Canonic MCP Server

The context layer that lets AI agents query your data correctly. Point canonic at your database and it builds the context an agent needs to answer data questions accurately: definitions, relationships, business meaning, and the guardrails that stop confidently-wrong answers. It keeps that context up to date as your data changes, and it never touches your warehouse beyond reading it.

People who work with context layer for ai and data agent and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-30 · ★ 3 · #212 OF 998 MAINTAINED OTHER · VERIFIED 2026-09-30

NOASSERTION · Python servers · how we verify → /methodology

01 · Install Canonic

Claude Code

claude mcp add mischuh-canonic -- uvx canonic

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "mischuh-canonic": {
      "command": "uvx",
      "args": [
        "canonic"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license no standard license detected - usage rights unclear; check the repo before commercial use

pypi package canonic - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.mischuh is GitHub-verified and matches the repo owner

03 · What Canonic can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.28.0 · 2026-09-28

0.28.0 (2026-09-28) · register canonic with the MCP registry

v0.27.1 · 2026-09-26

0.27.1 (2026-09-25) · add marketplace keycloak guide and cross-link examples

v0.27.0 · 2026-09-24

0.27.0 (2026-09-24) · add unauthenticated /livez and /readyz probes and --foreground

04 · Who maintains Canonic

canonic is maintained by mischuh. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

category
other - ranked #212 of 998 actively-maintained other servers as of 2026-09-30.
release cadence
10+ releases in the last 90 days (latest 2026-09-28)
registry
io.github.mischuh/canonic (active, first published 2026-09-28)
packages
pypi:canonic

06 · Canonic FAQ

What is Canonic?

The context layer that lets AI agents query your data correctly. Point canonic at your database and it builds the context an agent needs to answer data questions accurately: definitions, relationships, business meaning, and the guardrails that stop confidently-wrong answers. It keeps that context up to date as your data changes, and it never touches your warehouse beyond reading it.

Is Canonic still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-30 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Canonic?

Run `uvx canonic`. You can also paste the ready-made client config above.

Does Canonic run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Canonic

More MCP servers to compare · AI CLI MCP · Mlab Sh · PDF Modifier · Clipboard MCP · Molpha MCP

More Python MCP servers · Agenticorg · Paper Banana CN · Terminal MCP · Py Scrappy · Hive Vault · see all