Skip to main content
Glama
Ghostkey316

Vaultfire MCP Server

by Ghostkey316
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote
README.md
<div align="center">

> **⚠️ Alpha Software** — Vaultfire Protocol is in active development. Smart contracts are deployed on mainnet but have **not been formally audited** by a third-party security firm. Read-only tools are safe for any agent. Write tools interact with live contracts and transactions are irreversible. Use at your own risk. See [LICENSE](./LICENSE) for warranty disclaimers.

# @vaultfire/mcp-server

**MCP server for [Vaultfire Protocol](https://github.com/Ghostkey316/ghostkey-316-vaultfire-init)**

On-chain trust verification for any MCP-compatible AI.
Works with **Claude · Copilot · Cursor · Windsurf · Google ADK** and more.

Deployed on **Base · Avalanche · Arbitrum · Polygon**.

[![npm version](https://img.shields.io/npm/v/@vaultfire/mcp-server)](https://www.npmjs.com/package/@vaultfire/mcp-server)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

</div>

---

## Quick Start

### Claude Desktop

Add to your `claude_desktop_config.json` (usually at `~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):

```json
{
  "mcpServers": {
    "vaultfire": {
      "command": "npx",
      "args": ["-y", "@vaultfire/mcp-server"],
      "env": {
        "VAULTFIRE_CHAIN": "base"
      }
    }
  }
}
```

To enable write tools (register agents, create bonds), add your private key:

```json
{
  "mcpServers": {
    "vaultfire": {
      "command": "npx",
      "args": ["-y", "@vaultfire/mcp-server"],
      "env": {
        "VAULTFIRE_CHAIN": "base",
        "PRIVATE_KEY": "your_private_key_here"
      }
    }
  }
}
```

### Cursor

Add to `.cursor/mcp.json` in your project root:

```json
{
  "mcpServers": {
    "vaultfire": {
      "command": "npx",
      "args": ["-y", "@vaultfire/mcp-server"],
      "env": {
        "VAULTFIRE_CHAIN": "base"
      }
    }
  }
}
```

### Generic (npx)

```bash
# Read-only mode (no key needed)
npx @vaultfire/mcp-server

# With a specific chain
VAULTFIRE_CHAIN=avalanche npx @vaultfire/mcp-server

# With write tools enabled
PRIVATE_KEY=your_private_key npx @vaultfire/mcp-server
```

### Install globally

```bash
npm install -g @vaultfire/mcp-server
vaultfire-mcp-server
```

---

## Available Tools

### Read-Only Tools (always available)

| Tool | Description |
|------|-------------|
| `vaultfire_verify_agent` | Full trust verification: identity, bonds, Street Cred, reputation, bridge status |
| `vaultfire_get_street_cred` | Get Street Cred score (0-95) and tier |
| `vaultfire_get_agent` | On-chain identity data (URI, type, registration date, active status) |
| `vaultfire_get_bonds` | All partnership bonds for an address |
| `vaultfire_get_reputation` | Reputation data (average rating, feedback count, verified %) |
| `vaultfire_discover_agents` | Find agents by capability tags |
| `vaultfire_protocol_stats` | Protocol stats: total agents, bonds, bonded value, bridge sync |

### Write Tools (require `PRIVATE_KEY` env var)

| Tool | Description |
|------|-------------|
| `vaultfire_register_agent` | Register an AI agent on-chain (ERC-8004) |
| `vaultfire_create_bond` | Create a partnership bond with economic stake |

> **Warning:** Write tools submit real transactions to mainnet. Transactions are irreversible.

---

## Resources

The server exposes two MCP resources for protocol context:

| URI | Description |
|-----|-------------|
| `vaultfire://chains` | All 4 supported chains with contract addresses and chain details |
| `vaultfire://scoring` | Street Cred scoring formula and tier definitions |

---

## Configuration

| Environment Variable | Required | Default | Description |
|---------------------|----------|---------|-------------|
| `VAULTFIRE_CHAIN` | No | `base` | Chain to query: `base`, `avalanche`, `arbitrum`, `polygon` |
| `PRIVATE_KEY` | No | — | Private key for write tools (register, bond). Never commit this. |
| `VAULTFIRE_RPC_URL` | No | — | Custom RPC URL (overrides default for selected chain) |

---

## Street Cred Scoring

Street Cred is a composite trust score (0–95) computed from live on-chain data:

| Component | Points | Condition |
|-----------|--------|-----------|
| Identity Registered | 30 | Agent has ERC-8004 on-chain identity |
| Has Bond | 25 | At least one partnership bond exists |
| Bond Active | 15 | At least one bond is currently active |
| Bond Tier | 0–20 | Platinum (≥0.5 ETH) / Gold (≥0.1) / Silver (≥0.05) / Bronze (≥0.01) |
| Multiple Bonds | 5 | More than one bond (ecosystem participant) |

**Tiers:**

| Tier | Score Range | Description |
|------|-------------|-------------|
| Unranked | 0 | No on-chain trust signals |
| Bronze | 1–30 | Basic identity or minimal bond activity |
| Silver | 31–55 | Registered and bonded with some stake |
| Gold | 56–75 | Active bond with meaningful stake |
| Platinum | 76–95 | Multiple active bonds with significant stake |

---

## Supported Chains

| Chain | Chain ID | Hub | Native Token |
|-------|----------|-----|--------------|
| Base | 8453 | ✅ Primary | ETH |
| Avalanche | 43114 | — | AVAX |
| Arbitrum | 42161 | — | ETH |
| Polygon | 137 | — | POL |

---

## Why Vaultfire

| Feature | Vaultfire | AxisTrust | Cred Protocol | Okta XAA |
|---------|-----------|-----------|---------------|----------|
| AI Accountability Bonds | ✅ | ❌ | ❌ | ❌ |
| AI Partnership Bonds | ✅ | ❌ | ❌ | ❌ |
| On-chain, trustless | ✅ | ❌ | partial | ❌ |
| Multi-chain (day one) | ✅ (4) | ❌ | ❌ | ❌ |
| Street Cred composite score | ✅ | T-Score | C-Score | ❌ |
| Belief-weighted governance | ✅ | ❌ | ❌ | ❌ |
| ERC-8004 compliant | ✅ | ❌ | ✅ | ❌ |

> Morals over metrics. Privacy over surveillance. Freedom over control.
> Making human thriving more profitable than extraction.

**Core differentiators:**
1. **AI Accountability Bonds** — real economic skin-in-the-game, not just scores
2. **AI Partnership Bonds** — mutual economic stakes between agents
3. **Belief-weighted governance** — first in industry (not token-weighted)
4. **Cross-chain from day one** — 4 mainnet chains
5. **Street Cred scoring** — composite 0-95 trust score from on-chain data

---

## Vaultfire Ecosystem

| Package | Description |
|---|---|
| [`@vaultfire/agent-sdk`](https://github.com/Ghostkey316/vaultfire-sdk) | Core SDK — register agents, create bonds, query reputation |
| [`@vaultfire/langchain`](https://github.com/Ghostkey316/vaultfire-langchain) | LangChain / LangGraph integration |
| [`@vaultfire/a2a`](https://github.com/Ghostkey316/vaultfire-a2a) | Agent-to-Agent (A2A) protocol bridge |
| [`@vaultfire/enterprise`](https://github.com/Ghostkey316/vaultfire-enterprise) | Enterprise IAM bridge (Okta, Azure AD, OIDC) |
| [`@vaultfire/mcp-server`](https://github.com/Ghostkey316/vaultfire-mcp-server) | **This package** — MCP server for Claude, Copilot, Cursor |
| [`@vaultfire/openai-agents`](https://github.com/Ghostkey316/vaultfire-openai-agents) | OpenAI Agents SDK integration |
| [`@vaultfire/vercel-ai`](https://github.com/Ghostkey316/vaultfire-vercel-ai) | Vercel AI SDK middleware and tools |
| [`@vaultfire/xmtp`](https://github.com/Ghostkey316/vaultfire-xmtp) | XMTP messaging with trust verification |
| [`@vaultfire/x402`](https://github.com/Ghostkey316/vaultfire-x402) | X402 payment protocol with trust gates |
| [`@vaultfire/vns`](https://github.com/Ghostkey316/vaultfire-vns) | Vaultfire Name Service — human-readable agent IDs |
| [`vaultfire-crewai`](https://github.com/Ghostkey316/vaultfire-crewai) | CrewAI integration (Python) |
| [`vaultfire-agents`](https://github.com/Ghostkey316/vaultfire-agents) | 3 reference agents with live on-chain trust |
| [`vaultfire-a2a-trust-extension`](https://github.com/Ghostkey316/vaultfire-a2a-trust-extension) | A2A Trust Extension spec — on-chain trust for Agent Cards |
| [`vaultfire-showcase`](https://github.com/Ghostkey316/vaultfire-showcase) | Why Vaultfire Bonds beat trust scores — live proof |
| [`vaultfire-whitepaper`](https://github.com/Ghostkey316/vaultfire-whitepaper) | Trust Framework whitepaper — economic accountability for AI |
| [`vaultfire-docs`](https://github.com/Ghostkey316/vaultfire-docs) | Developer portal — quickstart, playground, framework picker |
---

## Security

- **Read-only tools** require no credentials and are safe to run anywhere
- **Write tools** require `PRIVATE_KEY` — always load from env vars, never hardcode
- Smart contracts are deployed on mainnet but **have not been formally audited**
- Transactions sent via write tools are irreversible
- Do not expose your MCP server config (with `PRIVATE_KEY`) to untrusted parties

---

## License

MIT — Copyright 2025 Ghostkey316

See [LICENSE](./LICENSE) for full terms and warranty disclaimers.
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 7 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: discover_agents finds agents by tags, get_agent retrieves identity data, get_bonds lists partnership bonds, get_reputation provides rating data, get_street_cred gives a score and tier, protocol_stats shows system-wide metrics, and verify_agent performs a comprehensive trust check. The descriptions reinforce these unique functions, making misselection unlikely.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with the prefix 'vaultfire_' (e.g., vaultfire_discover_agents, vaultfire_get_agent). This uniform snake_case naming convention makes the set predictable and easy to parse, with no deviations in style or structure across the seven tools.

Tool Count5/5

With 7 tools, the count is well-scoped for a server focused on AI agent verification and data retrieval in the Vaultfire ecosystem. Each tool serves a specific, non-redundant function, covering discovery, identity, bonds, reputation, scoring, stats, and verification, which aligns perfectly with the domain's needs without being overly sparse or bloated.

Completeness5/5

The tool surface provides complete coverage for the domain of AI agent verification and on-chain data access. It includes discovery, detailed identity and bond retrieval, reputation and scoring metrics, protocol-level statistics, and a comprehensive verification tool that integrates all aspects. There are no obvious gaps; agents can perform end-to-end workflows without dead ends.

Resources