Skip to main content
Glama
vivmuk

Medhā MCP

by vivmuk

Venice Responses API

venice_responses

Generate AI chat responses via OpenAI-compatible API, supporting single-turn or multi-turn conversations, tool use, and agentic workflows with configurable models and output limits.

Instructions

OpenAI-compatible Responses API. Single-turn or multi-turn with tool support. Operator preferences — default: minimax-m3-preview; also try: qwen-3-7-max. OpenAI Responses API; agentic tool-use loop supported. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputYesEither a plain string or an array of role+content messages.
modelNo
temperatureNo
max_output_tokensNo
Behavior4/5

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

With no annotations provided, the description carries full burden and it does a solid job: discloses uncensored/NSFW behavior, x402 wallet auth capability (no Venice account needed), API key support, and tool-use loop support. This is meaningful behavioral context beyond what any schema or annotation provides. Slightly limited by not describing rate limits or return format, but strong for an unannotated tool.

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

Conciseness4/5

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

The description is reasonably concise at ~5 sentences and front-loads the key purpose. Some redundancy exists (mentioning 'OpenAI Responses API' twice and repeating OpenAI-compatibility), but overall it packs useful info without bloat. Slight repetition reduces this from a 5.

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 tool with no output schema and 25% param coverage, the description provides decent operational context: model defaults, NSFW policy, auth options, and tool-use capability. However, it doesn't explain return value structure, streaming, error behavior, or the input schema nuances for tool-calling messages — gaps an agent would benefit from given the 'tool support' claim.

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 only 25% (only 'input' is documented). The description compensates partially by clarifying the input can be single-turn or multi-turn with tool support, and mentions the model preference defaults, but doesn't clarify temperature semantics, max_output_tokens constraints, or how tool use is specified in the message array. Minimal value added beyond schema for the undocumented params.

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?

Description clearly states this is an 'OpenAI-compatible Responses API' supporting 'Single-turn or multi-turn with tool support.' It distinguishes from siblings by highlighting the OpenAI Responses API compatibility and agentic tool-use loop, which differentiates from venice_chat. However, it doesn't explicitly contrast with venice_chat, only implying the distinction.

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?

The description notes model preferences (default minimax-m3-preview, also try qwen-3-7-max) which aids model selection, and mentions premium/uncensored behaviors. However, it never explicitly states when to use this tool vs venice_chat or when NOT to use it, leaving the agent to infer the boundaries from the sibling list and the description's own framing.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vivmuk/medha-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server