Based on the schema, this server lets you discover available models and run single-turn prompts against them; the README also describes broader multi-model review/search workflows.
List supported model providers and their available models, including provider-specific model IDs and accepted input modalities.
Execute a single-turn prompt against a specified provider and model ID.
Optionally attach local text or image files as context.
Return the model’s response as a text result.
README-described extras not exposed by the schema: second-opinion review prompts, live cross-provider model search, and document-to-markdown conversion.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@moa-mcp Run 'Why is the sky blue?' on all available models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A local stdio MCP server (mixture of models) for running single-turn prompts across multiple model providers - OpenAI, Ollama (cloud) and OpenRouter. Similar in spirit to Claude's advisor tool, but not limited to one family of models: agents can fan the same prompt out to several models and combine the output.
get_second_opinion - sends a piece of work (writing, code, a design, a technical solution) to another model with reviewer instructions: lead with a verdict, then specific, actionable findings ordered by importance. An optional focus narrows the review; optional attachments add context.
execute_prompt - executes a single-turn prompt against a given provider and model_id, with an optional system prompt. Optional attachments is a list of local file paths included as context: text files are inlined, images are embedded for vision models, and documents (PDF, Word, PowerPoint, Excel, ...) are converted to markdown with markitdown. Paths work because the server always runs on the same machine as the caller.
search_models - searches models across all providers, with catalogues fetched live from each provider's API and cached for a few minutes. The query is matched case-insensitively against model name, model id and provider name (an empty query matches everything). Returns an object with:
models - at most limit matches, interleaved across providers so one large catalogue cannot crowd out the others, each with the provider, a human-friendly name, the id to pass to the other tools, the input modalities (null where the provider does not report them) and the cost in USD per million input/output tokens (null where pricing is not reported or is subscription-based, e.g. Ollama cloud);
truncated - true when more models matched than limit returned;
errors - one entry per provider whose catalogue could not be fetched (e.g. a missing API key); those providers are skipped rather than failing the whole search.
Related MCP server: mcp-second-opinion
cp .env.example .env # then fill in the keys you use; every provider is optional
uv syncclaude mcp add --scope user mom -- uv run --directory /path/to/mom-mcp mom-mcpuv run pytestProviders are declared in src/mom_mcp/providers.py as instances of a single OpenAI-compatible Provider dataclass, each with a parser that maps its /v1/models response onto the shared Model shape. To add a provider, declare a new Provider and register it in PROVIDERS.
Execute a single-turn prompt against a model and return its response.
provider and model_id must match an entry from list_models. attachments
is an optional list of local file paths (text or images) included as
context with the prompt.
Inputs: prompt (required), model_id (required), provider (required), attachments. Returns: result
List supported model providers and the models available under each.
Returns a mapping of provider name to a list of models, each with a
human-friendly name, the provider-specific model id to pass to
execute_prompt, and the input modalities the model accepts (text-only
models reject image attachments).
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have completely distinct purposes: one lists available models, the other executes prompts. There is no overlap or ambiguity in their functionality.
Both tool names follow a consistent verb_noun pattern: 'list_models' and 'execute_prompt'. The naming style is uniform and predictable.
With only 2 tools, the server feels thin for a typical MCP server, but the two tools cover a minimal end-to-end workflow (discover models, execute prompts). This is borderline acceptable but not a rich toolkit.
For the stated purpose of executing single-turn prompts against models, the surface is complete: list_models provides the necessary metadata to call execute_prompt, and execute_prompt handles the execution. No obvious gaps exist within this narrow scope.
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
