docs: add Entroly MCP cost optimization cookbook

[juyterman1000]

What this PR adds

Adds a new cookbook guide: Reduce LLM API Costs with Entroly MCP and Continue

This follows the same format as existing MCP cookbooks (GitHub, Sentry, Supabase, Snyk, etc.) and shows Continue users how to:

1. Add Entroly as an MCP server — one YAML block in config
2. Or run as a transparent proxy — zero Continue config changes
3. Monitor savings via the Entroly dashboard

Why this is useful for Continue users:

Continue sends repo context to LLM APIs on every request. On large codebases, this means 100K+ tokens per call. Entroly compresses this by 70-95% while maintaining answer quality.

Key features shown in the cookbook:

• Context compression (knapsack + entropy scoring)
• Provider cache alignment (Anthropic 90% discount, OpenAI 50%)
• WITNESS hallucination guard (, ~3ms)
• Reversible compression via CCR handles

File added:

• \docs/guides/entroly-mcp-cost-optimization.mdx\

Apache-2.0, local-first, no outbound analytics by default. All benchmark claims backed by committed JSON artifacts at github.com/juyterman1000/entroly.

---

Summary by cubic

Adds a new cookbook that shows how to cut LLM token costs in Continue using the entroly MCP server or a local proxy. Users can set it up fast and monitor savings from context compression and cache alignment.

• New Features
  • Added guide: docs/guides/entroly-mcp-cost-optimization.mdx
  • Covers two paths: add entroly as an MCP server, or run entroly proxy with no Continue config changes
  • Includes dashboard monitoring and a quick explainer of compression, cache alignment, reversible context, and WITNESS guard

^{Written for commit 37ee924. Summary will update on new commits.}

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

I have read the CLA Document and I hereby sign the CLA

---

_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}

[cubic-dev-ai]

1 issue found across 1 file

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="docs/guides/entroly-mcp-cost-optimization.mdx">

<violation number="1" location="docs/guides/entroly-mcp-cost-optimization.mdx:21">
P2: Missing `uv`/`uvx` prerequisite despite using `uvx` in MCP server command</violation>
</file>

<sub>Reply with feedback, questions, or to request a fix.

Re-trigger cubic</sub>

[cubic-dev-ai]

P2: Missing uv/uvx prerequisite despite using uvx in MCP server command

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At docs/guides/entroly-mcp-cost-optimization.mdx, line 21:

<comment>Missing `uv`/`uvx` prerequisite despite using `uvx` in MCP server command</comment>

<file context>
@@ -0,0 +1,121 @@
+
+- Continue installed in your IDE (VS Code, JetBrains, etc.)
+- Python 3.10+ installed
+- An LLM API key (Anthropic, OpenAI, etc.)
+
+## Setup
</file context>