Inferenceindexer MCP vs Tokencost Dev
A side-by-side look at the Inferenceindexer MCP and Tokencost Dev MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Inferenceindexer MCP for conversational ai work as a local process; choose Tokencost Dev 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 Inferenceindexer MCP when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
II_API_BASE, II_API_KEY, II_SSR_SECRET. - You want tools like
search_models, get_model, get_model_history.
Choose Tokencost Dev when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You want tools like
get_model_details, calculate_estimate, compare_models.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 49/100 · Fair | 60/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | II_API_BASEII_API_KEYII_SSR_SECRET | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 8 | 4 |
| Full listing | View Inferenceindexer MCP | View Tokencost Dev |
Tools & capabilities
Inferenceindexer MCP tools 8
search_modelsSearch/list models with current pricing (by text, tier, sort)get_modelFull detail + current price for one modelget_model_historyHistorical** price trends for one model (the differentiator)list_providersAll providers with model counts + price statsget_providerDetail for one provider (models, tiers, price range)get_composite_latestCurrent SIT-Composite index value + tier breakdownget_composite_historySIT-Composite index history / trendcompare_providersPrice of one model across all providers that host it
Tokencost Dev tools 4
get_model_detailsLook up pricing, context window, and capabilities for an LLM model. Uses fuzzy matching so you don't need the exact model key.calculate_estimateEstimate the cost for a given number of input and output tokens on a specific model. Supports optional cached_tokens for prompt caching discounts.compare_modelsFilter and compare models by provider, minimum context window, or mode. Returns top 5 most cost-effective matches.refresh_pricesForce a re-fetch of pricing data from the LiteLLM registry. Use this if you suspect the cached data is stale.
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.
Inferenceindexer MCP
{
"mcpServers": {
"inferenceindexer-mcp": {
"command": "uvx",
"args": [
"inferenceindexer-mcp"
],
"env": {
"II_API_BASE": "YOUR_II_API_BASE_HERE",
"II_API_KEY": "YOUR_II_API_KEY_HERE",
"II_SSR_SECRET": "YOUR_II_SSR_SECRET_HERE"
}
}
}
}
Tokencost Dev
{
"mcpServers": {
"tokencost-dev": {
"command": "npx",
"args": [
"-y",
"tokencost-dev"
]
}
}
}
Frequently asked questions
Inferenceindexer MCP is categorized under Conversational AI and uses a local stdio subprocess. Tokencost Dev belongs to Conversational AI and uses a local stdio subprocess. Pick Inferenceindexer MCP for conversational ai work and Tokencost Dev 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.
Inferenceindexer MCP has no declared pricing — check the project's own site. Tokencost Dev 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 inferenceindexer-mcp and tokencost-dev as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Inferenceindexer MCP has a quality signal of 49/100 (Fair) with 1 views, 0 installs and 0 GitHub stars. Tokencost Dev has 60/100 (Good) with 1 views, 0 installs and 1 GitHub stars.