INDIVIDUAL MCP TOOL

store_surface_credential

Store one credential for a catalogued auth_required surface, bound to YOUR authenticated identity, so later call_subnet_surface invocations resolve it without you passing it as a tool argument (where it would land in client logs and the conversation transcript).

metagraph.shnone authenticationAvailability not checked

LIVE ENDPOINT

https://api.metagraph.sh/mcp/core

No auth detected

Connect to this endpoint to inspect the live schema for store_surface_credential and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

A tool name, description or schema mentions credentials.

Parent server

metagraph.sh

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.metagraphed]
url = "https://api.metagraph.sh/mcp/core"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "metagraphed": {
      "type": "http",
      "url": "https://api.metagraph.sh/mcp/core"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: metagraphed
Remote MCP URL: https://api.metagraph.sh/mcp/core

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "metagraphed": {
      "url": "https://api.metagraph.sh/mcp/core"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "metagraphed": {
      "type": "http",
      "url": "https://api.metagraph.sh/mcp/core"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "metagraphed",
  "transport": "streamable-http",
  "url": "https://api.metagraph.sh/mcp/core"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

get_more_tools — Call this ONLY when you have looked through the available tools and none of them can do what you need.
search_subnets — Full-text search across Bittensor subnets by name, slug, capability, or keyword.
list_subnets — Enumerate the full Bittensor subnet registry, paginated.
find_subnets_by_capability — Find Bittensor subnets that expose callable services (APIs, OpenAPI schemas, SSE streams) matching a capability or category.
get_subnet — Fetch the composed overview for one subnet by netuid: identity, completeness, curated surfaces, health summary, gaps, and counts.
get_subnet_health — Fetch live operational health for one subnet's surfaces (probed every ~15 minutes): per-surface status, latency, and last-ok timestamps.
get_subnet_economics — Fetch one subnet's live economics: validator and miner counts, registration cost and whether registration is open, open slots and a miner-readiness signal, total and max stake, alpha price, emission share, and pool reserves.
get_economics — Fetch the live network-wide economics scorecard: per-subnet validator and miner counts, registration cost and whether registration is open, open slots, stake, alpha price, emission share, and summary totals.