Skip to content
PlyMove logo

PlyMove MCP server

Which MCP servers are PlyMove'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 2026-10-25

← Back to PlyMove

Whose server it is
  • Registry namecom.plymove/mcpverified in the MCP registry

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

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools6
  • Server calls itselfPlyMove Storyboard
  • Server version2.0.0
  • Protocol version2025-03-26

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 207 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: turn a chess game and learner rating into a teaching storyboard; explain why a candidate move fails for a given rating; compare plausible human moves with the objectively best move.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "turn a chess game and learner rating into a teaching storyboard", the likely first call is build_game_storyboard.
  • For "explain why a candidate move fails for a given rating", the likely first call is compare_moves.
  • For "compare plausible human moves with the objectively best move", the likely first call is compare_moves.

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 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer262 ms
  • Space in an agent's context≈ 1,055 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 97 of 100
  • Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 6

What an agent can do with it

  • can do · turn a chess game and learner rating into a teaching storyboard
  • can do · explain why a candidate move fails for a given rating
  • can do · compare plausible human moves with the objectively best move

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 offers6 tools · read 2026-10-25
  • build_game_storyboard

    Build a verified Elo-aware game storyboard: opening, story arc, ranked moments, branches, and main lesson. Read-only analysis — does not modify user files or external systems.

  • explain_game

    Legacy alias for build_game_storyboard — Elo-aware game storyboard (read-only analysis; does not write files).

  • find_teaching_moments

    Legacy alias for build_game_storyboard — ranked storyboard chapters from a PGN (read-only analysis).

  • explain_position

    Explain a single position for a target learner Elo (read-only analysis).

  • compare_moves

    Compare candidate moves at a position for a learner (read-only analysis).

  • analyze_what_if

    Analyze a user-requested alternative at a mainline decision point: legal SAN validation, Stockfish continuation, Maia naturalness, teaching point, and annotated RAV PGN (read-only).

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.plymove.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.