Read and write one codebase ontology kept as Markdown in the repository.
io.github.wlsdks/ontology-atlas — MCP Server Model Context Protocol
This MCP server reads and writes a single codebase ontology that is stored as Markdown within its repository. The server’s role is to operate on that ontology representation, enabling retrieval and updates of the ontology content maintained in the repo.
🛠️ Key Features
Read one codebase ontology stored as Markdown in the repository
Write (update) the same ontology stored in the repository
🚀 Use Cases
Access an ontology maintained as Markdown for a specific codebase
Persist ontology changes back to the repository’s Markdown source
⚡ Developer Benefits
Centralized ontology representation in a Markdown repository file
Consistent interface for reading and updating the same ontology artifact
⚠️ Limitations
Scope appears limited to a single codebase ontology stored as Markdown in the repository
Coding agents now change code faster than a team can keep a picture of it in
their heads. Atlas keeps that picture beside the code: what each part is for,
which files implement it, what depends on what, and what nobody knows yet. Your
agent reads it before a task and proposes updates after; you keep, correct or
reject each change as a Markdown diff.
Your agent starts with context. Claude Code, Codex, Cursor and Antigravity read the concepts, code paths, dependencies and open questions a task touches, over MCP.
You own the record. One Markdown file per concept in an atlas/ folder, versioned and reviewed in Git like the code.
You decide what is true. Agent proposals stay proposals until you accept them.
It says what it does not know. A line on the map is a declared relationship, not proof of runtime impact; missing evidence shows as unknown, never as safe. Compact task handoffs preserve whole uncertainty statements or report omissions with the document reads needed to inspect them. Initial analysis also excludes literal Markdown examples and marks truncated document evidence for review with a hash-bound original-source follow-up. Task matching and navigation use authored evidence; code examples, hidden comments and blockquotes cannot supply capability claims or work coordinates.
See it
Projects — every project and how much of it has code evidence.
Library — documents in, cited wiki pages out.
Planning — read a project folder's Markdown in place, without copying it.
Briefing — what changed in a period, as pull requests, commits and files.
Analysis — which parts depend on which, with the evidence beside each claim.
Git — the exact Markdown diff before you save.
Harness — what your repository tells, blocks and watches for agents.
Automations — scheduled checks that keep the folder current.
New in v1.9: Git and pull request briefings, which read a repository's pull requests, commits and files in separate views, and Planning, which reads a project folder's Markdown in place. See the releases.
A few things worth knowing before you start:
The map shows declared relationships, not proof of runtime impact; its key explains every mark and direction. Map
An empty folder offers its start actions, and a failed start can be retried without overwriting files. Popup tours are retired. First run
Library setup and checks need the app; a browser offers the app or adding files. Library
Planning is read-only and works in the macOS app on a folder you choose; it shows Markdown and PNG/JPEG images. Planning
Git's send-only action does not commit new file changes; it asks you to review a stale folder or branch again. Pull can change files across the repository. Git
Before a folder is connected, the app keeps Library, Planning, Agents and Briefing reachable. Features
Open a folder. Atlas reads its Markdown in place, or starts an atlas/ folder in your repository, and shows the path before it writes anything.
Connect your agent. In Agents › MCP, press Connect for your tool, restart the agent, and ask about your next task.
macOS (Apple Silicon) is signed and notarized and carries the MCP server inside the app. Windows x64 is an unsigned beta. On Linux, use the browser version or run the CLI and MCP server from a source checkout. Releases list each version's files and checksums.
How it works
text
your-repo/
├── src/
└── atlas/ ← cloned, branched and reviewed with the code
├── project.md
├── domains/ capabilities/ elements/
├── sources/ documents kept exactly as they arrived
└── wiki/ pages written from those sources, every fact cited
A Markdown file whose frontmatter has kind: is one concept. Its uid never
changes, its slug is its current address, and its path names the code it
describes. The map, documents, Library, Insights and Git screens all read these
files.
Your agent reaches the folder two ways:
MCP: the agent starts the Atlas MCP server, which reads and writes the folder on disk, even with the app closed. Connect an agent · MCP reference
ACP: Claude Agent and Codex also run in the app's own chat; each write waits until you allow it. Agents
A project's source-path repair opens the affected concept and recorded relative path; stale or missing targets require remeasurement.
Project checks distinguish a document changed since its last meaning review from malformed input. They ask for review and explicit re-finalization; supported code paths and saved changes do not accept the meaning. Analysis filters capabilities by changed, missing or unchecked source evidence while keeping the selected claim open.
Codex's locally configured permission profiles are excluded from the in-app mode picker because their effective approval behavior is not disclosed. Read-only startup stays required; an unsolicited move into a profile is reported as unverified, without claiming the runtime was stopped.
The full project editor confirms leaving unsaved changes inside the app, so Cancel and Back work in the macOS WebView as well as the browser.
The Analysis review summary lists the agent-authored concepts without a recorded human review, with exact concept links and five more entries per expansion. Opening a concept does not mark it reviewed.
Analysis compares recorded dependencies between responsibilities, then opens the exact concepts and declaring document beside the selected claim. Implementation records, unchecked source and missing explanations stay distinct. In the macOS app, documents and cited files can be dated in their respective bound Git repositories; missing access or history stays unknown, and a folder chosen for reading must match the existing connection. Analysis
Local-first
The installed app's Briefing prototype opens a chosen Git repository without requiring an ontology. Pull requests, commits and files have separate reading views. An explicit public GitHub read lists PRs updated in the selected local dates, including open and closed work; a moving, paginated list may be incomplete. Each PR original is attributed and remains inspectable. Commit-only summaries use a local model, while the separately labelled earlier combined briefing retains matched PR descriptions and earlier results. Private PR access and in-app ACP explanations are not yet available in the PR inventory. Failed reads retain the session's earlier results. Inspect individual commit messages and bounded, endpoint-based file comparisons inside Atlas. Author records and optional ontology grouping do not establish verified behavior changes. Change briefing
No backend, account or telemetry. The folder stays plain Markdown on your disk.
Model calls with your API key or a local model are opt-in, and each records its destination in .ontology-atlas/llm-audit.jsonl.
A connected coding agent may send your prompt and what it reads to its own provider; Atlas's log does not cover those transfers.
Atlas is early. Our benchmark has not yet shown better answers with Atlas, and
Atlas was slower (the correction).
Construction trials, their failures and limits are in
the construction measurements.
Read CONTRIBUTING.md; external pull requests come from forks.
AGENTS.md is the contract for people and agents alike.
bash
pnpm install
pnpm dev
pnpm checks:changed -- --run
pnpm pr:land <number> merges a reviewed pull request and keeps its original
commits. Development checks covers choosing checks,
CI internals and lane budgets.
Pre-push checks the commit being pushed and runs affected lint, unit and Node
tests in parallel with the relevant cheap checks. CI owns browser, full contract
and dependency-graph verification. Test-only edits to CI tooling run their
regressions without starting unrelated product suites; changes to the planner
implementation still require exhaustive CI.
Repository commands
Command
What it answers
node scripts/ci/run-playwright-ci.mjs --help
Browser shard options, without discovering or running tests; unknown options fail before execution
pnpm agents:check
Each harness's instruction files are valid; Codex and Claude files need not match
pnpm brand:sprites
Rebuild Moru sprites, 70 animation exports, 16 poses and compass sizes from retained project sources; inspect assets/brand/moru/preview.html
pnpm brief:new -- --slug=<slug> --owns=<path,...>
A delegation brief with the port, scratch, checks and merge lines filled in
pnpm build:static
Reuse out/ only for matching build inputs; fail without a reuse stamp if inputs change during the build
pnpm bundle:plan · pnpm bundle:prune
Plan merging several branches as one, then prune the branches main contains (/merge)
pnpm checks:changed
Which gates this change needs
pnpm conflicts:scan
Which open pull requests change the same files as this branch, and whether a trial merge conflicts
Dry-run a merge, or merge queued pull requests until the queue is empty
pnpm pr:land <n> · pnpm pr:queue
Queue a pull request to merge (green ones merge together behind one CI run), and show the queue
pnpm review:facts -- --base=<ref>
The mechanical facts a reviewer would otherwise count by hand: line growth, 800-line files, export and dependency changes, untouched sibling tests, security paths
pnpm seo:check
After pnpm build: every sitemap URL in out/ canonicalizes to itself, / and each locale root point at /{locale}/download/, and titles and descriptions are unique per locale
pnpm typecheck
Types across every file, with Next's generated route and page types
Prepare an interactive state with an optional local module, then measure rendered facts per width: horizontal overflow, occluded or unreachable controls, small touch targets, off-ramp type/radius/shadow values, low contrast, unequal repeated sets, scroll-end reserve
Builds and serves the static export on a free port (or uses --url), opens each route with a vault attached, and prints one screenshot path per route and width
Use --scope=<selector> to audit one visible modal or region. The selector must match exactly one visible element; the report includes its measured element count.
At folder entry, Moru greets, offers a small folder and waits. Play gives way to the existing waiting view when a folder opens. The download invitation uses a separate welcome. Hops travel only while airborne; hovering lets a hop land before Moru waits. Pet Moru for a brief shy, clap, dance, thinking, pondering, hearts, laughter or flipper-groove response; right-click Moru or press Shift+F10 for pause/resume. No playback button sits beside the character. Reduced motion keeps a still expression.
New 32-pose gestures add a bow, flipper five and hat greeting to petting; the download welcome also offers a fish trick. A small wordless bubble answers touch with a heart, note or sparkle and occasionally accompanies a return hop. Waiting stays quiet. Peekaboo, rosy temper and bubble play are available in the catalogue.
Moru now keeps its rounded shape during the small nod. Play combines three phrases with different quiet rests; petting varies the order while avoiding the two most recent gestures. Waiting remains gentle and stationary.