"Canonical" matching MCP servers:

Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.

Repository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.

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

Canonical vocabulary server for autonomous business design. Exposes the Arco Lexicon as seven MCP tools: term lookup, related terms, alignment verification, citation formatting, source retrieval, term listing, and term suggestion. No authentication required. Streamable HTTP transport.

Gives a party of AI agents a shared, curated memory vault: they can submit raw episodes, recall entities and their graph neighbors, fetch canonical answers with status and disputes, and get briefings and quest updates. A nightly consolidation pass turns those queued episodes into durable canon facts with lane authority, rumor, disputed, and secret-field handling.

MCP server for verifying narrative consistency and querying story-state facts in DeepSeek Harness, exposing read-only ledger tools for canonical evidence and continuity checks.

Enables personal AI agents to store and recall durable, private, human-readable relationship memory about people in a user's life, using Markdown as canonical storage with disposable SQLite and vector indexes for fast retrieval.

MCP server that enables AI agents to search, fetch, and analyze a self-maintaining markdown knowledge base with provenance, drift detection, and canonical definitions.

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.

Enables MCP clients to create and manage long-form story projects with isolated databases, persistent drafts, canonical continuity checks, controlled updates, and local semantic retrieval through MCP tools, resources, and prompts.

Enables humans and AI agents to share canonical, versioned knowledge through MCP, with auditable provenance, review workflows, and reconciliation.

Enables AI agents to read, search, and preview governed markdown memories with explicit state and sensitivity, plus quarantine-only write, while never mutating canonical memory or exposing undeclared content.

Enables AI agents to query databases correctly by serving governed context over MCP, including canonical metric definitions, relationships, business meaning, and guardrails, so answers come back with resolved definitions, fired filters, freshness, and a trust score instead of guesses.

MCP server for the governed knowledge layer, enabling agents to query canonical entries, retrieve conflicts, and manage proposals with strict tenant isolation and audit.

Enables LLMs to read a user-owned, local-first memory store kept in a portable folder (USB, SSD or laptop), with per-profile permissions limiting what each client can see and access cut off when the pocket is locked or unplugged. Also lets models propose new memories for the user to review and approve, keeping provenance and keeping canonical memory free of direct model writes.