useful for OpenAI/Anthropic-compatible clients)
By default, gateway_api_key is empty and auth is disabled (local-first). To
enable gateway authentication, set ISARTOR__GATEWAY_API_KEY to a secret value. In
production, always set a strong key.
Observability headers
All endpoints in the Deflection Stack include:
X-Isartor-Layer:l1a|l1b|l2|l3|l0X-Isartor-Deflected:trueif resolved locally (no cloud call)
Example: OpenAI-compatible request
curl -sS http://localhost:8080/v1/chat/completions \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-4o-mini",
"messages": [
{"role": "user", "content": "2 + 2?"}
]
}'
If gateway auth is enabled, also add:
-H 'Authorization: Bearer your-secret-key'
Many OpenAI-compatible SDKs and coding agents also call:
curl -sS http://localhost:8080/v1/models
OpenAI-compatible agent features supported by Isartor:
GET /v1/modelsfor model discoverystream: trueon/v1/chat/completionswith OpenAI-style SSE anddata: [DONE]tools,tool_choice,functions, andfunction_callpassthroughtool_callspreserved in provider responses- tool-aware exact cache keys, with semantic cache skipped for tool-use flows
Example: Anthropic-compatible request
curl -sS http://localhost:8080/v1/messages \
-H 'Content-Type: application/json' \
-d '{
"model": "claude-sonnet-4-6",
"system": "Be concise.",
"max_tokens": 100,
"messages": [
{
"role": "user",
"content": [{"type": "text", "text": "What is the capital of France?"}]
}
]
}'
If gateway auth is enabled, also add:
-H 'X-API-Key: your-secret-key'
Supported tools at a glance
| Tool | Command | Mechanism |
|---|---|---|
| GitHub Copilot CLI | isartor connect copilot | MCP server (cache-only) |
| GitHub Copilot in VS Code | isartor connect copilot-vscode | Managed settings.json debug overrides |
| OpenClaw | isartor connect openclaw | Managed OpenClaw provider config (openclaw.json) |
| OpenCode | isartor connect opencode | Global provider + auth config |
| Claude Code + GitHub Copilot | isartor connect claude-copilot | Claude base URL override + Copilot-backed L3 |
| Claude Code | isartor connect claude | Base URL override |
| Claude Desktop | isartor connect claude-desktop | Managed local MCP registration (isartor mcp) |
| Cursor IDE | isartor connect cursor | Base URL override + MCP |
| OpenAI Codex CLI | isartor connect codex | Base URL override |
| Gemini CLI | isartor connect gemini | Base URL override |
| Antigravity | isartor connect antigravity | Base URL override |
| Generic / other tools | isartor connect generic | Base URL override |
Add --gateway-api-key <key> to any connect command only if you have explicitly
enabled gateway auth.
Connection status
# Check all connected clients
isartor connect status
Global troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
| "connection refused" | Isartor not running | Run isartor up first |
| Gateway returns 401 | Auth enabled but key not configured | Add --gateway-api-key to connect command |
For tool-specific troubleshooting, see each integration page above.