Skip to content
FetchDelta logo

FetchDelta MCP server

Which MCP servers are FetchDelta'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 FetchDelta

Whose server it is
  • Registry namecom.fetchdelta/agent-toolsverified in the MCP registry

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

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools7
  • Server calls itselfcom.fetchdelta/agent-tools
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 240 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: resolve a public page into markdown with headings and links; compare a public page against its shared baseline for changes; extract price mentions from public pricing pages.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "resolve a public page into markdown with headings and links", the likely first call is resolve.
  • For "compare a public page against its shared baseline for changes", the likely first call is diff.
  • For "extract price mentions from public pricing pages", the likely first call is pricing_snapshot.
  • Parameters are untyped or undescribed in 6 of 7 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 2026-10-28
  • 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 answer213 ms
  • Space in an agent's context≈ 888 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsB · 86 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 7

What an agent can do with it

  • can do · resolve a public page into markdown with headings and links
  • can do · compare a public page against its shared baseline for changes
  • can do · extract price mentions from public pricing pages

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 offers7 tools · read 2026-10-28
  • catalog

    Free: list FetchDelta products, current prices and source limitations. No payment or stored session.

  • preview_page

    Free: preview readability of one public HTML page before purchasing. Truncated Markdown only; no JavaScript or login bypass.

  • resolve

    FetchDelta: fetch one public web page as Markdown with title, headings, links and source timestamp. Use for current docs, changelogs or policy text. HTML only; no JavaScript rendering or login. Preview source readability for free before…

  • diff

    FetchDelta: compare one public web page with its previous stored snapshot. Returns added/removed lines and change previews. The first call creates a baseline; later calls share that URL baseline across buyers. Use page-watch-30d for a…

  • pricing_snapshot

    FetchDelta: extract price mentions, commercial terms and source Markdown from one to five public pricing pages in one request. Text evidence, not verified prices or normalized plan comparisons. Repeat the url query parameter for multiple…

  • page_watch_30d

    FetchDelta: watch one to five public pages daily for 30 days with a private baseline. Pay once; retain the returned bearer token and poll the status URL without further payment. No subscription or automatic renewal. Repeat the url query…

  • poll_watch

    Unpaid: read a purchased daily watch. Supply its bearer token privately in request _meta['com.fetchdelta/watch-token'], never in tool arguments or public logs.

How to connect

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

{
  "mcpServers": {
    "agent-tools": {
      "type": "http",
      "url": "https://fetchdelta.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

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

OpenAPI spec

9 paths, read 2026-10-28. 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.