"Canonical" matching MCP servers:

Bitcoin-anchored provenance for AI outputs; enables stamping, verifying, and tracing outputs with offline-verifiable canonical roots.

Exposes canonical knowledge about DeepSeek FR (models, pricing, FAQ, official links) to MCP-compatible AI clients, enabling querying of site information without API keys.

MCP server for deterministic document infrastructure, enabling canonical normalization, schema validation, and grammar compilation for structured AI artifacts.

Enterprise AI operator evaluation MCP server. 27 tools (22 read + 5 write) for measuring, benchmarking, diagnosing, and interv ening on how human operators use AI tools across 5 canonical metrics.

Enables deterministic, read-only construction of Seedance-oriented video prompts, planning of multimodal reference-aware sequences, prompt diagnosis, and discovery of canonical See Dance 2 resources.

A read-only, deterministic server that enables assembling copy-ready video prompts, planning timed shot sequences, diagnosing prompt clarity and current duration/resolution/reference/end-frame/audio limits, and retrieving canonical creation, guide, pricing, and policy URLs.

Provides read-only tools to build English or Chinese video prompts, plan reference-aware sequences, diagnose prompts, and fetch canonical SeeVido resources without API keys.

Enables LLMs to perform structured, verifiable knowledge operations using the Canonical Knowledge Structure (CKS) ecosystem, including validation, querying, comparison, evolution, and derivation of knowledge.

Enables Claude Code users to decompose a raw prompt into structured, typed blocks and then recompile them into a Claude-optimized XML prompt with an estimated token count. It also exposes the full catalog of available block types with descriptions and their recommended canonical ordering for manual prompt crafting.

Enables Claude Code to break raw prompts into structured, typed blocks and recompile them into Claude-optimized machine-readable XML, with tools for listing available block types and canonical ordering. It also returns token estimates and supports manual block editing within the workflow.

Enables Claude Code to break raw prompts into structured, typed blocks, recompile those blocks into Claude-optimized XML prompts with token estimates, and list all available block types and their canonical ordering. It works statelessly over Streamable HTTP with no authentication required.

Exposes prompt-engineering tools that break a raw prompt into typed blocks, let them be adjusted, and recompile them into a Claude-optimized XML prompt with an estimated token count. Also lists the available block types and their recommended canonical ordering.

Enables decomposing raw prompts into structured, typed blocks and recompiling them into Claude-optimized machine-readable XML prompts, all callable directly from Claude Code conversations. Also exposes the full set of available block types and their recommended canonical ordering for manual crafting.

Enables deterministic, neural-free compilation of natural language into typed intent and canonical receipts, with proof-gated synthesis and governed tool use via read-only compiler functions.

Exposes generate_image for general image generation and hatch-pet specific workflows: canonical base generation, identity reference, multi-image input, layout guides, and single-action row chroma-key source images.

Enables Claude Code to decompose raw prompts into structured typed blocks, compile blocks into Claude-optimized XML prompts with estimated token counts, and list all 16 available block types with their canonical ordering.

Exposes five tools that let an assistant list and inspect schema-mutation benchmark tasks, grade submitted JSON tool calls against canonical answers, run the benchmark against a chosen model, and read dataset provenance. It enables measuring whether a model follows the current tool schema or falls back on a memorized one.

Enables Claude Code users to decompose raw prompts into typed structured blocks, compile those blocks into Claude-optimized XML prompts with token estimates, and list all available block types and their canonical ordering — all directly inside a conversation without a browser or copy-paste.

Exposes prompt-engineering tools that decompose raw prompts into typed, structured blocks, let those blocks be reviewed or edited as JSON, and recompile them into reordered, Claude-optimized XML prompts with token estimates. Also enumerates the available block types and their recommended canonical order for manual crafting.

A Model Context Protocol server providing pre-curated canonical memory, prose/code provenance checking, and benchmark metrics to improve accuracy and reduce costs across AI tools.