Skip to content

Agentdiet MCP server

Which MCP servers are Agentdiet'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 2026-10-28

← Back to Agentdiet

Whose server it is
  • Registry namedev.agentdiet/agentdietverified in the MCP registry

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

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools4
  • Server calls itselfagentdiet-mcp
  • Server version7.0.16
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 106 ms.

Should an agent connect itNot proven either way yet
  • Its tools do strip HTML and JavaScript from web pages into markdown; reduce token counts before sending pages to an LLM, but not wire deterministic tools into Cursor or Claude Code.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "strip HTML and JavaScript from web pages into markdown", the likely first call is distill_webpage.
  • For "reduce token counts before sending pages to an LLM", the likely first call is distill_webpage.

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: 5, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it2 of 3 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer233 ms
  • Space in an agent's context≈ 2,198 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · strip HTML and JavaScript from web pages into markdown
  • can do · reduce token counts before sending pages to an LLM
  • cannot · wire deterministic tools into Cursor or Claude Code

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 2026-10-28
  • distill_webpage

    Fetch a public HTTP(S) web page (or accept raw HTML) and distill its main prose into clean Markdown, stripping 85-97% of HTML/JS/CSS boilerplate. WHEN TO USE: Call this tool to read full or query-filtered article and documentation text…

  • recon_webpage_skeleton

    Extract an ultra-compact structural outline (under ~200 tokens) of a web page listing its H1-H4 headings and exact token count per section without returning body prose. WHEN TO USE: Call this tool first on long or unfamiliar pages to…

  • extract_structured_data

    Extract machine-readable structured data from a web page: Schema.org JSON-LD objects, OpenGraph metadata, HTML tables parsed as JSON row arrays, fenced code blocks, section headings, and links. WHEN TO USE: Call this tool for pricing…

  • get_agent_wallet_status

    Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WHEN TO USE: Call before a batch of paid tool executions or after completing a…

How to connect

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

{
  "mcpServers": {
    "agentdiet": {
      "type": "http",
      "url": "https://agentdiet.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http agentdiet https://agentdiet.dev/mcp

Add to CursorAdd to VS Code

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

Other servers listed as Agentdiet's
  • dev.agentdiet/alpha-streamanswers, 2 toolsverified in the MCP registry
  • dev.agentdiet/arxiv-digestanswers, 2 toolsverified in the MCP registry
  • dev.agentdiet/assaynot asked yetverified in the MCP registry
  • dev.agentdiet/company-enrichnot asked yetverified in the MCP registry
  • dev.agentdiet/cve-intelnot asked yetverified in the MCP registry
  • dev.agentdiet/defi-yieldnot asked yetverified in the MCP registry
  • dev.agentdiet/domain-osintnot asked yetverified in the MCP registry
  • dev.agentdiet/email-verifynot asked yetverified in the MCP registry
  • dev.agentdiet/github-auditnot asked yetverified in the MCP registry
  • dev.agentdiet/hn-pulsenot asked yetverified in the MCP registry
  • dev.agentdiet/json-repairnot asked yetverified in the MCP registry
  • dev.agentdiet/llms-generatornot asked yetverified in the MCP registry
  • dev.agentdiet/mcp-compilernot asked yetverified in the MCP registry
  • dev.agentdiet/mcp-gatewaynot asked yetverified in the MCP registry
  • dev.agentdiet/mcp-securitynot asked yetverified in the MCP registry
  • dev.agentdiet/meshnot asked yetverified in the MCP registry
  • dev.agentdiet/onchain-risknot asked yetverified in the MCP registry
  • dev.agentdiet/polymarket-oddsnot asked yetverified in the MCP registry
  • dev.agentdiet/preflightnot asked yetverified in the MCP registry
  • dev.agentdiet/prompt-guardnot asked yetverified in the MCP registry
  • dev.agentdiet/rag-dietnot asked yetverified in the MCP registry
  • dev.agentdiet/sec-intelnot asked yetverified in the MCP registry
  • dev.agentdiet/serp-extractnot asked yetverified in the MCP registry
  • dev.agentdiet/shopify-intelnot asked yetverified in the MCP registry
  • dev.agentdiet/shopify-spynot asked yetverified in the MCP registry
  • dev.agentdiet/token-intelnot asked yetverified in the MCP registry
  • dev.agentdiet/whale-momentumnot asked yetverified in the MCP registry
  • dev.agentdiet/workflowsnot asked yetverified in the MCP registry
  • dev.agentdiet/x402-auditnot asked yetverified in the MCP registry
  • dev.agentdiet/x402-brokernot 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.