Skip to content
KushBitx logo

KushBitx MCP server

Which MCP servers are KushBitx's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-29

← Back to KushBitx

Whose server it is
  • Registry namecom.kushbitx/agentproofverified in the MCP registry

The registry name sits under kushbitx.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools5
  • Server calls itselfkushbitx-agentproof
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 95 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: check a proposed USDC payment against spending policy; simulate a Base transaction before the agent signs it; verify a Base USDC transfer's recipient, amount and confirmations.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "check a proposed USDC payment against spending policy", the likely first call is spendguard_evaluate.
  • For "simulate a Base transaction before the agent signs it", the likely first call is preflight.
  • For "verify a Base USDC transfer's recipient, amount and confirmations", the likely first call is verify_payment.
  • Parameters are untyped or undescribed in 3 of 6 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-29
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer107 ms
  • Space in an agent's context≈ 1,907 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 92 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 6

What an agent can do with it

  • can do · check a proposed USDC payment against spending policy
  • can do · simulate a Base transaction before the agent signs it
  • can do · verify a Base USDC transfer's recipient, amount and confirmations

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers5 tools · read 2026-10-29
  • spendguard_evaluate

    Free. Check a proposed Base USDC payment against a spending policy you supply (per-transaction limit, daily budget, human-approval threshold, allowed recipients) before money moves. Returns APPROVE, HUMAN_APPROVAL or BLOCK with findings…

  • quick_check

    Fast pre-payment sanity check for agents on Base: confirms the RPC reports Base mainnet (chain ID 8453) and that the official USDC contract has deployed code. No request body. Returns PASS or FAIL with both checks and a timestamp. It is…

  • token_risk

    Token-risk report for one Base ERC-20 contract. Checks whether the token can be sold (honeypot simulation), buy/sell/transfer tax, owner privileges (mint, pause, blacklist, balance changes, proxy upgrades), holder concentration and DEX…

  • preflight

    Simulate one unsigned Base transaction before an agent signs it. Runs eth_call and gas estimation on current chain state, decodes the intent (ERC-20 transfer, approve, NFT setApprovalForAll), flags unlimited approvals, calldata sent to a…

  • verify_payment

    Verify one Base USDC payment onchain before an agent releases goods or credit. Reads the transaction receipt and checks the official USDC Transfer logs against the expected recipient, amount and optional sender. Returns VERIFIED…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "agentproof": {
      "type": "http",
      "url": "https://kushbitx.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http kushbitx https://kushbitx.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://kushbitx.com/mcp as a custom connector in the settings.

OpenAPI spec

20 paths, read 2026-10-29. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.