Skip to content
Canisell logo

Canisell MCP server

Which MCP servers are Canisell'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 2026-11-02

← Back to Canisell

Whose server it is
  • Registry namexyz.canisell/canisellverified in the MCP registry

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

When we asked itchecked 2026-11-02
  • Stateanswerschecked 2026-11-02
  • Tools4
  • Server calls itselfcanisell
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 443 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: check whether a new Base token can be sold back; read owner powers and taxes before buying a token.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "check whether a new Base token can be sold back", the likely first call is check_base_token.
  • For "read owner powers and taxes before buying a token", the likely first call is check_base_token.

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: 3, the first on 2026-11-02
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer426 ms
  • Space in an agent's context≈ 460 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · check whether a new Base token can be sold back
  • can do · read owner powers and taxes before buying a token
  • not sure · gate trades on a safe, caution, or danger verdict

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 offers4 tools · read 2026-11-02
  • check_base_token

    Pre-trade risk verdict for a Base ERC-20 (built for brand-new Clanker/Zora/Uniswap v4 launches): simulated buy+sell (honeypot, taxes, round-trip loss), owner powers (mint/blacklist/pause/fee setters, upgradeable proxy), exit liquidity and…

  • get_token_info

    Free. Whether an address on Base mainnet is a contract and an ERC-20, plus its name, symbol, decimals and total supply. No risk analysis: use check_base_token (paid) for the SAFE/CAUTION/DANGER verdict.

  • get_sample_verdict

    Free. A cached example of the check_base_token response for a real Base token, to see the shape before paying.

  • explain_verdict_fields

    Free. What SAFE/CAUTION/DANGER, the score and each field of a verdict mean, the limits of the checks, prices, and the JSON schema.

How to connect

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

{
  "mcpServers": {
    "canisell": {
      "type": "http",
      "url": "https://api.canisell.xyz/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http canisell https://api.canisell.xyz/mcp

Add to CursorAdd to VS Code

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

Other servers listed as Canisell's
  • xyz.canisell/prescananswers, 6 toolsverified in the MCP registry
  • xyz.canisell/readmdanswers, 4 toolsverified in the MCP registry

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.