Local MCP server exposing the Cloudflare Clef-Flash decision model to AI agents — structured decisions with probability outputs, fully offline via llama.cpp.
A "reflex" for AI coding agents: structured decisions with probabilities — not prose.
Local MCP server that gives agents (Claude Code, Codex, Cursor, ZCode, …) access to the Clef-Flash decision model (9B, Apache-2.0 by Cloudflare) through a single tool: clefdecide. Pass a state and typed questions, get a probability distribution over your options in one forward pass. Fully local, offline, no tokens burned.
clef-mcp (step 3) never downloads anything. If the model is missing, tool calls return a structured MODELNOTINSTALLED error with a hint. Steps 1 and 2 combine: npx clef-mcp install --setup.
Chat LLM clefdecide --------- Output prose, you parse it strict JSON: probability per option Determinism varies per run single forward pass, no sampling Latency (1 decision) seconds of generation ~0.5 s local Context cost grows with every decision fixed, small schema Privacy depends on provider 100% on-device, works offline Calibration vibes softmax over trained option scores
Sweet spot: decision points inside agent loops — next action, routing, classification, severity, yes/no judgment — asked dozens of times per task.
Type Criteria Answer ------------------------ choice map option id → description, or a plain list probability per option score ordered list (index = score) probability per level noul optional {"true": "...", "false": "..."} {"true": p, "false": 1-p}
Response — strictly structured, never prose. Each decision carries the model-reported confidence (when the runtime sends it), plus token usage for the call:
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/HighlyLoadedEgo--ClefMCP.html)
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
rokbenko/quackd🦆🧠 Give your small robot a brain. Tell a Microduck, a Reachy Mini, a LeRobot arm or any ROS base what you want in plain language. An LLM (Claude, OpenAI, Gemini, Grok, or a local model via Ollama, vLL
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
F0Rextasy/omp-laya-judgeLocal Laya System-1 judge MCP server + skill for oh-my-pi: typed decisions in milliseconds, zero LLM tokens
DrakTheDude/stackchan-local-llmYour StackChan, your language model, your network — local-first firmware and server kit for the M5Stack StackChan. Voice, face, camera and MCP tools, with nothing sent to a cloud service.
XiaoDuoYa/codex-with-chatgptChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.