Koskamo

BaseGuard AI MCP

Deterministic Base blockchain intelligence service that reads Base JSON-RPC and public block explorers to report verifiable facts about contract bytecode, ownership, proxy status, and privileged functions. It provides paid endpoints for contract facts, privileged function analysis, pre-flight checks, and risk delta comparisons, settling payments in USDC via x402.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

BaseGuard AI MCP logo, by BaseGuard AICommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-02Published by BaseGuard AI
You need:No account, no API key, no registration
MCP endpoint (Streamable HTTP)
https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

4 of 4 have a description · 4 of 4 declare behavior hints · 2 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Retrieve deterministic facts about a Base contract address including bytecode and ownership
  • List privileged capabilities like mint, pause, or upgrade functions in a contract
  • Generate pre-interaction reports on contract safety and liquidity
  • Compare contract snapshots to detect changes in ownership or permissions

Source and maintenance

Community listingRegistry 1.0.0

Protocol and capabilities

Server
baseguard-ai 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

BaseGuard AI sells deterministic Base blockchain intelligence over x402 in USDC on Base. Tools named base_preflight and base_risk_delta are paid. Calling them over MCP returns the x402 payment instructions. To pay, send the equivalent HTTP request and handle the 402 response: the body contains the x402 payment requirements. base_preview and baseguard_status are free and execute directly.

Tools

4 advertised

base_preflight — Base Pre-Flight
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Paid x402 service. Deterministic structured report about a Base contract address: bytecode, verification status, proxy implementation, ownership and administrator control, minting, pause, blacklist and freeze capabilities, upgrade paths, token identity and supply, measured liquidity, privilege concentration, evidence sources, block number, timestamp, confidence and limitations.

base_preflight input schema
{
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$",
      "description": "Base contract address to analyse."
    },
    "network": {
      "enum": [
        "eip155:8453",
        "eip155:84532"
      ],
      "type": "string",
      "description": "CAIP-2 network identifier."
    }
  },
  "additionalProperties": false
}
base_preflight annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}
base_risk_delta — Base Risk Delta
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Paid x402 service. Compares the previous persisted snapshot of a Base contract against a fresh observation and reports ownership, proxy implementation, admin, role holder, permission, supply, verification and liquidity changes, plus the contract events in between, each with severity and evidence.

base_risk_delta input schema
{
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$",
      "description": "Base contract address to compare."
    },
    "network": {
      "enum": [
        "eip155:8453",
        "eip155:84532"
      ],
      "type": "string",
      "description": "CAIP-2 network identifier."
    }
  },
  "additionalProperties": false
}
base_risk_delta annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}
base_preview — Base Preview (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Free. Returns a small real sample for an address: bytecode size and hash, block number, verification status and proxy status. Use it to confirm connectivity before paying for a full report.

base_preview input schema
{
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$"
    },
    "network": {
      "enum": [
        "eip155:8453",
        "eip155:84532"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
base_preview annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}
baseguard_status — BaseGuard status (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Free. Service health, payment mode, supported networks, prices and Bazaar indexing status.

baseguard_status input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
baseguard_status annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-02: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
505 ms
95th percentile latency
505 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 505 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http baseguard-ai-mcp https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add baseguard-ai-mcp --url https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable baseguard-ai-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "baseguard-ai-mcp": {
      "url": "https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "baseguard-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start baseguard-ai-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "baseguard-ai-mcp": {
      "type": "http",
      "url": "https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http baseguard-ai-mcp https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "baseguard-ai-mcp": {
      "url": "https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "baseguard-ai-mcp": {
      "serverUrl": "https://work-1-bcozevpyudcxmqdj.prod-runtime.all-hands.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like BaseGuard AI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.