Skip to content
trusted blogs logo

trusted blogs MCP server

Which MCP servers are trusted blogs'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 trusted blogs

Whose server it is
  • Registry namecom.trusted-blogs/blogsucheverified in the MCP registry

The registry name sits under trusted-blogs.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
  • Tools2
  • Server calls itselftrusted-blogs-blogsuche
  • Server version1.30.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 516 ms.

Should an agent connect itConnect it, with care
  • Its tools do find blogs matching a brand's topic and SEO metrics, but not book a sponsored article or post a blogger brief; approve finished articles before the blogger is paid.

Once connected

  • For "find blogs matching a brand's topic and SEO metrics", the likely first call is blogs_suchen.
  • Parameters are untyped or undescribed in 1 of 2 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: 7, the first on 2026-10-28
  • INITE MCP score80 of 100answers 100 · does the job 33 · definitions 92 · context 100 · connects 100
  • What an agent can do with it1 of 3 use cases
  • Answered100% of days7 of 7 daily checks
  • Median first answer515 ms
  • Space in an agent's context≈ 534 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 92 of 100
  • Typed results2 of 2 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 2

What an agent can do with it

  • can do · find blogs matching a brand's topic and SEO metrics
  • cannot · book a sponsored article or post a blogger brief
  • cannot · approve finished articles before the blogger is paid

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 2026-10-28
  • blogs_suchen

    Sucht im Katalog von trusted blogs nach Blogs für Kooperationen (Sponsored Posts, Linkaufbau). Filter nach Suchbegriff, Themen, Sprache und SEO-Werten. Liefert je Blog Themen, SEO-Werte und einen Link zum Profil. Preise sind nicht…

  • themen_auflisten

    Listet alle Themen (als Slugs wie reisen-outdoor) und Sprachen, nach denen blogs_suchen filtern kann.

How to connect

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

{
  "mcpServers": {
    "blogsuche": {
      "type": "http",
      "url": "https://api.trusted-blogs.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http trusted-blogs https://api.trusted-blogs.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.trusted-blogs.com/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.