MCP Cost Optimizer vs Model Shunt
A side-by-side look at the MCP Cost Optimizer and Model Shunt MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose MCP Cost Optimizer for conversational ai work as a local process; choose Model Shunt for conversational ai as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose MCP Cost Optimizer when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
CONTROL_PLANE_URL. - You want tools like
estimate_llm_cost, analyze_llm_usage, compare_llm_models.
Choose Model Shunt when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
SHUNT_PROVIDER, SHUNT_MODEL, GEMINI_API_KEY, GROQ_API_KEY, DEEPSEEK_API_KEY, SHUNT_BASE_URL, SHUNT_API_KEY, SHUNT_ALLOWED_ROOTS.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 56/100 · Good | 44/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | CONTROL_PLANE_URL | SHUNT_PROVIDERSHUNT_MODELGEMINI_API_KEYGROQ_API_KEYDEEPSEEK_API_KEYSHUNT_BASE_URLSHUNT_API_KEYSHUNT_ALLOWED_ROOTS |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 3 | Not listed |
| Full listing | View MCP Cost Optimizer | View Model Shunt |
Tools & capabilities
MCP Cost Optimizer tools 3
estimate_llm_costSingle-request estimateanalyze_llm_usageCosts by model, unpriced models, duplicate opportunitycompare_llm_modelsIndependent migration scenario
Model Shunt tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
MCP Cost Optimizer
{
"mcpServers": {
"mcp-cost-optimizer": {
"command": "npx",
"args": [
"-y",
"mcp-cost-optimizer"
],
"env": {
"CONTROL_PLANE_URL": "YOUR_CONTROL_PLANE_URL_HERE"
}
}
}
}
Model Shunt
{
"mcpServers": {
"model-shunt": {
"command": "npx",
"args": [
"-y",
"launcher"
],
"env": {
"SHUNT_PROVIDER": "YOUR_SHUNT_PROVIDER_HERE",
"SHUNT_MODEL": "YOUR_SHUNT_MODEL_HERE",
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY_HERE",
"GROQ_API_KEY": "YOUR_GROQ_API_KEY_HERE",
"DEEPSEEK_API_KEY": "YOUR_DEEPSEEK_API_KEY_HERE",
"SHUNT_BASE_URL": "YOUR_SHUNT_BASE_URL_HERE",
"SHUNT_API_KEY": "YOUR_SHUNT_API_KEY_HERE",
"SHUNT_ALLOWED_ROOTS": "YOUR_SHUNT_ALLOWED_ROOTS_HERE"
}
}
}
}
Frequently asked questions
MCP Cost Optimizer is categorized under Conversational AI and uses a local stdio subprocess. Model Shunt belongs to Conversational AI and uses a local stdio subprocess. Pick MCP Cost Optimizer for conversational ai work and Model Shunt for conversational ai.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
MCP Cost Optimizer is listed as free. Auth: no auth required. Model Shunt has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add mcp-cost-optimizer and model-shunt as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, MCP Cost Optimizer has a quality signal of 56/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Model Shunt has 44/100 (Fair) with 1 views, 0 installs and 0 GitHub stars.