Get Started

Korely MCP

Your agent memory as MCP tools, connect with a URL and a key.

Korely MCP exposes your agent memory store over the Model Context Protocol, so any MCP-capable client (Claude Code, Cursor, Windsurf, VS Code, Codex) can recall and remember through tools. It's a hosted Streamable HTTP endpoint, nothing to install, authenticated by your kor_live_ key. What it stores are typed, bi-temporal facts, not a transcript.

This is the agent store, keyed. Korely MCP lives at https://api.korely.ai/agent/mcp and takes a kor_live_ bearer. Use exactly this URL: an agent key is not accepted on the other MCP path of the API host, /mcp.

Quick setup

Get a key first (one command, Sign up as an agent):

pip install korely-memory
korely init --agent

Then point your client at the endpoint with the key as a bearer token:

claude mcp add --transport http korely https://api.korely.ai/agent/mcp \
  --header "Authorization: Bearer kor_live_..."

{
  "mcpServers": {
    "korely": {
      "url": "https://api.korely.ai/agent/mcp",
      "headers": { "Authorization": "Bearer kor_live_..." }
    }
  }
}

[mcp_servers.korely]
url = "https://api.korely.ai/agent/mcp"
bearer_token_env_var = "KORELY_API_KEY"

Restart the client and the four Korely tools appear.

Available tools

Tool	What it does
`korely_get_context`	The recall call. Assembles the end user's currently-valid typed facts plus the most relevant memories into a prompt-ready block. Call before answering.
`korely_add`	Remember a decision, preference, or fact, Korely extracts the typed triples. Call after something durable is settled.
`korely_get_facts`	Read the typed `(subject, predicate, object)` facts. `as_of` reconstructs a point in time; `include_invalidated` shows superseded facts.
`korely_search`	Semantic vector search over the raw memories, when you want the source rather than the assembled block. Takes `min_score` like `POST /v1/memories/search`.

Every tool takes an optional user_id to scope to one end user (unlimited per tier). The tools map onto the same REST endpoints the SDK uses, one store, every surface.

Verify it

A quick reachability + auth check, the same key as a bearer:

curl https://api.korely.ai/v1/ping \
  -H "Authorization: Bearer kor_live_..."
# {"ok": true, "tier": "hobby", "region": "eu-hel1", "processing_region": "global", "scopes": [...]}

In your client, ask it to recall something for a user, then to remember a new fact, then recall again, it should call korely_get_context and korely_add on its own.

Local stdio server (alternative)

Prefer a local process over the hosted endpoint, for a client that only speaks stdio? The same four tools ship as a stdio server, korely-mcp, in the Python package. It is a thin client, not an offline store: every tool call goes to the REST API at api.korely.ai with your key, so it needs the network like the hosted endpoint. Since 0.1.16 it needs no extra dependency and runs on Python 3.9 or later; the [mcp] extra is kept, empty, so the install line below keeps working:

pip install 'korely-memory[mcp]'

korely-mcp reads the key from ~/.korely/config.json (written by korely init) or KORELY_API_KEY. Same tools, same store, it just runs locally and calls the REST API for you. See Vibecoding for the full coding-assistant walkthrough.

What's next

Wire the memory into your own agent: the Quickstart and SDK reference.
Understand the moat: temporal facts and the graph.