auxiliar-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recommend_toolsA | Recommend the best web-access provider(s) on the auxiliar.ai gateway for a job, ranked by measured benchmarks (quality, latency p50, cost per success, error rate — dated runs on a shared public corpus). Returns executable routes, the numbers behind each pick, and honest caveats. Use when deciding which search/scraping/crawling/extraction/browser API to use. |
| get_scorecardA | Full benchmark leaderboard for one job/verb: every scored provider on the auxiliar.ai gateway, best first, with raw measured metrics and run dates. Use to compare all options rather than be handed a pick. |
| get_providerA | Everything about one provider on the auxiliar.ai gateway: route and call pattern, entry pricing, when to choose or avoid it, and all its dated benchmark scorecards across verbs. |
| about_auxiliarA | What auxiliar.ai is and how an agent uses it: a web-access API gateway — one API key for 24 search, scraping, browser-automation and voice providers, upstream keys injected server-side, usage at provider-metered prices. Call this to learn how to get a key and call the gateway. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: about_auxiliar introduces the service, get_provider details a single provider, get_scorecard shows benchmarks for a verb, and recommend_tools recommends providers. No overlap.
All tool names use a consistent verb_noun pattern in snake_case (about_auxiliar, get_provider, get_scorecard, recommend_tools), making them predictable and easy to understand.
With 4 tools covering onboarding, provider details, benchmarks, and recommendations, the count is well-scoped for an information-focused MCP server about a gateway service.
The tools cover the main user needs: understanding, provider details, benchmarks, and recommendations. A minor gap is the lack of a tool to list all providers or verbs, but recommend_tools partially addresses this by taking a job as input.