# Continuum-AI-Corp/orcarouter-mcp-server [Health: Active]

**Category:** 🔗 Aggregators  
**Repository:** https://github.com/Continuum-AI-Corp/orcarouter-mcp-server  
**GitHub Stars:** 12  
**npm Downloads (last month):** 582  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/continuum-ai-corp-orcarouter-mcp-server

## Description
Browse 160+ LLM models (OpenAI, Anthropic, Google, Qwen, DeepSeek, …) with live pricing — no API key required for catalog tools. Routes chat completions through the OrcaRouter gateway with automatic fallback. npx -y @orcarouter/mcp.

## Tools
Capabilities this server exposes over MCP:

- **orcarouter_chat** — Send a single-turn chat request to OrcaRouter and return the assistant's response text. Default model is the workspace's auto-router. Use `orcarouter/<name>` for other routers or `<provider>/<model>` for direct calls. For OpenAI reasoning models (gpt-5/o1/o3/...), max_tokens is automatically routed to max_completion_tokens at the wire level. The optional `models` array sets a fallback chain — the primary `model` is tried first, then each entry on failure (5 entries total max, including the primary). Errors are returned as text content with isError:true; common cases include missing API key, rate limits, and upstream provider outages. Requires ORCAROUTER_API_KEY.
- **orcarouter_models_list** — List LLM models in the OrcaRouter catalog. Each entry includes id, name, description, owned_by, context_length, supported_endpoint_types, and pricing (both per-token and per-million tokens). Filter by `provider`, `capability`, or `min_context` — filters compose (all conditions must match) and are applied server-side. Discover valid provider ids first with orcarouter_providers_list. Returns the full catalog when called without filters. Read-only, no API key required.
- **orcarouter_model_card** — Get detailed information about a single model — display name, long description, pricing (per-call and per-million tokens), context window, max output, modalities (input/output), supported endpoints, latency percentiles (p50/p95), and release date. Use this when you already know the model id and want full details; for browsing or filtering across many models use orcarouter_models_list instead. Returns isError:true with a clear hint when the id is not found. Read-only, no API key required.
- **orcarouter_providers_list** — List all model providers on OrcaRouter with their `provider_id`, human-readable `display_name`, `icon_url`, and `model_count`. Call this first to discover valid provider ids (e.g. 'openai', 'anthropic', 'google', 'qwen', 'deepseek') which you can then pass to orcarouter_models_list as the `provider` filter. Takes no parameters and returns the same list on every call until the deployment's catalog changes. Read-only, no API key required.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "orcarouter-mcp-server": {
    "command": "npx",
    "args": ["-y","@orcarouter/mcp"],
    "env": {
      "ORCAROUTER_API_KEY": "",
      "ORCAROUTER_BASE_URL": "",
      "ORCAROUTER_REQUEST_TIMEOUT": ""
    }
  }
}
```

**Requires environment variables:** `ORCAROUTER_API_KEY`, `ORCAROUTER_BASE_URL`, `ORCAROUTER_REQUEST_TIMEOUT` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What Continuum-AI-Corp/orcarouter-mcp-server MCP server does

Continuum-AI-Corp/orcarouter-mcp-server MCP server connects MCP clients to OrcaRouter for two related tasks: exploring the available LLM catalog and sending chat completion requests. The catalog tools expose provider names, model metadata, pricing, context limits, capabilities, supported endpoints, latency percentiles, and release dates. These read-only operations do not require an OrcaRouter API key.

The chat tool sends a single-turn request and returns the assistant’s response text. It can use the workspace’s automatic router by default, address another OrcaRouter router, or call a provider/model directly. This makes the server suitable for agents that need to compare models before choosing one, or that should delegate model selection to OrcaRouter.

## How it works

The package runs as a local Node.js MCP process and communicates with the client through the MCP protocol. MCP clients discover the available input schemas through `tools/list`, so the client can present or invoke the four exposed tools without a separate tool-definition setup.

`orcarouter_providers_list` returns provider identifiers and model counts. Those identifiers can then be supplied to `orcarouter_models_list`, whose provider, capability, and minimum-context filters are combined server-side. `orcarouter_model_card` is intended for a known model ID and returns a fuller record than the catalog listing.

For chat, the primary model is attempted first. An optional `models` array can add up to four fallbacks, for a maximum chain of five models including the primary. Requests aimed at OpenAI reasoning models have `max_tokens` translated to `max_completion_tokens` at the wire level. Failures, including missing credentials, rate limits, and upstream outages, are returned as error text with `isError: true`.

## Setup and configuration

Install and run Continuum-AI-Corp/orcarouter-mcp-server MCP server with Node.js 18 or newer:

```bash
npx -y @orcarouter/mcp
```

Add the command to an MCP client configuration, then provide `ORCAROUTER_API_KEY` for chat calls. The README documents configurations for Claude Desktop, Claude Code, Cursor, and Windsurf; the server also works with other clients that implement MCP. The key is read from the environment, is not logged, and is sent only to the OrcaRouter API.

Configuration variables include:

- `ORCAROUTER_API_KEY`: required only by `orcarouter_chat`.
- `ORCAROUTER_BASE_URL`: optional API base URL; the default is `https://api.orcarouter.ai`.
- `ORCAROUTER_REQUEST_TIMEOUT`: optional per-request timeout in seconds; the default is `300`.

## Tools and capabilities

Continuum-AI-Corp/orcarouter-mcp-server MCP server exposes these tools:

- `orcarouter_chat`: Send a single-turn chat request with router, direct model, and fallback-chain options.
- `orcarouter_models_list`: Browse the complete catalog or filter it by provider, capability, and minimum context length.
- `orcarouter_model_card`: Retrieve detailed metadata for one model, including pricing, modalities, context window, output limit, endpoints, latency, and release date.
- `orcarouter_providers_list`: List providers with IDs, display names, icon URLs, and model counts.

The catalog can be used before authentication to compare available models and pricing. Chat routing is the only listed capability that needs the OrcaRouter credential.

## Limitations and notes

The server performs single-turn chat requests rather than describing a multi-turn conversation or agent memory feature. Catalog results are read-only. Provider and model identifiers must match the OrcaRouter catalog; the provider-list tool is the documented way to discover valid provider IDs. The fallback chain is limited to five total entries, including the primary model. API availability, rate limits, and provider outages can still cause chat errors even when the MCP process is running.

_Full upstream README: https://allmcps.com/mcp/continuum-ai-corp-orcarouter-mcp-server/readme_