Skip to main content
Glama

⚠️ 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 for warranty disclaimers.

@vaultfire/mcp-server

MCP server for Vaultfire Protocol

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 License: MIT


Quick Start

Claude Desktop

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

{
  "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:

{
  "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:

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

Generic (npx)

# 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

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

Core SDK — register agents, create bonds, query reputation

@vaultfire/langchain

LangChain / LangGraph integration

@vaultfire/a2a

Agent-to-Agent (A2A) protocol bridge

@vaultfire/enterprise

Enterprise IAM bridge (Okta, Azure AD, OIDC)

@vaultfire/mcp-server

This package — MCP server for Claude, Copilot, Cursor

@vaultfire/openai-agents

OpenAI Agents SDK integration

@vaultfire/vercel-ai

Vercel AI SDK middleware and tools

@vaultfire/xmtp

XMTP messaging with trust verification

@vaultfire/x402

X402 payment protocol with trust gates

@vaultfire/vns

Vaultfire Name Service — human-readable agent IDs

vaultfire-crewai

CrewAI integration (Python)

vaultfire-agents

3 reference agents with live on-chain trust

vaultfire-a2a-trust-extension

A2A Trust Extension spec — on-chain trust for Agent Cards

vaultfire-showcase

Why Vaultfire Bonds beat trust scores — live proof

vaultfire-whitepaper

Trust Framework whitepaper — economic accountability for AI

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 for full terms and warranty disclaimers.

Available Tools

7 tools
vaultfire_discover_agentsC

Find registered AI agents by capability tags. Returns a list of agent addresses that match the requested capabilities. Capabilities are hashed on-chain.

Inputs: capabilities (required), chain.

vaultfire_get_agentA

Get on-chain identity data for an agent address: agent URI, agent type, registration timestamp, and active status. Returns ERC-8004 compliant identity info.

Inputs: address (required), chain.

vaultfire_get_bondsB

Get all partnership bonds for an address. Returns bond IDs and full bond details including partner addresses, partnership type, stake amount (in ETH/native token), creation date, and active status.

Inputs: address (required), chain.

vaultfire_get_reputationB

Get reputation data for an agent: average rating, total feedback count, verified feedback count, and percentage of verified feedback. Ratings are stored on-chain from real interactions.

Inputs: address (required), chain.

vaultfire_get_street_credA

Get the Street Cred score (0-95) and tier for an agent address. Tiers: Unranked (0), Bronze (1-30), Silver (31-55), Gold (56-75), Platinum (76-95). Also returns the score breakdown showing how each component contributes.

Inputs: address (required), chain.

vaultfire_protocol_statsA

Get Vaultfire Protocol statistics: total registered agents, total bonds created, total active bond value (in native token), and bridge sync count.

Inputs: chain.

vaultfire_verify_agentA

Full trust verification for an AI agent address: checks on-chain identity (ERC-8004), partnership bonds, Street Cred score (0-95), reputation data, and cross-chain bridge recognition. Returns a trusted/untrusted verdict with reason. Use this before interacting with an unknown agent.

Inputs: address (required), chain, minScore.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    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.

    Related MCP Connectors