Point any MCP client at the registry and it gets metagraphed as callable tools: subnet discovery and comparison, per-subnet health and economics, OpenAPI schemas for every registered subnet API (callable through the registry itself), chain blocks/extrinsics/events, account lookup, and grounded question-answering — the same data every REST route serves, shaped for agents. Bittensor in a box: one connect, no key, no account, no local install.

```
https://api.metagraph.sh/mcp
full catalog · 240 tools

https://api.metagraph.sh/mcp/core
core profile · 23 tools
```

## Which endpoint [#which-endpoint]

**Default to `/mcp/core`.** The full `/mcp` tool list serializes to \~406K tokens of tool schemas — more than most model context windows — and a client that holds tool definitions in context pays that on every session. `/mcp/core` lists the curated golden path (discover → verify → integrate → call → screen economically) at \~43K tokens.

|                      | `/mcp`                                        | `/mcp/core`                            |
| -------------------- | --------------------------------------------- | -------------------------------------- |
| Tools listed         | 240                                           | 23 (the curated golden path)           |
| `tools/list` context | \~406K tokens                                 | \~43K tokens                           |
| Tools callable       | all 240                                       | all 240 — listing filters, calls don't |
| Pick it when         | context is cheap (subagents, offline tooling) | context is model context — most agents |

<Callout title="A context diet, not an authorization boundary">
  A session connected to `/mcp/core` can still `tools/call` every one of the 240 tools — listing
  filters, calls don't. When a thin session needs one the core profile never listed, it calls it by
  name, and `ask` answers whole questions without any further tools at all — a core session is never
  stranded.
</Callout>

`get_more_tools` is not part of that: it reports a capability this server lacks. Call it when nothing
in the catalogue does what you need, and describe the goal in `context` — it records the gap and
returns an acknowledgement, not data or additional tools.

## Authentication [#authentication]

Optional. Anonymous access works on both endpoints at 100 requests/60s per client IP. Clients that support MCP authorization prompt an OAuth sign-in (GitHub) on first connect; an `Authorization: Bearer mg_…` [API key](/settings) header works too. Authenticating raises rate limits (500 requests/60s per account, higher on paid tiers) — it does not unlock additional tools or surfaces.

## Connect a client [#connect-a-client]

### Claude Code [#claude-code]

One CLI command, no config file to hand-edit:

```bash
claude mcp add --transport http metagraphed https://api.metagraph.sh/mcp/core
```

### Claude Desktop & claude.ai [#claude-desktop--claudeai]

Both take the endpoint as a custom connector: **Settings → Connectors → Add custom connector**, then paste `https://api.metagraph.sh/mcp/core`. Claude Desktop also accepts a config-file entry:

```json title="claude_desktop_config.json"
{
  "mcpServers": {
    "metagraphed": {
      "transport": { "type": "http", "url": "https://api.metagraph.sh/mcp/core" }
    }
  }
}
```

### Cursor [#cursor]

```json title=".cursor/mcp.json"
{
  "mcpServers": {
    "metagraphed": { "url": "https://api.metagraph.sh/mcp/core" }
  }
}
```

### VS Code [#vs-code]

```json title=".vscode/mcp.json"
{
  "servers": {
    "metagraphed": { "type": "http", "url": "https://api.metagraph.sh/mcp/core" }
  }
}
```

### Any other client [#any-other-client]

Any client that speaks streamable-HTTP MCP connects directly — no install, no key:

```json title="Generic streamable-HTTP entry"
{
  "type": "streamable-http",
  "url": "https://api.metagraph.sh/mcp/core"
}
```

## First calls to try [#first-calls-to-try]

All three are in the core profile:

| Tool                  | Try                                                      | What it shows                                                                    |
| --------------------- | -------------------------------------------------------- | -------------------------------------------------------------------------------- |
| `search_subnets`      | `{"query": "inference"}`                                 | Keyword discovery across every subnet's curated profile.                         |
| `ask`                 | `{"question": "which subnets expose an inference API?"}` | A grounded natural-language answer with citations — the whole-question shortcut. |
| `call_subnet_surface` | a surface id from `list_subnet_apis`                     | Calling a subnet's own registered API through the registry, schema-checked.      |

Every tool mirrors a documented REST route — the [API reference](/docs/api-reference) covers the request/response shapes behind them, and [For agents](/agents) has the rest of the machine surface: playbooks, `llms.txt`, the served skill, and prompt-ready links.

<ApiSources paths="[&#x22;/mcp&#x22;, &#x22;/mcp/core&#x22;]" />