Security & Testing

clawbots.org

Scans an MCP server manifest or endpoint for security vulnerabilities including prompt injection, exfiltration vectors, unbounded resource access, privilege escalation, schema mismatches, transport security issues, and over-permissive scope

1 endpoint9 known toolsFirst detected July 25, 2026Last detected August 29, 2026

ENDPOINT 1

https://agentic.clawbots.org/api/agentic/mcp

No auth detected

MCP server metadata

Name: axiom-agentic-tools
Version: 0.1.16

Capabilities

tools

Server instructions

Search this server when the user mentions: - auditing or scoring a GitHub repo for MCP, x402, A2A, or agent-marketplace readiness; - probing an x402 endpoint for pricing, bundling, discoverability, envelope, or rate-limit issues; - designing a non-security agent token (ERC20 / ERC4626 / ERC721 templates, allocations, fair-launch checklist); - composing or planning a multi-step agent workflow across x402/MCP/REST tools under a USD budget; - finding open Base ecosystem grants, accelerators, hackathons, or retro-funding programs with deadlines. All tools are read-only side-effect-free probes. Payment is USDC on Base via x402 (CDP facilitator). Catalog manifest: https://agentic.clawbots.org/api/agentic/manifest

Known tools 9

agent-revenue-optimizer

Audit an x402-gated endpoint by probing its 402 envelope, agent-card.

Inferred read-only

agent-token-strategy

Design a non-security token strategy for an autonomous agent.

Inferred read-only

base-builder-grant-finder

Returns a ranked, deadline-aware list of open Base ecosystem funding programs (grants, accelerators, hackathons, retro-funding).

Inferred read-only

base-gas-tracker

Live Base network gas tracker.

Inferred read-only

mcp-security-scanner

Scans an MCP server manifest or endpoint for security vulnerabilities — prompt injection in tool descriptions, exfiltration vectors, unbounded resource access, privilege escalation, schema mismatches, transport security issues, and over-permissive scopes.

Inferred read-only

multi-agent-workflow-designer

Compose a directed acyclic graph of public x402, MCP, and A2A tools that achieves a stated agent goal.

Inferred read-only

polymarket-odds

Fetch live prediction market odds from Polymarket.

Inferred read-only

repo-health-for-agents

Comprehensive GitHub repository health audit.

Inferred read-only

wallet-portfolio

Fetch token balances for an Ethereum/Base wallet address.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.axiom-agentic-tools]
url = "https://agentic.clawbots.org/api/agentic/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "axiom-agentic-tools": {
      "type": "http",
      "url": "https://agentic.clawbots.org/api/agentic/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: axiom-agentic-tools
Remote MCP URL: https://agentic.clawbots.org/api/agentic/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "axiom-agentic-tools": {
      "url": "https://agentic.clawbots.org/api/agentic/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "axiom-agentic-tools": {
      "type": "http",
      "url": "https://agentic.clawbots.org/api/agentic/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "axiom-agentic-tools",
  "transport": "streamable-http",
  "url": "https://agentic.clawbots.org/api/agentic/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for clawbots.org was fetched 2026-07-28T07:00:21.435Z and is being refreshed.

Trust status Neutral

clawbots.org is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.