Hark
HOW IT WORKSCONNECT YOUR TOOLS
Back to Connect
Connect

Connect Claude Code to Hark (MCP memory server setup)

Add Hark's MCP server to Claude Code so every session starts with your project's decisions, current state and next step already loaded.

MCP endpoint
https://harkstudio.io/mcp

Sign in to Hark to connect a client. Personal tokens and per-account details live inside the app.

Claude Code (CLI)

Recommended: install the Hark mod — starts briefed, ends with a handoff. Or connect with one command.

Install the Hark mod (recommended · Early access)

The mod brings the project brief into every session, keeps the plan through compaction, asks before edits that touch an agreed decision, and writes the handoff when you stop. Needs Claude Code 2.1.287 or newer.

In a Claude Code session
/plugin marketplace add Hark-Studio/hark-mod
/plugin install hark-memory@hark

Use Connections → Access keys → Claude Code preset to make a pairing code. Have your agent exchange the code and store the returned key in the plugin’s sensitive setting, never in chat. Link the project and check /hark brief.

Open secure plugin configuration
/plugin configure hark-memory@hark
Link the repo to its Hark project (use your project's code)
mkdir -p .hark && echo V-012 > .hark/project
Full guide: the Hark mod for Claude Code →

Without the mod

1. In a terminal:

claude mcp add --transport http hark https://harkstudio.io/mcp

Add --scope user to make it available in every project, or --scope project to share it via .mcp.json with teammates.

  1. Start a session: claude. On first tool use a browser tab opens — sign in with your Hark account, then approve on the consent screen.
  2. Check: claude mcp list should show hark as connected. Inside a session, /mcp shows status.
  3. Optional shell hooks (brief on start, handoff on stop): curl -fsSL https://harkstudio.io/install.sh | sh -s -- V-012

First prompt to try: "Use Hark to list my workspaces, then create a project called Test in <workspace>."

Verify it works

Ask your client: "List my Hark workspaces." Expected: your workspace names.

Then: "Create a project called Connection test in <workspace>." Expected: a new V-### appears in the app and the activity log shows the source ("via Claude Code", "via Codex", etc.). Delete the test venture afterward.

Troubleshooting

  • "Unauthorized request origin" — the client origin isn't allowlisted; retry from the latest app version, or email hello@harkstudio.io.
  • Consent screen loops / stale token — remove the connector in the client, sign out of Hark, sign back in, re-add the connector.
  • Tools list is empty — the connector isn't enabled for this chat (Claude and ChatGPT require enabling it per conversation).
  • Plan cap error — you've hit the monthly agent-call cap for this workspace; see billing.
  • Old endpoint — anything pointing at a lovable.app URL must be updated to harkstudio.io/mcp.

What Hark keeps clear

Evidence on every line

Every record shows Agreed / Observed / Proposed and a source you can open: where did this come from? Agreed means accepted, not independently verified. Observed is reserved for system evidence such as a merged pull request. An agent's claim is never shown as verified simply because it was accepted.

Learn more about Evidence on every line

Repo-native rules

Once linked and selected as the source, the repo's CLAUDE.md or AGENTS.md is authoritative. Hark mirrors it on pushes and retains history rather than authoring competing edits. Optional .hark/ export carries accepted handoff state and decisions into the repo. Repo activity suggests drafts with commit evidence. Agent briefs include mirrored instruction documents and linked repo metadata. Arbitrary repo-document browsing is not exposed by the current tools: Hark never serves source code. Automatic session hooks and compaction protection in the Hark mod are Claude Code-only; other tools follow their connection guide and explicit session tools.

Learn more about Repo-native rules

Scoped, expiring agent access

New agent keys default Propose: suggest changes, never approve them. An eight-character pairing code expires after 15 minutes and works once; no key is pasted into a setup chat. One-link agent approval asks you to sign in, choose permissions, projects and expiry, then approve. The agent still completes pairing. Keys normally expire after 90 days and can be revoked or rotated. The separate show-once Copy key path is for private storage, not chat.

Learn more about Scoped, expiring agent access
SIGN IN TO CONNECT