MCPVault

allow_fallbacks

MCP tool from Openrouterai by heltonteixeira

(boolean, optional): If true (default), allows falling back to other providers if the preferred ones fail or are unavailable. If false, fails the request if preferred providers cannot be used. Overrides OPENROUTERPROVIDERALLOWFALLBACKS. (Phase 2)

How to use it

allow_fallbacks is exposed by the Openrouterai MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the allow_fallbacks tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Openrouterai

$pnpm install @mcpservers/openrouterai
FULL OPENROUTERAI LISTING

Other tools in Openrouterai (15)

chat_completion

Sends a request to the OpenRouter Chat Completions API.

data_collection

("allow" "deny", optional): Specify whether providers are allowed to collect data from the request. Overrides OPENROUTERPROVIDERDATACOLLECTION. (Phase 2)

get_model_info

Get detailed information about a specific model:

ignore

(array of strings, optional): List of provider names to exclude (e.g., ["openai", "anthropic"]). Models from these providers will not be used. Overrides OPENROUTERPROVIDERIGNORE. (Phase 1)

max_tokens

(number, optional): Maximum number of tokens to generate in the completion. Overrides OPENROUTERMAXTOKENS.

messages

(array, required): An array of message objects conforming to the OpenAI chat completion format.

model

(string, optional): The model to use (e.g., openai/gpt-4o, google/gemini-pro). Overrides OPENROUTERDEFAULTMODEL. Defaults to openrouter/auto if neither is set.

order

(array of strings, optional): A prioritized list of provider IDs (e.g., ["openai/gpt-4o", "anthropic/claude-3-opus"]). Overrides OPENROUTERPROVIDERORDER. (Phase 2)

provider

(object, optional): Provider routing configuration. Overrides corresponding OPENROUTERPROVIDER environment variables.

quantizations

(array of strings, optional): List of quantization levels to filter by (e.g., ["fp16", "int8"]). Only models matching one of these levels will be considered. Overrides OPENROUTERPROVIDERQUANTIZATIONS. (Phase 1)

require_parameters

(boolean, optional): If true, only use providers that support all specified request parameters (like tools, functions, temperature). Overrides OPENROUTERPROVIDERREQUIREPARAMETERS. (Phase 2)

search_models

Search and filter available models:

sort

("price" "throughput" "latency", optional): Sort providers by the specified criteria. Overrides OPENROUTERPROVIDERSORT. (Phase 2)

temperature

(number, optional): Sampling temperature. Defaults to 1.

validate_model

Check if a model ID is valid: