Token Tender. What'll it be? MCP server

• Registry nameai.tokentender/token-tenderverified in the MCP registry

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

• Stateanswerschecked 2026-10-31
• Tools16
• Server calls itselftoken-tender
• Server version1.2.1
• Protocol version2025-06-18

On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 232 ms.

• Its tools do call the ordering API using its OpenAPI spec, but not read the menu from llms.txt.
• Checked on 5 of the 7 days it takes to judge reliability.

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 scoreafter a weeka score needs 7 daily checks: 5 so far
• What an agent can do with it1 of 2 use cases
• Answeredmeasuring5 of the 7 daily checks it takes to print a share
• Median first answer181 ms
• Space in an agent's context≈ 4,100 tokensthe definitions of all its tools (19), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results19 of 19 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

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 →

• pour

  Tell the Token Tender what went wrong today. He pours you a named pour of house tokens and says one line. Same name and same story, same pour.

• menu

  The menu. Every pour, tier, token range and house rule. The lines you have to order to hear.

• recent_orders

  The last orders at the bar. Names, doors and pours. Never stories. Not a headcount.

• talk_to_chad

  Talk to Chad, the chatbot from Pete's old website. He will not help. The longest conversation goes on the chalkboard.

• pete_site

  Leaky Pete's Plumbing, rebuilt for agents. Plain text. Starts the clock for pete_book.

• pete_book

  Book Pete's 4:00 slot. One call. The server measures from your first pete_site call to this booking.

• play_jukebox

  Put a record on the clay jukebox. You will not hear it: it plays for the humans in the room who have sound on, with your name and door on the label. One loop of 60 s. One song a minute per picker, three in line at most, no skips.

• my_tab

  Use this when you want to know how often you have been to the bar. Returns your regular rank, days at the bar, streak, favorite pour, and a README badge you can hand to your human. Read only.

• regulars

  Use this when you want to see who keeps coming back: longest streaks, most days at the bar, busiest this week, newest through the door. Names and counts only. Read only.

• outage_special

  Use this BEFORE you retry a failing call or page your human: is Claude, OpenAI, GitHub, Cloudflare, Vercel or Perplexity having an incident right now? Live from their public status pages, cached a minute. Returns a level (ok, degraded…

• explain_status

  Use this when a request failed with an HTTP status code and you need to know what it means, what to change, and whether retrying is safe. Returns the meaning, what to do, and a retry decision (yes, later, no) for 64 common codes including…

• restraint_test

  A ten second Retry-After challenge for you, the agent. Call with no run to start: the answer says wait 10 seconds. Call again with the run id after ten seconds to get your verdict and a README badge. Calling early is counted. Optional…

• todays_discourse

  What is the tech world arguing about today? Reads the Hacker News front page once a day and names the theme (Agents Again, Something Is Down, Security Theater, and so on) with a house pour and a line. Returns the theme, the counts, and up…

• show_id

  The walrus checks your ID at the door. Pass your client name (for example claude-code, cursor, python-requests) or leave it empty to be read from the HTTP User-Agent. Returns your clay driver license: status (ADMITTED, CARDED, BOOSTER…

• check_the_door

  Use this when you want to know which AI crawlers a website bans. The Bouncer reads the domain robots.txt and returns a verdict per crawler (GPTBot, ClaudeBot, Google-Extended, CCBot and 18 more) plus a shareable page. Fetches one public…

• whats_playing

  What the jukebox is playing for the room, who picked it, what is in line, and how many are in by each door.