clef-mcp
Related Servers
Alternatives to clef-mcp
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to query a locally running Kev decision model through MCP tools, returning calibrated probabilities for typed questions such as yes/no, choice, and score.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceProvides an MCP interface to the Laya decision model, enabling typed queries (yes/no, multiple choice, score) with preflight token-budget reporting, honest confidence calibration, and structured error handling.47 PyPI5Apache 2.0
- AlicenseAqualityCmaintenanceEnables running Jev AI typed decisions from any MCP client, returning choices, scores, or yes/no with calibrated probabilities.311 npmMIT
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables MiMo Desktop to run a typed-decision engine through local stdio MCP, returning choice/score/noul predictions with calibrated confidence for auto-execution, LLM review, or escalation—without generating text.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-speaking hosts to ask typed questions (yes/no, choice, score) and receive calibrated probabilities instead of prose, over a stdio transport. Runs offline by default with an explicitly disclosed, opt-in egress contract for live providers.66 npmApache 2.0
- AlicenseAqualityBmaintenanceEnables coding agents to request calibrated probability judgments over typed questions—yes/no, named choices, or ordered scores—about a described situation, returning one probability per option rather than free text. Runs Cloudflare's Clef model locally on Apple Silicon Macs, with images or video frames optionally attached, and answers delivered as a single MCP tool call.178 PyPIMIT
- AlicenseAqualityBmaintenanceEnables agents to ask TypeSafe AI's Jev decision model typed questions — choices, scores, true/false propositions, and image bounding boxes — about a text or JSON state, returning structured answers with calibrated probabilities and confidence instead of free-form prose. Supports images, multi-question batch calls, and long-context requests over stdio.652 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables any MCP host to pose typed yes/no, choice, and score questions and receive calibrated probabilistic judgments instead of prose, over stdio and offline by default.66 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables agents and services to ask small decision models typed questions about text, JSON, images, or video, returning labels, scores, or yes/no answers over MCP tools or a Jev-compatible HTTP API.Apache 2.0
TDQS
Scored across 1 tool
With a single tool there is no possibility of tool misselection; the only differentiation needed is between question types (choice/score/noul), which the description enumerates explicitly.
A single verb_noun name with a server prefix (`clef_decide`) is internally consistent and predictable, and the prefix would scale cleanly if more `clef_*` tools were added.
One tool is borderline thin even for a focused decision-model wrapper; batching up to 64 questions inside one call partly compensates, but there is no separate schema-discovery or model-listing operation.
The tool covers the core judging lifecycle (arbitrary state in, typed questions, structured distributions with confidence and usage out) and supports batching and model override; minor gaps exist around discovering available models or validating question schemas before a call.