feat: add pricing sync script and update model prices from OpenRouter (#27)

* fix: pin npm package versions in MCP integration templates

Prevent supply chain attacks by pinning exact versions instead of
using unpinned `npx -y @package` which pulls latest on every run.

23 of 25 integrations pinned. sqlite-mcp and aws skipped (packages
not found on npm registry).

* fix: use stable azure/mcp version instead of beta

* feat: add pricing sync script and update model prices from OpenRouter API

- scripts/sync-pricing.py fetches real-time pricing from OpenRouter
- Updated 64 price fields across 13 provider files
- Run periodically or in CI to keep prices current

providers/liquid.toml

@@ -0,0 +1,58 @@
+# liquid — auto-generated from OpenRouter API
+
+[provider]
+id = "liquid"
+display_name = "Liquid"
+api_key_env = "LIQUID_API_KEY"
+base_url = ""
+key_required = true
+
+[[models]]
+id = "lfm-2-24b-a2b"
+display_name = "LiquidAI: LFM2-24B-A2B"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.03
+output_cost_per_m = 0.12
+supports_streaming = true
+
+[[models]]
+id = "lfm-2.2-6b"
+display_name = "LiquidAI: LFM2-2.6B"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.01
+output_cost_per_m = 0.02
+supports_streaming = true
+
+[[models]]
+id = "lfm-2.5-1.2b-instruct:free"
+display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free)"
+tier = "free"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "lfm-2.5-1.2b-thinking:free"
+display_name = "LiquidAI: LFM2.5-1.2B-Thinking (free)"
+tier = "free"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "lfm2-8b-a1b"
+display_name = "LiquidAI: LFM2-8B-A1B"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.01
+output_cost_per_m = 0.02
+supports_streaming = true