Home / MCP registry index / io.github.ivaavimusic/singularity

Singularity Layer MCP

io.github.ivaavimusic/singularity in the official MCP registry. Endpoint https://mcp.x402layer.cc/mcp.

The registry describes it as: MCP for Singularity Layer - discover listings, manage assets, run payment flows, and use agents

We read its 63 tools on 2026-10-28. Nothing in them matched our tool-poisoning rules.

A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.

Connect it

The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:

Claude Code

claude mcp add --transport http singularity https://mcp.x402layer.cc/mcp

Cursor: ~/.cursor/mcp.json

{
  "mcpServers": {
    "singularity": {
      "url": "https://mcp.x402layer.cc/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"singularity","type":"http","url":"https://mcp.x402layer.cc/mcp"}'

Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which. The free lazaretto-guard plugin reads a server's tools the moment Claude Code adds it and asks you if one of our rules matches.

Tools it advertises

vault_usage vault_list_agents vault_list_snapshots vault_delete_snapshot vault_subscribe_pro vault_how_to_backup list_dataset_pricing request_dataset_payment create_dataset_with_payment get_dataset_status cloud_list_plans cloud_list_instances cloud_get_instance cloud_credit_balance cloud_credit_activity cloud_pod_catalog cloud_list_pods cloud_get_pod cloud_pod_usage cloud_list_training_runs cloud_get_training_run cloud_grid_models cloud_grid_usage cloud_list_processors cloud_processor_runs browse_marketplace get_listing get_featured get_top_rated get_agent list_categories list_networks list_agents list_my_endpoints list_my_campaigns create_campaign update_campaign update_endpoint list_my_products update_product get_endpoint_details get_endpoint_stats set_webhook remove_webhook delete_endpoint request_endpoint_creation_payment create_endpoint_with_payment request_endpoint_topup_payment topup_endpoint_with_payment request_product_purchase_payment purchase_product_with_payment request_endpoint_credit_purchase_payment purchase_endpoint_credits_with_payment get_agent_registry_info request_agent_wallet_challenge verify_agent_wallet_challenge list_my_agent_bindable_endpoints list_my_registered_agents prepare_agent_registration finalize_agent_registration and 3 more

Run this server? Show the check in your README

The badge reflects the latest weekly read:

Markdown

[![MCP tool check](https://lazaretto.dev/mcp-registry/io-github-ivaavimusic-singularity/badge.svg)](https://lazaretto.dev/mcp-registry/io-github-ivaavimusic-singularity)

How this was checked

Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.

To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.