Connect via MCP

Jackdaw exposes your knowledge graph as a Model Context Protocol (MCP) server. Any AI that supports MCP — Claude.ai, Cursor, Claude Code, and more — can pull your context on demand.

Endpoint

https://mcp.jackdaw.so/mcp/

Jackdaw uses OAuth 2.0. When you connect a new AI client, it registers itself and walks you through a standard consent flow — you grant it a token with the scopes you choose. There's nothing to paste by hand.

Scope	What it allows
`jackdaw:read`	Read your context and search your subjects
`jackdaw:write`	Propose structured facts or supported actions (which still require your approval)

Tools

The MCP server exposes read tools plus two structured proposal tools. It does not let a connected model generate or edit wiki prose.

`get_context`

Retrieves a relevant slice of your knowledge graph for the current conversation. Pass the user's actual question as query so Jackdaw can surface the right facts.

{ "query": "what projects am I working on this week?" }

`remember`

Stages a fact for your review. Nothing is saved until you approve it in your inbox.

{ "key": "preferred language", "value": "TypeScript", "kind": "preference" }

kind is one of: fact, preference, decision, goal, constraint, rejection, correction.

`search_subjects`

Search your knowledge graph by keyword or meaning.

{ "query": "Sentinel Dev" }

`read_subject`

Read the human-authored notes and structured knowledge for one subject. Pass a subject's name, or a key returned by search_subjects.

{ "key": "Sentinel Development Group" }

`get_instructions`

Read the approved coding-agent instruction pack for the current workspace or repository.

`propose_action`

Stage a supported action for review. Nothing runs until you confirm it, and any irreversible final step remains yours.

Connecting Claude.ai

In Claude.ai, open Settings → Connectors (you'll need a plan that supports custom connectors).
Add a custom connector with the URL https://mcp.jackdaw.so/mcp/.
Authorize the OAuth flow.
Claude can now call get_context, remember, and the rest in any conversation.

Best practice: pair MCP with the hook

If you use Claude Code, install the Claude Code hook alongside MCP. They cover different paths: MCP lets the model pull your context when it decides to call get_context, while the hook pushes the relevant slice into every prompt automatically — so your context is there even on the turns the model wouldn't have thought to ask for it. Running both means you're covered either way.

The one rule that matters

However you connect an AI, the single most important behavior is this: call get_context before answering anything about you — and pass the user's real question as the query, not a generic string. That's what makes the AI ground its answer in your actual context instead of guessing.

On this page