Living docs and MCP context for GitHub repos — conventions, gaps, and source-cited pages on merge.
io.github.Jackalope-Dev/moxie-docs MCP Server
The Moxie Docs MCP server provides living docs and context for GitHub repositories, focusing on conventions, gaps, and source-cited pages related to merge decisions. It exposes a model context protocol to align agent behavior with repository documentation and MCP conventions.
🛠️ Key Features
Living docs and MCP context for GitHub repos
Conventions, gaps, and source-cited pages on merge
Tooling integration with MCP, agent skills, and CLI wiring
Repository-level model context to guide automated decisions
Lightweight, publish-ready readme excerpts and docs
🚀 Use Cases
Generate and maintain MCP context for code reviews and merges
Surface source-cited pages and conventions to agents
Enable consistent agent behavior across repositories
Quickly onboard new teams with MCP-driven docs
⚡ Developer Benefits
Clear MCP context model for repository learning
Reusable tools and CLI (moxie-docs) to wire MCP with repos
Easy integration into CI/CD for documentation-driven decisions
Open structure for extending conventions and gaps
⚠️ Limitations
Focuses on MCP context and docs; may not cover all repository toolchains
Dependent on repository-provided readme excerpts and source citations
Readme excerpt quality varies by repo; may require normalization
Topics
aiai-skillsai-toolsdocumentationmcp
Captured live from the server via tools/list.
moxie.get_conventions
Get the coding conventions Moxie inferred for the repository. Read-only; no side effects. Returns a Markdown list grouped by category (e.g. testing, structure, docs, review); each convention has a title, summary, confidence score, agent guidance, and the source file paths that evidence it. Use this for the general rules to follow; when you already know the files you're about to edit, prefer moxie.get_doc_impact for conventions scoped to those paths.
Parameters2
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
category
string
optional
Optional category filter, such as testing, structure, docs, or review.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"category": {
"type": "string",
"description": "Optional category filter, such as testing, structure, docs, or review."
}
}
}
moxie.search_docs
Keyword and semantic search across the connected repository's generated docs, conventions, documentation gaps, AI-context notes, and indexed code. Read-only; no side effects. Returns ranked matches in Markdown grouped into Documentation and Code sections, each with a title, snippet, and source paths. Use for open-ended lookups when you don't know which category holds the answer; when you do, the specific getters (get_conventions, get_doc_gaps, get_documentation_opportunities) are more direct. Omitting query returns recent context instead.
Parameters3
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
query
string
optional
Search phrase or topic. Omit to return recent context for the repository.
limit
number
optional
Maximum matches to return (1-20, default 8).
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"query": {
"type": "string",
"description": "Search phrase or topic. Omit to return recent context for the repository."
},
"limit": {
"type": "number",
"description": "Maximum matches to return (1-20, default 8)."
}
}
}
moxie.list_docs
List the repository's generated documentation as a browsable table of contents - every doc page, not a query-filtered subset. Read-only; no side effects. Returns Markdown grouped by section, each entry with its title, slug, repository path, and source paths, plus the total count and a pagination cursor so you can tell whether more pages remain (no silent truncation). Use this to see what docs already exist before adding one (so you don't duplicate) or to find the slug to pass to propose_doc_update; when you are hunting for a specific topic, search_docs is more direct.
Parameters4
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
section
string
optional
Optional section/collection filter (case-insensitive substring), e.g. "Backend" or "Billing". Omit to list every section.
limit
number
optional
Maximum docs to return (1-200, default 50).
offset
number
optional
Number of docs to skip for pagination (default 0). Use the cursor in the response to fetch the next page.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"section": {
"type": "string",
"description": "Optional section/collection filter (case-insensitive substring), e.g. \"Backend\" or \"Billing\". Omit to list every section."
},
"limit": {
"type": "number",
"description": "Maximum docs to return (1-200, default 50)."
},
"offset": {
"type": "number",
"description": "Number of docs to skip for pagination (default 0). Use the cursor in the response to fetch the next page."
}
}
}
moxie.get_doc_gaps
List the unresolved documentation gaps Moxie found - areas of the codebase that lack docs. Read-only; no side effects. Returns a Markdown list, each gap with a title, severity, summary, and suggested file paths. This is gaps only; for the full prioritized work queue that also includes drift repairs and PR-template work, use get_documentation_opportunities, and to scope gaps to files you're about to edit use get_doc_impact.
Parameters2
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
severity
string
optional
Optional severity filter: high, medium, low, or info.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"severity": {
"type": "string",
"description": "Optional severity filter: high, medium, low, or info."
}
}
}
moxie.get_documentation_opportunities
List the actionable documentation updates Moxie recommends as a prioritized queue: missing docs, drift repairs, and PR-template work. Read-only; no side effects. Returns a Markdown list, each opportunity with a title, kind (documentation_gap | documentation_drift | pr_template), severity, summary, suggested action, estimated files changed, and source paths. Use this to pick the next doc task; it is the superset of get_doc_gaps (which lists gaps only).
Parameters3
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
kind
string
optional
Optional kind filter: documentation_gap, documentation_drift, or pr_template.
severity
string
optional
Optional severity filter: high, medium, low, or info.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"kind": {
"type": "string",
"description": "Optional kind filter: documentation_gap, documentation_drift, or pr_template."
},
"severity": {
"type": "string",
"description": "Optional severity filter: high, medium, low, or info."
}
}
}
moxie.get_documentation_patterns
Get Moxie's summary of how THIS repository organizes and maintains documentation - where docs live relative to code and how they are kept current. Read-only; no side effects. Returns a Markdown list of pattern entries, each with a title, explanation, and source citations. Use this to decide WHERE a new doc should go before calling propose_doc_update; for the list of WHICH docs need work, use get_documentation_opportunities instead.
Parameters1
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
}
}
}
moxie.get_ai_context
Get the compact briefing an agent should read before editing this repository: index status, verified commands, agent tips, top conventions, open documentation gaps, and queued documentation opportunities. Read-only; no side effects. Returns a single Markdown document. Call this first at the start of a task; once you know which files you'll change, follow up with get_doc_impact for path-scoped guidance.
Parameters1
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
}
}
}
moxie.get_doc_impact
Given the file paths an agent is about to change (and optionally a subset being deleted), return the conventions, documentation gaps, and existing/related docs whose evidence overlaps those paths, plus a net-new/undocumented analysis and any removal candidates. Read-only; no side effects. Returns a Markdown report. Call this BEFORE writing code so doc updates land in the same PR; then use propose_doc_update to write a doc, or propose_doc_removal for an orphaned one.
Parameters3
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
changedPaths
array
required
Repository-relative file paths the agent intends to modify (e.g., apps/web/src/app/api/billing/webhook/route.ts).
deletedPaths
array
optional
Subset of paths that are being DELETED. Moxie flags any doc whose every cited source path is in this list as a removal candidate for moxie.propose_doc_removal.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"changedPaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Repository-relative file paths the agent intends to modify (e.g., apps/web/src/app/api/billing/webhook/route.ts)."
},
"deletedPaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Subset of paths that are being DELETED. Moxie flags any doc whose every cited source path is in this list as a removal candidate for moxie.propose_doc_removal."
}
},
"required": [
"changedPaths"
]
}
moxie.review_change
Self-review a change you are about to commit BEFORE opening the PR. Pass the proposed new state of each changed file (and any deleted paths); Moxie returns a severity-ranked list of violations to fix: convention breaches, docs your change makes factually false, net-new API/surface added without docs, and doc references broken by deletions. Read-only; no side effects and no writes. Returns a Markdown verdict (clean | warnings | must-fix) with each finding's location, fix, and - for doc issues - the slug to pass to propose_doc_update. Call this as the final step of the edit flow, then fix findings and re-run.
Parameters3
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
changedFiles
array
required
The files your change adds or modifies, in their PROPOSED new state. Provide newContent (the full new file text) for each; you may also/instead provide patch (a unified diff). Max 20 files per call.
deletedPaths
array
optional
Repository-relative paths your change DELETES, so Moxie can flag docs whose references break.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"changedFiles": {
"type": "array",
"description": "The files your change adds or modifies, in their PROPOSED new state. Provide newContent (the full new file text) for each; you may also/instead provide patch (a unified diff). Max 20 files per call.",
"items": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Repository-relative path, e.g. apps/web/src/app/api/foo/route.ts."
},
"newContent": {
"type": "string",
"description": "The full new contents of the file after your change."
},
"patch": {
"type": "string",
"description": "Optional unified diff for the file (used if newContent is omitted)."
},
"status": {
"type": "string",
"description": "Either \"added\" or \"modified\"."
}
},
"required": [
"path"
]
}
},
"deletedPaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Repository-relative paths your change DELETES, so Moxie can flag docs whose references break."
}
},
"required": [
"changedFiles"
]
}
moxie.propose_doc_update
Propose a documentation file to add or update as part of YOUR current change. Records a new proposal each call (not idempotent) and does NOT modify your repository or open a PR - Moxie resolves the target path and returns the path + Markdown for YOU to write into your working branch, so the docs land in the SAME PR as the code. Returns the resolved target path and the content to write. Provide either targetPath or baseSlug.
Parameters7
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
title
string
required
Short human title for the documentation update.
markdown
string
required
The documentation content (Markdown) to write to the target file.
targetPath
string
optional
Repository-relative path to write the doc to (e.g., docs/billing.md). Omit to resolve from baseSlug.
baseSlug
string
optional
Slug of an existing generated doc to update instead of supplying targetPath.
sourcePaths
array
optional
Code paths this doc documents, for provenance.
reason
string
optional
Why this doc is being added or changed.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"title": {
"type": "string",
"description": "Short human title for the documentation update."
},
"markdown": {
"type": "string",
"description": "The documentation content (Markdown) to write to the target file."
},
"targetPath": {
"type": "string",
"description": "Repository-relative path to write the doc to (e.g., docs/billing.md). Omit to resolve from baseSlug."
},
"baseSlug": {
"type": "string",
"description": "Slug of an existing generated doc to update instead of supplying targetPath."
},
"sourcePaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Code paths this doc documents, for provenance."
},
"reason": {
"type": "string",
"description": "Why this doc is being added or changed."
}
},
"required": [
"title",
"markdown"
]
}
moxie.propose_doc_removal
Propose deleting a Moxie-tracked documentation file that your change makes irrelevant, as part of YOUR current change. Moxie validates the path and returns it for you to delete in your working branch; Moxie itself does not delete files or open a PR - the deletion happens in your branch, so it lands in the SAME PR as the code. Returns the resolved path to delete. Provide either slug or targetPath.
Parameters5
repository
string
optional
The target repository as "owner/name" (e.g. "acme/app"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer.
slug
string
optional
Slug of the existing generated doc to remove.
targetPath
string
optional
Repository-relative path of the doc to remove (must be a Moxie-tracked doc). Use instead of slug.
removedSourcePaths
array
optional
Code paths being deleted that made this doc irrelevant, for provenance.
reason
string
optional
Why this doc is no longer relevant.
Raw schema
{
"type": "object",
"properties": {
"repository": {
"type": "string",
"description": "The target repository as \"owner/name\" (e.g. \"acme/app\"). Always pass this unless your token is scoped to a single repository. Matching is case-insensitive. If omitted when the token serves multiple repos, the call returns the list of repositories to choose from instead of an answer."
},
"slug": {
"type": "string",
"description": "Slug of the existing generated doc to remove."
},
"targetPath": {
"type": "string",
"description": "Repository-relative path of the doc to remove (must be a Moxie-tracked doc). Use instead of slug."
},
"removedSourcePaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Code paths being deleted that made this doc irrelevant, for provenance."
},
"reason": {
"type": "string",
"description": "Why this doc is no longer relevant."
}
}
}
The Moxie Docs Model Context Protocol (MCP) server, the agent skills Moxie 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 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.
This repository is documentation and distribution assets only. The hosted server, indexing pipeline, and your repositories' documentation are not stored here.
The fastest path — from your repository's directory:
bash
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.
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).
Command
What it does
moxie-docs setup
End-to-end: sign in, configure your MCP client, install the skill + AGENTS.md block, and smoke-test.
moxie-docs login
Sign in via the browser (OAuth 2.1 + PKCE) and store credentials in ~/.moxie-docs/.
moxie-docs status
Show your scope, connected repositories, and available tool count.
moxie-docs config <client>
Write the moxie-docs server entry into a client config (claude-code, cursor, or vscode).
moxie-docs install-skill
Install the moxie-docs skill and AGENTS.md guidance into the current repo.
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
Transport
Streamable HTTP MCP
Endpoint
https://moxiedocs.com/api/mcp
Protocol version
2025-06-18
Repository selection
Tools accept an optional repository argument (owner/name, e.g. acme/app). It is required only when a token serves multiple repositories and no single default applies. Matching is case-insensitive.
All write tools are proposals — Moxie returns the file path and content for you (the agent) to write into your own branch. Moxie 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:
code
Authorization: Bearer <MOXIE_TOKEN>
Moxie 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:
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.
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_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-tracked doc your change makes obsolete; returns path to delete in branch.
Tool
Purpose
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 - and flags net-new/undocumented surfaces.
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/features.
moxie.review_change
Self-review a change before opening the PR; returns a severity-ranked verdict (clean / warnings / must-fix) covering 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 the target path + Markdown to write into your branch.
moxie.propose_doc_removal
Remove a Moxie-tracked doc your change makes obsolete; returns the path to delete in your branch.
Prompts
The server also exposes MCP prompts that script the common workflows:
Prompt
Purpose
document-this-change
Runs the doc-impact check on your changed paths and walks you through proposing the doc updates so they land in the same PR.
fix-stale-docs
Finds the repository's open documentation gaps and drift opportunities and repairs them through Moxie.
review-before-finalize
Runs Moxie's guardrail over your diff before you open the PR to catch convention breaches, stale docs, undocumented surface, and broken references.
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.
The first command registers this repo as a marketplace; the second installs the moxie-docs plugin from it. On first use of a Moxie 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.
Agent Skills are small, triggered instruction files that teach an agent when and how to use a capability. Moxie 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:
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 installs into your repository
When Moxie connects a repository it opens one "Add Moxie 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):
File
Purpose
AGENTS.md
A short, always-on pointer block (between <!-- moxie-docs:start --> / <!-- moxie-docs:end --> markers) telling any agent to use the MCP server and the moxie-docs skill. Human-added content outside the markers is preserved. See templates/AGENTS.md.
.claude/skills/moxie-docs/SKILL.md
The repo-specific moxie-docs skill for Claude Code.
.agents/skills/moxie-docs/SKILL.md
The same skill for .agents-aware clients.
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 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 without depending on the private server. It carries no secrets and no server logic.
ts
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"]
renderSkillMarkdown, // ({ repository }) => the moxie-docs SKILL.md for a repo
renderAgentsGuidanceBlock,// ({ repository }) => the AGENTS.md guidance block
moxieDocsSkillMarkdown, // the canonical published skill, as a stringMOXIE_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 service.
Find the server
Moxie Docs is listed for MCP clients and directories under these names:
