OpenRouter vs MCP Server
A side-by-side look at the OpenRouter and MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose OpenRouter for conversational ai work as a local process; choose MCP Server 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 OpenRouter when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
OPENROUTER_API_KEY. - You want tools like
chat, generate_image, embed.
Choose MCP Server when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
VAPI_TOKEN. - You want tools like
list_assistants, create_assistant, get_assistant.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 57/100 · Good | 68/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | OPENROUTER_API_KEY | VAPI_TOKEN |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 58 |
| Directory activity | 8 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 5 | 13 |
| Full listing | View OpenRouter | View MCP Server |
Tools & capabilities
OpenRouter tools 5
chatSend a chat completion request to any OpenRouter model.generate_imageGenerate an image using an OpenRouter image generation model.embedGenerate embeddings for text input using an OpenRouter embedding model.list_modelsList available OpenRouter models, optionally filtered by capability.find_modelsSearch for models by name or slug.
MCP Server tools 13
list_assistantsLists all Vapi assistantscreate_assistantCreates a new Vapi assistantget_assistantGets a Vapi assistant by IDupdate_assistantUpdates an existing Vapi assistantlist_callsLists all Vapi callscreate_callCreates a outbound callget_callGets details of a specific calllist_phone_numbersLists all Vapi phone numbersget_phone_numberGets details of a specific phone numberlist_toolsLists all Vapi toolsget_toolGets details of a specific toolcreate_toolCreates a new Vapi tool- +1 more on 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.
OpenRouter
{
"mcpServers": {
"openrouter-2": {
"command": "uvx",
"args": [
"mcp-openrouter"
],
"env": {
"OPENROUTER_API_KEY": "YOUR_OPENROUTER_API_KEY_HERE"
}
}
}
}
MCP Server
{
"mcpServers": {
"vapi-ai-mcp-server": {
"command": "npx",
"args": [
"-y",
"@vapi-ai/mcp-server"
],
"env": {
"VAPI_TOKEN": "YOUR_VAPI_TOKEN_HERE"
}
}
}
}
Frequently asked questions
OpenRouter is categorized under Conversational AI and uses a local stdio subprocess. MCP Server belongs to Conversational AI and uses a local stdio subprocess. Pick OpenRouter for conversational ai work and MCP Server 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.
OpenRouter has no declared pricing — check the project's own site. MCP Server is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. 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 openrouter-2 and vapi-ai-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, OpenRouter has a quality signal of 57/100 (Good) with 8 views, 0 installs and 1 GitHub stars. MCP Server has 68/100 (Great) with 1 views, 0 installs and 58 GitHub stars.