Skip to content

Fetch Router MCP server

Which MCP servers are Fetch Router'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 Fetch Router

Whose server it is
  • Registry namedev.fetchrouter/fetchrouter-mcpverified in the MCP registry

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

When we asked itchecked 2026-11-02
  • Stateanswerschecked 2026-11-02
  • Tools2
  • Server calls itselffetchrouter
  • Server version0.1.1
  • Protocol version2025-06-18

On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 146 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Verify a page loaded instead of trusting its status code; Check per-site fetch reliability before choosing a fetch route.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "Verify a page loaded instead of trusting its status code", the likely first call is fetch_page.
  • For "Check per-site fetch reliability before choosing a fetch route", the likely first call is domain_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.

Measured dailydaily checks: 2, the first on 2026-11-02
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer426 ms
  • Space in an agent's context≈ 404 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · Fetch public pages as clean markdown or HTML for agents
  • can do · Verify a page loaded instead of trusting its status code
  • can do · Check per-site fetch reliability before choosing a fetch route

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 offers2 tools · read 2026-11-02
  • fetch_page

    Fetch a public URL and get its content only if it really loaded. Checks for block pages, CAPTCHAs, login walls and empty JavaScript shells, and retries through other routes (including a headless browser) automatically. Billed only on…

  • domain_reliability

    Pass rates per route (plain HTTP, browser, providers) for a domain over the last 30 days, from real verified fetches. Use it to choose mode/max_cost before fetching a hard site. Free, no key needed.

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

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

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.