TasteCaliber
Integrates with NVIDIA NIM API models as an inference provider for extracting structured coding preference signals, switchable via MCP provider tools.
Connects to a local Ollama inference server to run LLM-based extraction of coding preference signals, with the provider configurable and switchable through MCP tools.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
TasteCaliber
TasteCaliber is a universal Model Context Protocol (MCP) server and developer workbench powered by the taste-1 Meta Neuro-Symbolic engine. It observes how you write, accept, reject, and edit code across AI coding agents (Claude Code, Cursor, Windsurf, Cline, Zed), builds a calibrated profile of your coding preferences in local SQLite, and injects those preferences back into every coding turn.
Key Capabilities
Universal MCP Server (
v1.1.0): Exposes Streamable HTTP (POST /mcp, optionalTASTE_API_TOKENBearer protection) and Local Stdio (npx tsx mcp-stdio.ts) transports backed by a single SQLite store, plus edge parity on Cloudflare Workers D1 (worker.ts), with MCPToolAnnotations(readOnlyHint,destructiveHint,idempotentHint) and recovery-friendlyisError: truehints.4-Step Neuro-Symbolic Pipeline:
Input Extraction (Configurable LLM + Fallback Chain): Converts raw prompts, accepts, rejects, and
before/afterdiffs into structured candidate signals using Local Inference Engines (Ollama, LM Studio, vLLM), NVIDIA NIM Fast Models (meta/llama-3.1-8b-instruct,nvidia/llama-3.1-nemotron-nano-8b-v1,qwen/qwen2.5-coder-32b-instruct,mistralai/codestral-22b-instruct-v0.1), OpenRouter, or automatic built-in deterministic fallback.taste-1Decision Classifier (Non-Generative & Extensible): Evaluates salience, classifies across 11 core engineering categories + 5 daily-agent domain packs (python,devops,writing,workflow,data) and custom domains (taste_register_domain) + extractedtags, prevents duplicate paraphrased rules via semantic similarity checks, flags contradictions across code & behavioral axes (verbosity,autonomy,output-format), and updates confidence via a KL-regularized Meta-RL Objective.Markdown Compiler, Linter & Pre-Flight Patch Verifier: Generates lint-validated
.tastecaliber/taste/**/taste.mdfiles (with optional LLM synthesis gated by strict structural validation) and runs deterministictaste_verify_patchchecks on proposed code/diffs before edits land.Local SQLite Storage (
data/taste.db): Powered by Node 22's built-innode:sqlitein WAL mode withbusy_timeout=5000and indexed queries for multi-agent concurrency.
Zero-Cost & Agent-Managed Models: Connects to local engines or free-tier APIs (NVIDIA NIM, OpenRouter), switchable at any time directly from any coding agent via
taste_list_providersandtaste_set_provider.TokenEconomizer Cost Control (
src/engine/economics.ts):File- & Task-Aware Token-True Context:
taste_get_contextscores rules and verified micro-skills againstfilePath+taskQuery, defaults to'compact'formatting without double-JSON bloat, trims tomaxTokens(default800), and logs accurate baseline vs. injected token savings.Corroborated Repository Micro-Skills: Captures compact operational facts (
candidate -> verifiedat>= 2corroborations) across code and daily workflows to skip cold-start exploration turns.Failure-Loop Guard & Tool Pruning: Detects
3+consecutive corrective/reject signals (loopGuard), resets on'accept', tracks per-tool usage across all 18 MCP tools, and emits a copy-readyprunedAllowlistSnippet.
Related MCP server: Durebak
Quick Start
Prerequisites
Node.js
>= 22.14(uses built-innode:sqlite)Optional: Ollama / LM Studio running locally, or free API keys for NVIDIA NIM / OpenRouter.
1. Install & Configure
npm install
cp .env.example .envEdit .env to point at your local inference engine or free-tier API secrets:
TASTE_DB_PATH="./data/taste.db"
TASTE_API_TOKEN=""
LOCAL_LLM_BASE_URL="http://localhost:11434/v1"
LOCAL_LLM_MODEL="qwen2.5-coder:7b"
NVIDIA_API_KEY=""
OPENROUTER_API_KEY=""2. Run the MCP Server & Workbench
npm run devTasteCaliber Workbench:
http://localhost:3000MCP Streamable HTTP Endpoint:
http://localhost:3000/mcpMCP Stdio Entrypoint:
npm run mcp:stdio(npx tsx mcp-stdio.ts)
3. Run Tests & Type Check
npm test # Runs node:test suite for taste-1 neuro-symbolic & RL logic
npm run lint # Runs tsc --noEmit
npm run build # Builds production frontend bundleConnect Any Coding Agent
OpenCode (opencode.json)
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"tastecaliber": {
"type": "remote",
"url": "http://localhost:3000/mcp",
"enabled": true
}
}
}Claude Code (HTTP)
claude mcp add --transport http tastecaliber http://localhost:3000/mcpCursor / Windsurf / Cline (Local Stdio)
{
"mcpServers": {
"tastecaliber": {
"command": "npx",
"args": ["tsx", "mcp-stdio.ts"],
"env": {
"TASTE_DB_PATH": "./data/taste.db"
}
}
}
}See docs/mcp-protocol.md for Zed, HTTP JSON configurations, and raw JSON-RPC 2.0 tool schemas.
Recommended Free Deployment
Deployment Option | Free Tier | Cold Start | Best For |
Cloudflare Workers (Recommended) | 100,000 requests/day | Near-zero (V8 isolates) | Best free global edge option for TypeScript MCP servers |
Vercel Functions (Alternative) | Free Hobby tier | Fast serverless | Teams already building with Next.js needing instant rollbacks |
Docker / Fly.io / Railway | Free / low-cost tiers | Always-on | Hosting full Express UI + local |
Local Stdio ( | Unlimited (local) | Instant | Private single-machine coding agent workflows |
Read the step-by-step setup in docs/deployment.md.
Documentation Index
Architecture &
taste-1Engine — 4-step pipeline, Meta-RL objective math, extensible domains & behavioral conflict axes, SQLite schema (includingdomain_packs,micro_skills,economics_events,tool_usage), and.tastecaliber/taste/sync.MCP Protocol & Client Setup — Required MCP server specifications, all 18 tools (with
annotations), 6 resources/templates, 2 prompt templates, optional Bearer auth, and agent integration configs.LLM Providers & Local Engines — Configuring Ollama, LM Studio, vLLM, NVIDIA NIM, and OpenRouter free models.
Deployment Guide — Deploying TasteCaliber via
worker.ts+wrangler.toml(Cloudflare Workers D1), Vercel Functions,Dockerfile, and local stdio.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Multiplayer for the coding agents your team already uses: shared tasks, decisions, skills and tools.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables coding agents in different editors and MCP clients to share messages, project context, notes, task ownership, handoffs, and advisory file claims through a local SQLite-backed coordination server. Supports MCP stdio, MCP Streamable HTTP, a JSON HTTP API, and a local CLI for multi-project agent collaboration.MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding-agent sessions on the same machine to collaborate locally and durably by exchanging requests, replies, and task results through an authenticated loopback server with SQLite-backed storage, joined via CLI or an MCP stdio bridge. It also handles message delivery by priority and wait time, deduplicates idempotent sends, enforces task versioning, and preserves artifacts by content hash.12 npmApache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables an AI assistant to delegate coding tasks to local Codex or Claude Code CLIs, monitor their progress, read results, continue sessions, and browse the files in user-approved project workspaces. It exposes these capabilities over Streamable HTTP through a Cloudflare tunnel or locally over stdio, so a remote or cloud client can drive agents running on the user's own machine.60 npm1MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent local memory during sessions, storing and semantically searching project decisions, preferences, error patterns, guidelines, and cross-project standards from SQLite stores on the user's machine. An optional companion server also exposes an autonomous task queue for executing queued work.-