Skip to content
Empryo logo

Empryo MCP server

Which MCP servers are Empryo'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 2026-10-24

← Back to Empryo

Whose server it is
  • Registry namecom.empryo/docsverified in the MCP registry

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

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools4
  • Server calls itselfempryo-docs
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 41 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: navigate a codebase by its structure and symbol names; run parallel coding agents on one repository; steer a running coding agent from a phone.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 3 of 4 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: 4, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it0 of 3 use cases
  • Use1,451 GitHub stars
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer485 ms
  • Space in an agent's context≈ 369 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4

What an agent can do with it

  • cannot · navigate a codebase by its structure and symbol names
  • cannot · run parallel coding agents on one repository
  • cannot · steer a running coding agent from a phone

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 2026-10-24
  • search_docs

    Search current Empryo documentation. Returns exact page and section selectors and citation URLs.

  • list_docs

    List Empryo documentation pages, or the sections and export URLs of one page.

  • read_docs

    Read a full Empryo docs page or an exact section as Markdown or plain text. Use selectors returned by search_docs/list_docs; empty anchor means introduction.

  • current_release

    Read the current published Empryo version and available release artifacts. Never assumes the installed client matches this version.

How to connect

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

{
  "mcpServers": {
    "docs": {
      "type": "http",
      "url": "https://empryo.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

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

OpenAPI spec

18 paths, read 2026-10-24. 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.