Claude Web & Cowork

Claude has several surfaces, and they behave differently. This page covers the two connector-based ones:

• claude.ai chat in the browser, ordinary Claude conversations
• Claude Cowork, Claude's agentic workspace

For the complete Cowork click path, permissions, verification, recovery, upgrade, and removal, use the dedicated Claude Cowork installation guide. For the coding CLI, see Claude Code, which is the Claude surface with deterministic hook-based memory.

Which surface am I using?

There is no MemoryRouter Chrome extension, and none is needed, a remote connector is officially supported and avoids browser and page permissions entirely.

Prerequisites

• A MemoryRouter account and permission to connect the intended vault.
• A Claude account with custom-connector access and, on managed workspaces, administrator approval.
• Browser access for OAuth sign-in. Do not enter a provider key or Memory Key into Claude's OAuth client-secret field.

Connect the connector

Both surfaces use the same remote MCP connector:

https://mcp.memoryrouter.ai/mcp

The Review and connect link may prefill Claude's connector review form. That is only a convenience boundary: it does not silently add the connector, approve its URL, complete OAuth, select a vault, or enable it for a chat.

1. Open Customize → Connectors. On an individual plan choose + → Add custom connector. On Team/Enterprise, an Owner first adds it under Organization settings → Connectors → Add → Custom → Web, then members return to Customize and choose Connect.
2. Add the custom connector with the URL above.
3. Leave advanced OAuth client ID and secret empty, discovery and dynamic registration handle it.
4. Sign in and choose the vault for this connection.

Cross-session proof

1. Enable the connector in a Claude conversation. Ask it to store: "The synthetic demo project's release phrase is ORCHID-7419."
2. Approve the tool write and verify that store_memory succeeded.
3. Open a fresh conversation with the connector enabled and ask: "Search MemoryRouter for the demo project's release phrase."
4. Confirm ORCHID-7419 appears in the tool result. Do not copy the earlier conversation or repeat the answer in the question.

For read-only setups, seed the fact from a writable connection to the same vault first. Claude's native memory and MemoryRouter are separate systems; test the connector's search result, not merely a plausible response.

Plan availability

Custom connectors and Skills are available across Claude plans. Plugins are paid-plan packaging, and Team/Enterprise generally require an owner or administrator to provision connectors for members.

Anthropic changes plan capabilities over time; verify against Anthropic's current documentation before relying on a specific row.

What is included

The live connector exposes exactly ten tools: search_memories (with tier and importance filters), date_search_memories (time-window recall with the same filters), store_memory, memory_status, forget_all_memories, the reflection tools consolidate_memories, commit_reflections, inspect_memory, delete_memories, and the compatibility alias search. Resources, when the host exposes them, are memory://vault/stats and memory://vault/recent.

claude.ai chat (browser), version 1.0.0:

• Remote OAuth connector definition
• Read-write and read-only skill packages
• Scoped Project instructions for personal, project, and organization use in each mode
• An optional no-code plugin package for paid plans

Claude Cowork, version 2.0.0:

• Hosted OAuth connector configurations (read-write and read-only)
• A behavioral skill with explicit scope handling
• Two plugins, read-write and least-privilege read-only
• A marketplace bundle and enterprise managedMcpServers administrator templates
• Deterministic, hash-verified archives

Read-only is behavioral unless enforced

A read-only skill package tells Claude not to write. That is policy, not a security boundary. Real enforcement comes from either:

• connecting with only the memories:read scope, or
• blocking the store_memory tool through Claude organization policy.

The read-only plugin pins memories:read in its MCP configuration, which is the enforceable version.

Model-directed limits

The current MemoryRouter browser and Cowork packages install no deterministic lifecycle hook that forces recall or capture. Claude chooses when to use the tools, so recall and saving are not guaranteed on every turn.

Skills and Project instructions improve how consistently Claude uses memory, but they are orchestration, never authorization. For guaranteed automatic memory, use Claude Code or Codex against the same vault.

Vaults and projects

One connection is bound to one vault, chosen during OAuth. To change vaults, disconnect and reconnect.

Cowork's skill supports explicit conversation-local scopes (personal/default, project/<handle>, org/<handle>) and fails closed: if a write is requested with no active scope, it asks rather than guessing. Handles are never inferred from a folder, filename, or repository.

These handles are compatibility labels. The server accepts no scope argument, so for strict isolation use a dedicated vault per project or organization.

Enterprise and admin setup

For Team and Enterprise, an owner or administrator typically adds the connector for the organization. Cowork ships managedMcpServers templates, including a read-only variant that blocks store_memory and delete at the policy layer.

Those templates are administrator inputs for managed deployment, they are not files consumed by standard claude.ai.

Manual acceptance still required

These steps cannot be automated and must be completed in a real account:

• Interactive OAuth sign-in and vault choice
• Organization-level connector distribution and permission enforcement
• Plugin or marketplace acceptance, if you distribute the packages that way

Deletion

Per-memory deletion on Claude surfaces uses the delete_memories tool: ids come from search or inspect results, the memories:delete scope is required, and Claude must show you what will be deleted and get explicit confirmation before calling it. A store_memory receipt is not a deletion ID. The dashboard works too, and the underlying API endpoint is documented at Reflections.

Whole-vault deletion via forget_all_memories requires the memories:delete scope and the exact phrase DELETE ALL MEMORIES. Claude must ask for explicit confirmation first, and "forget that" is never treated as consent to erase a vault.

Troubleshooting

Connector missing or greyed out. Plan limit or admin policy. Free plans allow one custom connector; Team/Enterprise may require owner provisioning.

Claude ignores memory. Model-directed behavior. Ask explicitly, or add the skill and Project instructions.

"Insufficient scope" when saving. The connection is read-only. Reconnect and approve memories:write; a 403 is not retriable.

Vault statistics unavailable. Call memory_status, or read memory://vault/stats if the host exposes resources. Claude should never estimate counts.

Next steps

View the integration · Create an account · All integrations