vaultfire
Vaultfire ships an official MCP server as the npm package @vaultfire/mcp-server (bin vaultfire-mcp-server), a local stdio server that reads the four chains over JSON-RPC with ethers and exposes 9 tools and 2 resources. The provider ALSO advertises a hosted remote endpoint — llms.txt ("MCP Integration": url https://theloopbreaker.com/api/mcp, transport http), agents.txt (MCP-Endpoint / MCP-Transport: http), the tag on every page, and /api/health reports "mcp": true — but that endpoint does not exist: on 2026-09-19 GET, POST initialize and POST tools/list (Accept: application/json, text/event-stream) all returned the site's 404 HTML shell. The remote surface is therefore recorded as advertised-but-absent and deployment.mode is local-stdio, not both. Tool names and descriptions are taken verbatim from the package README on npm; input schemas were not introspected (a stdio server has to be installed and run to answer tools/list).
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport stdio
Tools
vaultfire_verify_agent— Full trust verification: identity, bonds, Street Cred, reputation, bridge statusvaultfire_get_street_cred— Get Street Cred score (0-95) and tiervaultfire_get_agent— On-chain identity data (URI, type, registration date, active status)vaultfire_get_bonds— All partnership bonds for an addressvaultfire_get_reputation— Reputation data (average rating, feedback count, verified %)vaultfire_discover_agents— Find agents by capability tagsvaultfire_protocol_stats— Protocol stats: total agents, bonds, bonded value, bridge syncvaultfire_register_agent— Register an AI agent on-chain (ERC-8004)vaultfire_create_bond— Create a partnership bond with economic stake
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.