Skip to main content
Glama
UplinkSwitch MCP server

UplinkSwitch MCP server

Official
by uplinkswitch

chat

Send messages to any supported model ID and get the answer with token usage and request cost, using one API key for OpenAI and Anthropic models.

Instructions

Send a conversation to any chat model id and return the answer with the token usage and the cost of the request. Needs UPLINKSWITCH_API_KEY in the environment. OpenAI and Anthropic models both work on the same key and base URL.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model": "<model>",
      "messages": "<messages>"
    },
    "name": "chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesA chat model id from list_models
messagesYesThe conversation, oldest first
max_tokensNoCap on the reply length
temperatureNoSampling temperature

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, so the description carries the full burden. It discloses useful behavior beyond the schema: the call incurs a cost, the response includes token usage, and both OpenAI and Anthropic models share one key and base URL. It omits error/timeout behavior, whether output streams, and how cost is computed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, no filler, and the core capability plus return contents are front-loaded before the auth requirement and provider note. Each sentence contributes a distinct piece of information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple four-parameter tool with full schema coverage and no output schema, the description covers purpose, auth prerequisite, provider compatibility, and the shape of the return (answer, usage, cost). Only failure modes and any output formatting detail are left unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters (model, messages, max_tokens, temperature) are already documented, setting the baseline at 3. The description adds only the notion of 'any chat model id' and the shared-key compatibility note, not new semantics for individual parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: send a conversation to a chat model and return the answer with token usage and cost. That cleanly separates it from listing/pricing siblings like list_models and compare_prices, though it never names those siblings to route the agent explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage only: it is clearly the tool for running a chat completion, and it gives a real prerequisite (UPLINKSWITCH_API_KEY must be in the environment). It does not say when to prefer it over siblings or point out that model ids come from list_models, leaving that to the schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools