
TokenOS MCP server
Which MCP servers are TokenOS'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 2026-10-19
- Registry nameai.tokenos/contract-auditverified in the MCP registry
The registry name sits under tokenos.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools1
- Server calls itselftokenos-contract-audit
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 116 ms.
- Its tools do none of the product's use cases we checked: deploy smart contracts from your own wallet; buy GPU compute time billed per minute.
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.
- INITE MCP score72 of 100answers 100 · does the job 0 · definitions 100 · context 100 · connects 100
- What an agent can do with it0 of 2 use cases
- Answered100% of days9 of 9 daily checks
- Median first answer373 ms
- Space in an agent's context≈ 118 tokensthe definitions of all its tools (1), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · generate a Solana or EVM dapp from a text description
- cannot · deploy smart contracts from your own wallet
- cannot · buy GPU compute time billed per minute
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 →
quick_auditStatic heuristic scan of a Solidity or Solana (Anchor / Rust) contract: findings with severity, line numbers and fixes, plus a letter grade.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"contract-audit": {
"type": "http",
"url": "https://tokenos.ai/api/mcp/apps/contract-audit"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http tokenos https://tokenos.ai/api/mcp/apps/contract-auditclaude.ai, ChatGPT and other clients: add https://tokenos.ai/api/mcp/apps/contract-audit as a custom connector in the settings.
- ai.tokenos/dapp-builderanswers, 3 toolsverified in the MCP registry
- ai.tokenos/gas-trackeranswers, 3 toolsverified in the MCP registry
- ai.tokenos/token-launch-plannernot asked yetverified in the MCP registry
- ai.tokenos/tokenomics-designernot asked yetverified in the MCP registry
- ai.tokenos/wallet-inspectornot asked yetverified 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.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.