Moxie Docs

Moxie Docs — MCP & Agent Tools

The Moxie Docs Model Context Protocol (MCP) server, the agent skills Moxie Docs installs into your repository, and the moxie-docs CLI that wires it all up — npx moxie-docs setup.

This repo is also the open-source home of the moxie-docs npm package: a setup CLI plus the MCP interface (tool catalog, prompts, server metadata, and skill renderers) you can import. The hosted server, indexing pipeline, and your generated docs stay in the private Moxie Docs service.

Moxie Docs indexes a connected GitHub repository and keeps its documentation alive — generating docs, discovering conventions, tracking documentation gaps and drift, and opening pull requests that keep docs in sync with code. The MCP server exposes that living context to coding agents (Claude Code, Cursor, VS Code, Codex, and any MCP-capable client) so they ground their work in how your repository actually does things — and keep the docs current as they change code.

• Website / dashboard: https://moxiedocs.com
• Human docs for the MCP server: https://moxiedocs.com/mcp
• MCP endpoint: https://moxiedocs.com/api/mcp

This repository is documentation and distribution assets only. The hosted server, indexing pipeline, and your repositories' documentation are not stored here.

Contents

• Quick start
• CLI
• The MCP server
  • Connection
  • Authentication
  • Client configuration
  • Tools
  • Prompts
• Claude plugin
• Skills
  • The moxie-docs skill
  • What Moxie Docs installs into your repository
• Use as a library
• Find the server
• Discovery endpoints
• License

Quick start

The fastest path — from your repository's directory:

npx moxie-docs setup

This signs you in (OAuth in your browser), writes the MCP config for your editor, installs the moxie-docs skill + AGENTS.md guidance, and verifies the connection. After that, your agent reads live context with moxie.get_ai_context before editing and proposes doc updates that land in the same PR.

Prefer to do it by hand? Connect a repository at https://moxiedocs.com, then add the server to your agent with a config block.

CLI

The moxie-docs CLI (Node ≥ 18, zero runtime dependencies) sets up and manages the connection. Run it with npx moxie-docs <command> or install it globally (npm i -g moxie-docs).

Useful flags: --client <name>, --token <dashboard-token>, --repo owner/name, --no-browser, --yes.

How authentication is written. By default setup/config write a URL-only server entry and let your editor perform its own OAuth sign-in on first use — so nothing in your committed config expires. The CLI's own browser sign-in (used for status and the setup smoke-test) stores a short-lived token plus a refresh token under ~/.moxie-docs/ (file mode 0600); it is never written into a client config. If you'd rather pin a static Authorization header, pass a long-lived dashboard token with --token and the CLI writes that instead. The CLI never logs token values, and it refuses to overwrite a client config it can't safely parse rather than discarding your other MCP servers.

The MCP server

Connection

All write tools are proposals — Moxie Docs returns the file path and content for you (the agent) to write into your own branch. Moxie Docs never edits your repository directly through MCP, and never merges. Reads return compact, citation-backed context rather than raw code dumps.

Authentication

Bearer token (available today). Create a token in the dashboard and send it as a header:

Authorization: Bearer <MOXIE_TOKEN>

Moxie Docs stores only the token hash (plus an encrypted copy so you can reveal it), a prefix, scope, and a last-used timestamp. You can reveal, rotate, or revoke tokens from the dashboard at any time.

OAuth 2.1 sign-in (for clients that support it). MCP clients that implement the OAuth authorization flow can connect by signing in through the browser instead of pasting a token — the client discovers the server's OAuth metadata, registers itself dynamically (RFC 7591), and obtains a token via the authorization-code + PKCE flow. Discovery documents:

• Protected resource metadata: https://moxiedocs.com/.well-known/oauth-protected-resource
• Authorization server metadata: https://moxiedocs.com/.well-known/oauth-authorization-server

Both authentication paths resolve to the same token model, so either works with the same tools. Connected applications can be reviewed and revoked from the dashboard.

Client configuration

Most agents accept a remote MCP server with a URL and headers. Replace <MOXIE_TOKEN> with a token from the dashboard.

Claude Code — .mcp.json (or claude mcp add):

{
  "mcpServers": {
    "moxie-docs": {
      "url": "https://moxiedocs.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <MOXIE_TOKEN>"
      }
    }
  }
}

Cursor — .cursor/mcp.json:

{
  "mcpServers": {
    "moxie-docs": {
      "url": "https://moxiedocs.com/api/mcp",
      "headers": { "Authorization": "Bearer <MOXIE_TOKEN>" }
    }
  }
}

VS Code — .vscode/mcp.json:

{
  "servers": {
    "moxie-docs": {
      "type": "http",
      "url": "https://moxiedocs.com/api/mcp",
      "headers": { "Authorization": "Bearer <MOXIE_TOKEN>" }
    }
  }
}

Keep tokens out of source control. Reference an environment variable where your client supports it, or paste the token only into local, untracked config.

Tools

• moxie.get_ai_context: Compact pre-edit briefing: repo status, verified commands, top conventions, open gaps, team notes. Read this first.
• moxie.get_doc_impact: Given the paths you're about to change (and any you're deleting), returns the conventions, gaps, and existing docs whose evidence overlaps them.
• moxie.get_api_context: Given paths you're about to touch, returns structured context for any API endpoints they map to: method, path, schema, and known consumers.
• moxie.review_change: Self-review a change before opening the PR; returns a severity-ranked list of convention breaches, stale docs, undocumented surface, and broken references.
• moxie.get_conventions: Discovered coding conventions, grouped by category, with confidence scores, agent guidance, and source-file citations.
• moxie.search_docs: Semantic + keyword search over generated docs, conventions, gaps, and AI context.
• moxie.get_doc_gaps: Unresolved documentation gaps with severity and the paths they concern.
• moxie.get_documentation_opportunities: Recommended doc work: missing docs, drift repairs, and PR templates.
• moxie.get_documentation_patterns: How the repository organizes and maintains its docs (where new docs belong).
• moxie.list_docs: Paginated, section-grouped table of contents of every generated doc.
• moxie.propose_doc_update: Add or update a doc as part of your current change; returns target path + Markdown to write into branch.
• moxie.propose_doc_removal: Remove a Moxie Docs-tracked doc your change makes obsolete; returns path to delete in branch.

Prompts

The server also exposes MCP prompts that script the common workflows:

Claude plugin

For Claude Code and Claude Cowork, this repository doubles as a plugin marketplace — a one-command way to add the Moxie Docs connector and skill together. The plugin bundles:

• the moxie-docs MCP server (the remote endpoint above), wired up so your client runs its own OAuth sign-in on first use — no token to paste or commit; and
• the moxie-docs skill, so the edit-then-document workflow is available the moment the plugin is installed.

Install it from inside Claude Code (or Cowork):

/plugin marketplace add Jackalope-Dev/Moxie-Docs-MCP
/plugin install moxie-docs@moxie-docs

The first command registers this repo as a marketplace; the second installs the moxie-docs plugin from it. On first use of a Moxie Docs tool, your client opens the browser to sign in, then the tools and prompts above are available. Update later with /plugin marketplace update moxie-docs, and remove with /plugin uninstall moxie-docs@moxie-docs.

Prefer a static token, or a client without plugin support? Use the client configuration blocks or the CLI instead — the plugin, the CLI, and a hand-written config all resolve to the same server and the same auth model.

The plugin's manifest lives in .claude-plugin/ and its server entry in .mcp.json.

Skills

Agent Skills are small, triggered instruction files that teach an agent when and how to use a capability. Moxie Docs publishes one skill, moxie-docs, that wires an agent into the edit-then-document workflow.

The moxie-docs skill

The canonical skill lives in this repo at skills/moxie-docs/SKILL.md and is also served from the website (with a published SHA-256 digest) at:

https://moxiedocs.com/.well-known/agent-skills/moxie-docs/SKILL.md

It tells an agent to read live context before editing (get_ai_context, get_doc_impact), follow the repository's real conventions and verified commands, and propose doc updates/removals that ship in the same PR as the code change — never inventing filler docs.

What Moxie Docs installs into your repository

When Moxie Docs connects a repository it opens one "Add Moxie Docs agent guidance" PR that adds three self-healing, deterministic files (regenerated only when they drift or the repo is renamed — never churning on every index):

The installed skill is the repo-specific variant of skills/moxie-docs/SKILL.md: identical workflow, with your owner/name baked in so multi-repo tokens target the right repository. Everything Moxie Docs writes is deterministic and contains no volatile data — live conventions and commands always come from the MCP server, not the committed file.

Cursor Rules

Moxie Docs publishes native Cursor rule files (.mdc) for Cursor AI Agent mode. The canonical rule lives in this repository at rules/moxie-docs.mdc and can be added to your repository under .cursor/rules/moxie-docs.mdc or imported via cursor.directory.

Use as a library

The package also exports the open-source MCP interface — the backend-independent contract — so you can build tooling against Moxie Docs without depending on the private server. It carries no secrets and no server logic.

import {
  moxieMcpTools,            // the tool catalog (names, descriptions, input schemas, annotations)
  moxieMcpPrompts,          // the document-this-change / fix-stale-docs prompt descriptors
  moxieMcpServerInfo,       // { name, version }
  moxieMcpProtocolVersion,  // "2025-06-18"
  moxieMcpCapabilities,
  buildMoxieMcpServerCard,  // full /.well-known/mcp/server-card.json document
  moxieMcpServerCard,       // canonical server card (tools + prompts included)
  moxieMcpPublicMethods,    // ["initialize", "tools/list", "prompts/list", "resources/list", "resources/read"]
  renderSkillMarkdown,      // ({ repository }) => the moxie-docs SKILL.md for a repo
  renderAgentsGuidanceBlock,// ({ repository }) => the AGENTS.md guidance block
  moxieDocsSkillMarkdown,   // the canonical published skill, as a string
  MOXIE_MCP_ENDPOINT,       // "https://moxiedocs.com/api/mcp"
  MOXIE_SITE_URL,
} from "moxie-docs";

What it does not include: the tool handlers, the indexing/doc-generation pipeline, AI/vector-search, the database layer, or token storage — those remain in the hosted Moxie Docs service.

Find the server

Moxie Docs is listed for MCP clients and directories under these names:

Machine-readable registry metadata for the hosted endpoint is in server.json in this repo.

Discovery endpoints

Moxie Docs publishes a small machine-discoverable surface so agents and crawlers can find the server:

License

MIT © Jackalope Dev. The contents of this repository (documentation, skill files, and templates) are open source. The hosted Moxie Docs service, indexing pipeline, and generated documentation are not part of this repository.