OwnContext

简体中文

Status: preview

Verified locally on macOS with Node 24: lint, type checking, unit/integration tests, a dry-run Worker build, and the account-free demo/setup preview from a fresh local clone. Tests cover read/write scopes, correction, duplicate suppression, stale-SHA rejection, and MCP Streamable HTTP against the Worker handler with fake GitHub/KV. These checks do not exercise a deployed service.

Still pending: deployment with real GitHub/Cloudflare accounts; live OAuth sign-in, consent, token refresh and revocation; cross-client read/save/correction/conflict acceptance in Claude Code and claude.ai; and a real-client recording. Linux CI is configured; native Windows is unverified. Treat this as preview software, not a completed live-client release.

OwnContext is a single-user, self-hosted MCP server that lets AI clients read and correct the same plain-text context in your private GitHub repository.

Related MCP server: github-mcp-server

Why it exists

Context should survive a change of AI client. Markdown and Git keep it portable; stated and inferred labels separate your statements from deductions; source references make an answer traceable; SHA-checked updates let a client correct a note without overwriting a newer edit.

The server supplies storage and tools. Your client decides what to read and how to merge a correction. Labels and source references are client-supplied, not independent verification of a claim.

A 30-second look

Recording placeholder: save a synthetic preference in one client, read it in another, correct it, then show a rejected stale edit. A recording has not been published. The local demo below exercises this sequence today.

Try the demo first

From a checkout of this source, with Node.js 24.11 or newer and npm:

npm ci --registry=https://registry.npmjs.org
npm run demo
npm run setup -- --dry-run

After dependency installation, the demo and setup preview run offline. The demo uses synthetic notes and two in-memory tool clients. It prints a Markdown correction and verifies duplicate suppression and a stale-SHA conflict. It does not start an HTTP server or change a repository.

Set up your own instance

Read the quickstart and permissions before running:

npm run setup

Live setup needs Git, GitHub CLI, your GitHub and Cloudflare accounts, a GitHub OAuth App, and a repository-scoped token. It inspects those accounts and asks you to type deploy before creating resources or publishing the Worker. It can create a private notes repository, add missing synthetic template files, provision OAuth KV, and deploy. Existing template files are preserved.

Your endpoint is https://YOUR-WORKER.YOUR-SUBDOMAIN.workers.dev/mcp. Start with read-only consent. Writes require a separate checkbox on the consent page.

Clients and platforms

Other clients must support the same HTTP transport and OAuth flow. No stdio transport or legacy SSE endpoint is included. See compatibility for the exact verification boundary.

Data flow and privacy

MCP client → your Cloudflare Worker → your private GitHub repository
                ↓
            OAuth state in Workers KV

GitHub sign-in identifies the one allowed account. A separate fine-grained token gives the Worker repository access. Notes, corrections, and optional selected snippets remain in private Git history. Cloudflare processes requests; GitHub stores the files; a connected AI client can send returned context to its model provider under that provider's terms.

OwnContext makes no model calls and has no analytics service or automatic capture hook. Tool logs contain the tool name and status, not note bodies. Provider and CLI logging have their own controls. There is no application-level end-to-end encryption or automatic redaction. Privacy and data flow.

Tools

• Read: get_context, search, read.

• Write, with explicit OAuth write consent: remember, update_note.

• Optional, disabled by default: capture_conversation, log_decision, log_meal.

update_note requires the SHA from read, or null to create. A conflicting content change is rejected; the client must re-read and merge. remember suppresses exact repeated facts. Optional capture stores only the snippets the client supplies, with stable batch identifiers for retries; it does not collect conversations by itself.

Costs

The software is free under Apache-2.0. You supply your own GitHub and Cloudflare accounts and pay any applicable storage, request, or platform charges. Free-tier eligibility and quotas depend on those providers. AI client subscriptions or model usage are separate. OwnContext does not set up billing or promise a zero-cost deployment.

Limits and non-goals

• One allowed GitHub identity and one private repository; no team accounts or per-folder OAuth scopes.

• Plain UTF-8 text, at most 200 KiB per readable file; keyword substring search, not semantic or vector search.

• GitHub API latency and quotas apply. Search is paginated; a page with no matches can still have a continuation cursor.

• Sources and stated/inferred labels require client judgment. Corrections are client-authored; there is no automatic truth resolution.

• Rules files and me/values.md are protected from MCP writes. Git history retains old content; deleting a current file does not erase its history.

• No delete tool, scheduler, background collection, full conversation export, multi-file transaction, or hosted service operated by the maintainer.

Documentation

• Quickstart

• Privacy and data flow

• Permissions and scopes

• Costs and limits

• Local benchmark method and raw samples (npm run benchmark; in-memory GitHub substitute, not deployed latency)

• Upgrade and rollback

• Recovery and uninstall

• Compatibility

Development and license

npm run lint
npm run typecheck
npm test
npm run check:release
npm run build

See CONTRIBUTING, SECURITY, and Code of Conduct. Licensed under Apache-2.0, copyright clean99. See NOTICE.